WO2025212785A1

WO2025212785A1 - Excess energy exchange

Info

Publication number: WO2025212785A1
Application number: PCT/US2025/022765
Authority: WO
Inventors: SaLisa Berrien
Original assignee: Individual
Current assignee: Individual
Priority date: 2024-04-02
Filing date: 2025-04-02
Publication date: 2025-10-09
Anticipated expiration: 2026-10-02

Abstract

In some embodiments, a method for exchanging excess energy capacity includes: receiving historical energy usage data from a gateway device installed at a first customer site; using a AI model to forecast future energy capacity of the first customer site; determining a recommendation of sellable energy capacity for the first customer site based on the forecasted future energy capacity; receiving a sell request to sell energy capacity from a user device associated with the first customer site; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site; assessing the aggregated capacity pool to determine a match to the buy request; and sending a notice to the first customer site and/or the second customer site to indicate an exchange of energy capacity between the first or the second customer site and the capacity pool.

Description

EXCESS ENERGY EXCHANGE

CROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of U.S. Provisional Application No. 63/572,953 filed on April 2, 2024, which is incorporated herein by reference in its entirety.

TECHNICAL FIELD

[0002] The present disclosure relates generally to energy optimization, and particularly to managing energy capacity in a power network.

BACKGROUND

[0003] In the U.S., a staggering 19 million commercial businesses are wasting 30% of the energy they pay for, and do not even know it. This is largely due to the lack of visibility into real-time using and billing structure of utilities (e.g., utility companies). For example, a demand charge may be imposed on customers whose energy demand reach a “spike” that exceeds their normal demand. Demand charges are calculated based on the maximum amount of power that a customer uses in any interval during the billing cycle, and are applied to the full billing cycle. Demand charges are a way for utilities to recover some of the costs associated with providing sufficient electricity generation and distribution capacity to their customers. By basing a portion of a customer’s electricity bill on their highest level of electricity demand, the utility is attempting to distribute more of the costs associated with building and maintaining the capacity of its power system to those who use it most.

[0004] Essentially, customers who happen to have had a high power demand (even for a short period of time) end up paying the peak demand charges which the utilities then use to pay for the cost of delivering sufficient electricity generation to meet the customer’s high power demand. Yet, in the existing infrastructure, utilities have no way of knowing when/if a customer may have a high power demand at a given time; and customers could not avoid high power demand when there is business necessity (e.g., when a special event is being planned at a venue). When a customer does incur a peak demand charge that is charged for a full billing cycle, it often does not have a need for high energy demand again soon. As a result, utilities generate excess energy capacity that are never fully utilized by the customers.

SUMMARY

[0005] In some aspects, a method for exchanging excess energy capacity on a power network includes: receiving, at a first time, historical energy usage data from a gateway device installed at a first customer site on the power network, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the first customer site; using a trained artificial intelligence (Al) model to forecast future energy capacity of the first customer site that may occur during a time period after the first time; determining a recommendation of a sellable energy capacity for the first customer site based at least in part on the forecasted future energy capacity of the first customer site; receiving a sell request to sell energy capacity from a user device associated with the first customer site, the sell request indicating an energy capacity to sell; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site on the power network, the buy request indicating an energy capacity in need; assessing the capacity pool to determine a match to the buy request from the capacity pool; and sending a notice to the user device associated with the first customer site indicating an exchange of energy capacity between the first customer site and the capacity pool has been made, and/or a notice to the user device associated with the second customer site indicating an exchange of energy capacity between the second customer site and the capacity pool has been made.

[0006] In some aspects, a system for exchanging excess energy capacity on a power network includes one or more processors configured to perform operations comprising: receiving, at a first time, historical energy usage data from a gateway device installed at a first customer site on the power network, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the first customer site; using a trained artificial intelligence (Al) model to forecast future energy capacity of the first customer site that may occur during a time period after the first time; determining a recommendation of a sellable energy capacity for the first customer site based at least in part on the forecasted future energy capacity of the first customer site; receiving a sell request to sell energy capacity from a user device associated with the first customer site, the sell request indicating an energy capacity to sell; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site on the power network, the buy request indicating an energy capacity in need; assessing the capacity pool to determine a match to the buy request from the capacity pool; and sending a notice to the user device associated with the first customer site indicating an exchange of energy capacity between the first customer site and the capacity pool has been made, and/or a notice to the user device associated with the second customer site indicating an exchange of energy capacity between the second customer site and the capacity pool has been made.

[0007] In some aspects, a non-transitory computer readable medium containing program instructions that, when executed, cause one or more processors to perform operations comprising: receiving, at a first time, historical energy usage data from a gateway device installed at a first customer site on the power network, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the first customer site; using a trained artificial intelligence (Al) model to forecast future energy capacity of the first customer site that may occur during a time period after the first time; determining a recommendation of a sellable energy capacity for the first customer site based at least in part on the forecasted future energy capacity of the first customer site; receiving a sell request to sell energy capacity from a user device associated with the first customer site, the sell request indicating an energy capacity to sell; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site on the power network, the buy request indicating an energy capacity in need; assessing the capacity pool to determine a match to the buy request from the capacity pool; and sending a notice to the user device associated with the first customer site indicating an exchange of energy capacity between the first customer site and the capacity pool has been made, and/or a notice to the user device associated with the second customer site indicating an exchange of energy capacity between the second customer site and the capacity pool has been made.

BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Additional embodiments of the disclosure, as well as features and advantages thereof, will become more apparent by reference to the description herein taken in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale. Moreover, in the figures, like-referenced numerals designate corresponding parts throughout the different views.

[0009] FIG. l is a schematic diagram of an example system for excess energy exchange, according to some embodiments.

[0010] FIG. 2A illustrates an example of user energy demand and demand charge which may be related to peak usage, according to some embodiments.

[0011] FIG. 2B illustrates an example of a user’s energy demand and high demand period, according to some embodiments.

[0012] FIG. 2C illustrates an example of a user anticipated high demand period, according to some embodiments.

[0013] FIG. 3 A is a flow diagram of an example process of energy capacity recommendation, according to some embodiments.

[0014] FIG. 3B is an example of current energy capacity and forecasted energy capacity as an intermediate result for energy capacity recommendation, according to some embodiments.

[0015] FIG. 3C is an example of forecasted energy capacity showing potential excess energy capacity that may be available for exchange, according to some embodiments.

[0016] FIG. 4 shows an example of how energy capacity available to sell is calculated, according to some embodiments.

[0017] FIG. 5 is a flow diagram of an example process of capacity buying recommendation for excess energy capacity exchange, according to some embodiments. [0018] FIG. 6 is a flow diagram of an example process of capacity matching for excess energy capacity exchange, according to some embodiments.

[0019] FIG. 7 is an example screen for energy capacity buying which may be displayed at a user device, according to some embodiments.

[0020] FIG. 8 is an example screen for energy capacity selling which may be displayed at a user device, according to some embodiments.

[0021] FIG. 9 is a flow diagram of an example process of load management, according to some embodiments.

[0022] FIG. 10 depicts an example of internal hardware that may be included in any electronic device or computing system that may be used to perform any of the aspects of the techniques and embodiments disclosed herein, according to some embodiments.

DETAILED DESCRIPTION

[0023] To overcome various shortcomings and technical issues in the existing utilities infrastructure, the inventors of the present disclosure have developed technical solutions that allow customers to exchange excess energy capacity by sharing with businesses that need more capacity. Examples of energy capacity may include amount of power that may be desired at a customer site. Energy capacity may be measured in kW. Systems and methods are provided that analyze customers’ historical energy usage and demand, for example, using artificial intelligence/machine learning algorithms. In some embodiments, the system may include gateway devices installable at each customer’s site to collect and monitor the customer’s energy use and demand. The system may predict customers’ future energy capacity and demand based on the customer’s historical energy usage and other information such as weather and holiday schedule. In some embodiments, the system may identify future excess capacity which the customers can sell and how much savings they can recoup from payment for the peak capacity. In some embodiments, the system may enable a customer to buy energy capacity for future use if a higher energy demand is anticipated.

[0024] In some embodiments, the system may facilitate sharing of pooled energy capacity between customers who want to buy capacity and customers who want to sell capacity. Using aggregated capacity pool, the system may match a buying customer with one or more selling customers’ capacity in the capacity pool and facilitate the exchange of capacity. In some embodiments, when a customer has sold future capacity, the system may monitor the customer’s energy usage to make sure that the sold incremental capacity is preserved, which prevents the customer from running a capacity deficit against what has already been committed. For example, the system may send an alert to the customer if the customer is about to reach a new peak demand. The system may ask the customer to activate a load management plan, in which the system may automate the registered assets of the customer in the system to reduce the customer’s energy load. In some embodiments, the gateway device of the system may be coupled to the customer’s building management system (BMS) to control the energy assets at the customer site.

[0025] In some embodiments, the system may also communicate with utilities about the exchanges of capacity amongst the customers. This information will allow customers to get proper credit from the utilities for buying shared energy capacity and avoid demand charges from the utilities. In turn, the energy capacity exchange information enables utilities to anticipate and meet future customer demands by minimizing the unused capacity amongst their customers.

[0026] The various embodiments in the present disclosure provide advantages over existing systems in that they can monitor and track each customer’s energy usage via a gateway device and communication network; recommend customers buying or selling options for excess capacity using artificial intelligence; and facilitate sharing of energy capacity through an aggregated capacity repository and Al-based matching algorithm. Further, the gateway device is integrated with a customer’s building management system to control the energy assets at the customer site in accordance with a load management threshold as the result of capacity selling.

[0027] As a result of the various solutions provided in the present disclosure, a customer may sell its energy capacity to recoup a portion of the cost of its higher demand charge. A customer may also buy capacity to meet its anticipated high power demand and avoid an increased demand charge. Utility has an alternative for capacity planning and can use the reserve margins for improved reliability and resilience. Thus, these solutions provide improved sustainability outcomes for organizations and the environment by reducing carbon emission. [0028] For the purposes of promoting an understanding of the principles of the present disclosure, reference will now be made to the embodiments illustrated in the drawings, and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended. It should be appreciated that the embodiments described herein may be implemented in any of numerous ways. Examples of specific implementations are provided below for illustrative purposes only. It should be appreciated that these embodiments and the features/capabilities provided may be used individually, all together, or in any combination of two or more, as aspects of the technology described herein are not limited in this respect.

[0029] FIG. 1 is a schematic diagram of an example exchange system 100 for excess energy capacity exchange, according to some embodiments. System 100 may be configured to communicate with a plurality of customer sites, e.g., 106-1, 106-2 etc. via a communication network. Each customer site, e.g., 106-1, may install a gateway device 110. In some embodiments, gateway device 110 may include one or more sensors to monitor the energy usage and other conditions of a customer site. For example, gateway device 110 may include pulse output transducers to measure gas, electricity, and/or water usage from existing meters and sensors at the customer site. In some examples, gateway device 110 may collect data about the temperature and humidity at the customer site. In some other examples, gateway device may include additional power meters to measure energy usage at the customer site.

[0030] In some embodiments, gateway device 110 may be coupled to a building management system (BMS) 108. The communication between the gateway device 110 and BMS 108 may be bidirectional. For example, gateway 110 may receive data about energy activities of energy assets at the customer site (e.g., a building) from BMS 108. Gateway 110 may also send data to BMS to control one or more energy assets in the building, for example, to reduce the load of an energy asset.

[0031] Each customer site may have a communication interface installed and configured to communicate with system 100. For example, the customer site 106-1 and system 100 may each have a wired or wireless interface (e.g., Wi-Fi, or Ethernet) to allow them to communicate with each other wired or wirelessly. In some variations, system 100 may be residing on the cloud, and each customer site (e.g., 106-1, 106-2, etc.) may communicate with the cloud wired or wirelessly.

[0032] The communication network allows gateway 110 at each customer site to transmit data about the energy usage at the customer site to system 100 for further processing and recommendation. Conversely, gateway 110 may receive data (e.g., command for controlling energy assets at the customer site) from system 100. In some embodiments, each customer site may be associated with a software application 118 (e.g., an application which can be executed at the customer site or a mobile device) that communicates with system 100. For example, application 118 may be communicative with system 100 for the customer to conduct transactions of exchanging energy capacity. Additionally, application 118 may receive an alert or recommendation from system 100 about energy capacity and communicate to system 100 with a response.

[0033] In FIG. 1, system 100 may include one or more processors 120 configured to facilitate exchange of excess/flexible energy capacity among the customers, which results in reduce demand on the electric grid from sharing capacity instead of setting new peak demands. In some embodiments, system 100 learns the energy behavior of the customer that is sharing its excess energy capacity. For example, system 100 may receive real-time data about the energy usage of the customer through gateway 110, and learns the customer energy behavior based on the historical energy usage. System 100 then predicts what future peak demand for that customer will be. In non-limiting examples, system may predict a customer’s future energy capacity for six months out or any suitable time period.

[0034] If potential energy waste is identified, the system may recommend the customer to share (e.g., selling) its energy waste with another user thereby reducing the need for more power needed on the distribution network. Examples of energy waste include the energy that the customer paid for (e.g., via demand charge) but not utilized. Additionally, and/or alternatively, customer may donate its energy waste to energy equity 116. Similarly, system 100 or utility 112 may also donate capacity to energy equity 116.

[0035] In some embodiments, system 100 may include an energy asset registry 102, which stores information about the energy assets the customer has registered with the system. Examples of energy assets include non-renewable energy equipment (e.g., heat pump, HVAC, lighting, appliances, office equipment), renewable energy equipment (e.g., solar, wind, water, biomass powered equipment), or battery storage equipment (e.g., EV charging devices, load management batteries), or any suitable energy consumption equipment at the customer site. In some examples, a customer (e.g., 106-1) may upload information about the energy asset registry 102 via the communication network. Examples of the uploaded information include nameplate capacity, vintage, and information about the efficiency of the assets at the customer site. The energy asset information may be uploaded by customers to the registry 102 via gateway device 100 or application 118, in some examples. This information enables the system 100 to have a holistic view of the customer energy portfolio and needs, perform full analytics on the customer energy portfolio, and provide improved and more accurate forecast of the customer’s energy capacity and recommendations, as will be described in detail further herein.

[0036] In some embodiments, system 100 may facilitate a customer to buy energy capacity for future energy use. In some scenarios, a customer may anticipate an energy demand increase or a spike due to anticipated activities, such as a conference or special events, increasing production at a manufacturer, upcoming weather conditions. Instead of triggering potential demand charges, the customer may have a need to buy excess capacity from another customer so that demand charge can be avoided. In some embodiments, system 100 may enable a customer to buy excess capacity from others, e.g., through a transaction as shown in FIG. 7. System 100 may receive a request from the customer to buy energy capacity. In response, system 100 may find another customer who has excess energy capacity to sell and enable the customer to share excess energy capacity from that another customer.

[0037] The sharing of the customers’ energy capacity may be performed in a peer-to-peer manner in that the customers can share (e.g., buy or sell) energy capacity via an aggregated capacity pool 104 in system 100, without moderation by the utility 112. This is performed through the capacity matching and aggregated capacity pool 104 of system 100. In non-limiting examples, system 100 may maintain a list of available excess energy capacity from customers who have excess energy capacity to sell (e.g., through recommendation from system 100). Upon receiving a request to buy energy capacity, system 100 may use the information in the request (e.g., the amount of energy capacity the buyer needs, the price the buyer is willing to pay) to search for matching excess energy capacity.

[0038] In some embodiments, system 100 may implement a matching algorithm using Al models to match a buying customer’s request to buy energy capacity to a selling customer who has excess capacity to sell. Once a match is found, system 100 may communicate with utility 112 and share such transaction information with utility 112. For example, utility 112 may receive information about customers’ sharing of energy capacity from system 100, e g., through an API to the utility’s billing system. Based on this data, utility 112 may apply credits to the buying customers who bought capacity so that the buying customers will not be charged of demand charge. The selling customers may get paid for selling the energy capacity. Additionally, utility 112 may forecast needs on their distribution networks.

[0039] In some embodiments, system 100 may be configured to manage the load of energy assets at a customer site, for example, a selling customer, to preserve the capacity sold to other customers. In some examples, system 100 monitors the energy usage of a customer (e.g., via gateway device 110) in real-time. System 100 may assess whether a customer is approaching a load management threshold (LMT) for energy demand. In response to determining that the customer is approaching the LMT, system 100 may sent an alert to the customer (e.g., via application 118 associated with the customer) and/or activate load management. Alternatively and/or additionally, system 100 may control one or more energy assets (e.g., via gateway device 110 and BMS 108) to reduce the load at the customer site so that the LMT is not exceeded.

[0040] In some embodiments, BMS 108 may be optional. For example, if a customer elects to only buy shared capacity, they would need to set up their account on the system to receive communication from the system about the transactions.

[0041] In FIG. 1, although only customer site A (106-1) and customer site B (106-2) are shown, it is appreciated that additional customer sites each having a similar configuration as customer site 106-1 may communicate with system 100. Additionally, each customer site 106 may be associated with a commercial, industrial or residential customer. Although it is shown the solution is focused within the utility for leveraging the underutilized energy capacity, it is appreciated customers can trade and gift credits outside the utility boundaries. As such, utility 112 may include multiple utilities.

[0042] FIG. 2A illustrates an example of user energy demand and demand charge which may be related to peak usage. In FIG. 2A, demand charge from the utility is based on the peak usage (e.g., dotted line) of a customer and billed for the full billing cycle. FIG. 2B illustrates an example of customer A’s energy demand and high demand period. Customer A has a big conference Sept 11-15 that causes a 500 kW average spike in load. The 500 kW spike triggers a higher demand charge from the utility. The demand charge applies to the full month, even though Customer A does not need the extra 500 kW between Sept 15-30. Customer A wants to recoup some of the costs from the high demand charge. FIG. 2C illustrates an example of a user anticipating high demand period. Customer B has a big conference Sept 18-22 that it anticipates will cause a 100 kW average spike in load. Customer B wants to avoid a higher demand charge from their utility for the month of September.

[0043] FIG. 3A is a flow diagram of an example process 300 of energy capacity recommendation. In some embodiments, process 300 may be implemented in system 100. Process 300 may include receiving historical energy usage data from gateway device, at act 302. For example, system 100 may receive real-time data about the customer energy usage via the gateway device 110 installed at a customer site. As described above, the energy usage data may include readings from utility meters at the customer site. Examples of energy usage data that may be received at system 100 may include energy demand (e.g., kW), amount of energy consumed (e.g., kWh), time of the day, temperature, and baseline data for measurement etc.

[0044] Additionally, process 300 may receive auxiliary information, at act 304. For example, system 100 may receive information about the weather of the region in which the customer site is located, the conditions (e.g., temperature, humidity etc.) of the customer site. Additionally, system 100 may receive information about the customer holiday schedule (for example, factory at customer site will be closing during Christmas holiday week). It is appreciated that the auxiliary information may additionally be obtained from other available data sources such as national weather archive for weather information (e.g., historical weather information), national holiday schedule based on the country code (e.g., ISO code) of the country where the meters are located. In some embodiments, the energy usage information from gateway device 110 may be time- stamped so that corresponding auxiliary information (e.g., weather, holiday schedule) may be obtained.

[0045] Process 300 may proceed to act 306 to forecast the customer’s future energy capacity, using an artificial intelligence (Al) model, the historical energy usage and other information related to the customer site. Various Al models may be used. For example, process 300 may use a trained time series model to predict daily peak demands for a future time window, e.g., 30 days, 60 days, 180 days or any suitable number of days. The model may be trained using collected training energy usage data from multiple customers that provide sufficient amount of historical demand to fit the model. In some examples, at least 60 days of historical data may be used. Any known techniques may be used to train the model.

[0046] In some embodiments, the model may be used to forecast a future energy capacity for the user based on the historical energy usage of that user. For example, the historical energy usage may be real-time energy usage data received from the customer (e.g., via gateway device 110 in FIG. 1). Other input to the model may include first date for which a forecast is needed, auxiliary information about the energy usage at the customer site as described above, and the length of the forecast period (e.g., 30 days, 180 days, or any suitable length).

[0047] In some embodiments, the customer’s energy assets (which drive the energy demand) are used by the system to better understand how the peak demand is being created to improve forecasting. For example, information about the registered assets at a customer site is used in forecasting that customer’s future energy capacity, where the forecast includes the maximum kW (peaks).

[0048] The output of the model may include forecasted energy peak demands in the time window defined by the user (e.g., 180 days). It is appreciated that other Al models may be trained and used to forecast customer future energy capacity (including energy peak demands).

[0049] FIG. 3B is an example of current energy use (curve in solid lines) and forecasted energy capacity (curve in dashed lines) to be used for energy capacity recommendation, as will be further described. FIG. 3C is an example of forecasted energy capacity showing potential excess energy capacity that may be available for exchange, according to some embodiments. As shown in FIG. 3C, the forecasted energy capacity (plot in dashed line) indicates areas (opportunity) for sellable energy capacity. The determination (recommendation) of sellable energy capacity is further described herein, with reference to FIG. 3A.

[0050] In FIG. 3A, process 300 may further include determining excess capacity based on the forecasted energy capacity, at act 308. In act 308, first, a time window is determined depending on the customer’s energy use rate. For example, a uniform time window (e.g. a time of use window that is common for most utilities) is used for all time of use rate customers and a full-day time window (e.g. non-time of use window) is used for flat rate customers to calculate baseline. This time window represents the peak hours, ensuring alignment with most utilities’ high-demand periods. Time of Use rates calculate the peak demand during specified windows when the utility system peaks. The rates during this time period are higher than the flat rate.

[0051] In act 308, the system may determine an overall peak load a baseline peak load for a forecasted time period, e.g., 30 days, within the appropriate time window. Whereas a flat rate window takes all hours into account, the Time of Use window only takes peak hours into account. The overall peak load may be determined as the highest peak load for each customer during the forecasted 30 days within the appropriate time window. The baseline load may be determined by computing the average of a number of highest peak loads (e.g., 10 peaks) within the same period. This would be considered a reliable baseline.

[0052] In act 308, the system may determine excess capacity for a customer. Excess capacity may represent the capacity beyond what the customer regularly uses. Excess capacity may be calculated as the difference between the Overall Peak Load and the Baseline Load, such that:

Excess Capacity = Overall Peak Load-Baseline Load

[0053] Process 300 may include determining sellable capacity for the customer, at act 310. In some embodiments, the sellable capacity may be determined as a percentage of the excess capacity the customer may sell considering a safety buffer for the customer's operational needs. For example, the entire excess capacity of a customer in the future may not be actually available to share (or sell) because the customer is continuing using the energy and its future energy usage may fluctuate. Selling a percentage of the excess capacity will permit the user to preserve such sellable capacity once the sellable capacity is sold. Process 300 may further include providing the recommendation of sellable capacity to the customer, at act 312.

[0054] FIG. 4 shows an example of how energy capacity available to sell is calculated, according to some embodiments. In FIG. 4, the customer’s peak load is 5000 kW, the baseline is 4500 kW, and the excess capacity is 500 kW (peak - baseline). In a nonlimiting example, the recommended sellable capacity is 80% of the excess capacity, which is 400 kW. In this example, the nameplate capacity of customer registered energy assets (e.g., 5200 kW) is not considered. In some embodiments, the energy capacity that the customer has already sold may be considered. For example, if the customer has already sold lOOkW energy capacity, then the energy capacity available to sell in the above example may be reduced by 100 kW, which is 300 kW.

[0055] FIG. 5 is a flow diagram of an example process 500 of capacity buying recommendation for excess energy capacity exchange. In some embodiments, process 500 may be implemented in system 100. Process 500 may start with acts 502, 504, 506, which are respectively similar to acts 302, 304, 306 (FIG. 3A), and the descriptions of these acts are not repeated herein. Process 500 may further include determining capacity shortage based on the forecasted energy capacity, at act 508. For example, the forecasted energy capacity may indicate that a peak demand is expected that is likely to trigger a demand charge, thus a capacity shortage is likely. In such case, process 500 may proceed to act 510 to determine the capacity needed based on the capacity shortage. In nonlimiting examples, the capacity needed to buy may be based on a difference between the energy demand threshold currently set for the customer for triggering demand charge and the projected peak demand. Subsequently, process 500 may proceed to act 512 to send the recommendation to the customer, with suggested capacity to buy.

[0056] FIG. 6 is a flow diagram of an example process 600 of capacity matching for excess energy exchange. In some embodiments, process 600 may be implemented in system 100 (FIG. 1). Process 600 may include receiving buy request to buy capacity, at act 602. For example, buy request may be recommended by the system (e.g., process 500 in FIG. 5) and confirmed by the customer. Process 600 may further assess the pooled capacity (e.g., capacity repository 104 in FIG. 1) and allocate the requested capacity using an Al model, at act 604. In some examples, allocation of the capacity may be performed on a first-come-first-serve basis. In some examples, allocation may be based on information in the sell requests and the buy request, such as the amount of energy capacity to buy and sell, the start day/time and end day/time to buy or sell in the buy or sell request. Additionally, the input to the Al model may include the aggregated forecast of energy capacity for the selling customers of the sell requests and the forecast of energy capacity for the buying customer of the buy request. Process 600 may further determine a match from the pooled capacity, at act 606. For example, act 606 may identify the selling customer ID and their capacity to sell, which matches the amount of capacity in the buy request. Upon a match being found, process 600 may proceed to act 608 to send a match notice to the customer. A capacity exchange transaction is completed.

[0057] In some embodiments, matching (e.g., acts 604, 606) may be performed using an Al model to optimize the allocation of capacity for the buy requests. In some embodiments, a request to buy capacity may be partially fulfilled if there are not sufficient capacities in the capacity pool. In that case, the system may notify the customer that a portion of the capacity to buy is fulfilled.

[0058] In some variations, processes 300, 500, and 600 (in FIGS. 3A, 5, 6) respectively for sell recommendation, buy recommendation, and matching capacity may be performed based on different energy resource types. For example, a customer may select to buy capacity for certain energy resource types (e.g., non-renewable, renewable, or battery storage) because these different resource types may have different rates. Thus, the system may recommend a customer to buy or sell capacity for certain resource type(s). Similarly, the system may perform capacity matching based on resource type(s).

[0059] FIG. 7 is an example screen 700 for energy capacity buying which may be displayed at a user device. In some embodiments, screen 700 may include information about buy options and is generated by system 100. Screen 700 may be displayed on a customer’s system. In area 702, customer is presented with different types of resources, e g., non-renewable, renewable, and battery storage. The customer may be presented with recommended buy capacity. Additionally, and/or alternatively, the customer may fill in the capacity to buy in each resource type and/or override the recommended capacity.

[0060] In FIG. 7, area 704 may display the customer location (e.g., address). Area 706 may be co-displayed with area 702. Area 706 may display a map showing the neighborhood of the customer or customers belonging to the same grid. Area 706 may display where capacity is available for sell and the type of capacity available for sell. For example, all available capacity for sell are displayed by icons on the map, where these icons may have different symbols or colors depending on the type of resource. Alternatively, upon a user selecting a type of capacity, area 706 may display all the available capacity for that type with a respective icon.

[0061] FIG. 8 is an example screen 800 for energy capacity selling which may be displayed at a user device. In some embodiments, screen 800 may include information about sell options and is generated by system 100. Screen 800 may be displayed on a customer’s system. In area 802, the system initially recommended capacity to sell may be displayed. In some embodiments, the user may click a recommendation button 806 to prompt the system at any time to recommend energy capacity to sell. The system may determine sellable capacity and display the recommendation (including recommended energy capacity to sell, and/or start day/time and end day/time) to the user in area 804. The customer may select to accept the recommended values or override the recommended values in area 804. Additionally, the system may calculate and display the dollar amount that the customer may recoup by selling the capacity in area 810. This calculation may be based on the amount of capacity to sell, the time/day to sell, the type of resource, and utility demand rate. Additionally, when selling energy capacity, the user may opt for load management program by clicking asset management box 808. This is further explained in detail in FIG. 9.

[0062] In some embodiments, once a customer has sold excess capacity, the customer should avoid using that incremental capacity so that the sold capacity that the customer has committed can be preserved. This can be done by the system’s load management capability. FIG. 9 is a flow diagram of an example process 900 of load management. In some embodiments, process 900 can be implemented in system 100. In some embodiments, process 900 may be implemented upon user opting in for load management (e g., selecting asset management option at 808 in FIG. 8). Process 900 may include receiving energy usage data from customer, at act 902. In non-limiting examples, energy usage data may be transmitted from the customer’s gateway device (e.g., 110 in FIG. 1), such as in a manner described in embodiments in FIG. 1.

[0063] Process 900 may identify constraints, at act 904. For example, system notes that the customer has sold capacity and how much capacity has been sold. Process 900 may determine the constraints based on the amount of capacity the customer has sold. In some examples, the constraints may be a delta amount of capacity that is available for sale.

[0064] Process 900 may further include determining load management threshold (LMT) based on energy usage data, at act 906. For example, act 906 may compute the average kW values of peak demands (e.g., top 10 peak demands, or any suitable number of peak demands) from forecasted energy capacity. LMT may be used to monitor a customer’s current energy use against a limit above which the customer may likely encroach on the capacity it offered up to share, leaving a deficit in capacity.

[0065] As such, load management in system 100 may be activated when the customer’s energy capacity is approaching LMT. For example, system 100 may continuously monitor the customer’s energy capacity (e.g., based on the energy data obtained from act 902). If the customer’s energy capacity approaches the LMT (e.g., has reached a percentage, e.g., 90% of LMT), then the system may activate load management, at act 908. Optionally, the system may send an alert to the customer (e.g., customer 106 in FIG. 1) before the LMT is reached (e.g., 80% LMT), where the alert indicates that the user is approaching the LMT. In response, the customer may agree to activate load management, if the customer has already enrolled in the load management program. Alternatively, the customer may manually execute the load management program.

[0066] Upon activating the load management, process 900 may proceed to act 910 to control one or more registered assets at the customer site. Information about the registered assets may be obtained from the energy asset registry (e.g., 102 in FIG. 1). In non-limiting examples, these registered assets may be modulated down (e.g., at a low energy mode) or turned off. The control of the registered assets at the customer site may be implemented via the BMS system (e.g., 108) and the gateway device (e.g., 110) installed at the customer site, as previously described. [0067] FIG. 10 depicts an example of internal hardware that may be included in system 100 (e.g., on the cloud) or at any customer site (e.g., through the application downloaded form the Internet) in any electronic device or computing system that may be used to perform any of the aspects of the techniques and embodiments in FIGS. 1-9. An electrical bus 1000 serves as an information highway interconnecting the other illustrated components of the hardware. Processor 1005 is a central processing device of the system, configured to perform calculations and logic operations required to execute programming instructions. As used in this document and in the claims, the terms “processor” and “processing device” may refer to a single processor or any number of processors in a set of processors that collectively perform a process, whether a micro-controller, central processing unit (CPU) or a graphics processing unit (GPU) or a combination thereof. Read only memory (ROM), random access memory (RAM), flash memory, hard drives, and other devices capable of storing electronic data constitute examples of memory devices 1025. A memory device, also referred to as a computer-readable medium, may include a single device or a collection of devices across which data and/or instructions are stored. The memory device may include, for example, 1026 for storing energy asset registry and/or capacity repository as described in embodiments in FIGS. 1-9.

[0068] An optional display interface 1030 may permit information from the bus 1000 to be displayed on a display device 1035 in visual, graphic, or alphanumeric format. An audio interface and audio output (such as a speaker) also may be provided.

Communication with external devices may occur using various communication ports 1040 such as a transmitter and/or receiver, antenna, an RFID tag and/or short-range, BLE, or near-field communication circuitry. A communication port 1040 may be attached to a communications network, such as the Internet, a local area network, Wi-Fi, or a cellular telephone data network for facilitating communications between system 100 and systems/gateway devices at customer sites described in FIG. 1.

[0069] The hardware may also include a user interface sensor 1045 that allows for receipt of data from input devices 1050 such as a keyboard, a mouse, a joystick, a touchscreen, a remote control, a pointing device, a video input device, and/or an audio input device, such as a microphone. Digital image frames may also be received from an imaging capturing device 1055 such as a video or camera that can either be built-in or external to the system. Other environmental sensors 1060, such as a location sensor and/or a temperature sensor, may be installed on system and communicatively accessible by the processor 1005, either directly or via the communication ports 1040.

[0070] Various inventive concepts may be embodied as one or more methods, of which examples have been provided. The acts performed as part of a method may be ordered in any suitable way. Accordingly, embodiments may be constructed in which acts are performed in an order different than illustrated, which may include performing some acts simultaneously, even though shown as sequential acts in illustrative embodiments.

[0071] Having described several embodiments of the invention in detail, various modifications, combinations, and improvements will readily occur to those skilled in the art. Such modifications, combinations and improvements are intended to be within the spirit and scope of the invention. Accordingly, the foregoing description is by way of example only, and is not intended as limiting.

Claims

CLAIMS What is claimed is:

1. A method for exchanging excess energy capacity on a power network, the method comprising: receiving, at a first time, historical energy usage data from a gateway device installed at a first customer site on the power network, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the first customer site; using a trained artificial intelligence (Al) model to forecast future energy capacity of the first customer site that may occur during a time period after the first time; determining a recommendation of a sellable energy capacity for the first customer site based at least in part on the forecasted future energy capacity of the first customer site; receiving a sell request to sell energy capacity from a user device associated with the first customer site, the sell request indicating an energy capacity to sell; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site on the power network, the buy request indicating an energy capacity in need; assessing the capacity pool to determine a match to the buy request from the capacity pool; and sending a notice to the user device associated with the first customer site indicating an exchange of energy capacity between the first customer site and the capacity pool has been made, and/or a notice to the user device associated with the second customer site indicating an exchange of energy capacity between the second customer site and the capacity pool has been made.

2. The method of claim 1, further comprising: receiving, at a second time, historical energy usage data from a gateway device installed at the second customer site, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the second customer site; using the trained Al model to forecast future energy capacity of the second customer site that may occur during a time period after the second time; determining a recommendation of an energy capacity to buy for the second customer site based at least in part on the forecasted future energy capacity of the second customer site; and transmitting the recommendation of the energy capacity to buy to the user device associated with the second customer site.

3. The method of claim 1, further comprising: receiving, auxiliary information associated with the first customer site, the auxiliary information including one or more of: weather of a location in which the first customer site resides or a holiday schedule of a country in which the first customer site is located; wherein determining the recommendation of the sellable energy capacity for the first customer site is additionally based on the auxiliary information associated with the first customer site.

4. The method of claim 1, further comprising: transmitting a record for the exchange of energy capacity between the second customer site and the capacity pool to a utility of the power network to cause the utility to apply billing credit to the second customer site, the billing credit based at least in part on an amount of energy capacity in the exchange of energy capacity between the second customer site and the capacity pool.

5. The method of claim 1, wherein the recommended sellable energy capacity is determined based at least in part on a difference between an overall peak load and a baseline peak load of the first customer site, wherein: the overall peak load is a highest peak load of the forecasted future energy capacity of the first customer within a time window; and the baseline peak load is an average of a number of highest peak loads of the forecasted future energy capacity of the first customer within the time window.

6. The method of claim 1, further comprising: determining a load management threshold for the first customer site based at least in part on an amount of energy capacity in the exchange of energy capacity between the first customer site and the capacity pool; receiving real-time energy usage data from the gateway device at the first customer site; determining, based on the real-time energy usage data, whether energy capacity for the first customer site is approaching the load management threshold; and in response to determining that the energy capacity for the first customer site has approached the load management threshold, activating a load management program.

7. The method of claim 6, wherein activating the load management program comprises: transmitting control command to the gateway device at the first customer site to cause one or more energy assets at the first customer site to change operation state so that load at the first customer site is reduced.

8. A system for exchanging excess energy capacity on a power network, the system comprising one or more processors configured to perform operations comprising: receiving, at a first time, historical energy usage data from a gateway device installed at a first customer site on the power network, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the first customer site; using a trained artificial intelligence (Al) model to forecast future energy capacity of the first customer site that may occur during a time period after the first time; determining a recommendation of a sellable energy capacity for the first customer site based at least in part on the forecasted future energy capacity of the first customer site; receiving a sell request to sell energy capacity from a user device associated with the first customer site, the sell request indicating an energy capacity to sell; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site on the power network, the buy request indicating an energy capacity in need; assessing the capacity pool to determine a match to the buy request from the capacity pool; and sending a notice to the user device associated with the first customer site indicating an exchange of energy capacity between the first customer site and the capacity pool has been made, and/or a notice to the user device associated with the second customer site indicating an exchange of energy capacity between the second customer site and the capacity pool has been made.

9. The system of claim 8, wherein the operations further comprise: receiving, at a second time, historical energy usage data from a gateway device installed at the second customer site, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the second customer site; using the trained Al model to forecast future energy capacity of the second customer site that may occur during a time period after the second time; determining a recommendation of an energy capacity to buy for the second customer site based at least in part on the forecasted future energy capacity of the second customer site; and transmitting the recommendation of the energy capacity to buy to the user device associated with the second customer site.

10. The system of claim 8, wherein the operations further comprise: receiving, auxiliary information associated with the first customer site, the auxiliary information including one or more of: weather of a location in which the first customer site resides or a holiday schedule of a country in which the first customer site is located; wherein determining the recommendation of the sellable energy capacity for the first customer site is additionally based on the auxiliary information associated with the first customer site.

11. The system of claim 8, wherein the operations further comprise: transmitting a record for the exchange of energy capacity between the second customer site and the capacity pool to a utility of the power network to cause the utility to apply billing credit to the second customer site, the billing credit based at least in part on an amount of energy capacity in the exchange of energy capacity between the second customer site and the capacity pool.

12. The system of claim 8, wherein the recommended sellable energy capacity is determined based at least in part on a difference between an overall peak load and a baseline peak load of the first customer site, wherein: the overall peak load is a highest peak load of the forecasted future energy capacity of the first customer within a time window; and the baseline peak load is an average of a number of highest peak loads of the forecasted future energy capacity of the first customer within the time window.

13. The system of claim 8, wherein the operations further comprise: determining a load management threshold for the first customer site based at least in part on an amount of energy capacity in the exchange of energy capacity between the first customer site and the capacity pool; receiving real-time energy usage data from the gateway device at the first customer site; determining, based on the real-time energy usage data, whether energy capacity for the first customer site is approaching the load management threshold; and in response to determining that the energy capacity for the first customer site has approached the load management threshold, activating a load management program.

14. The system of claim 13, wherein activating the load management program comprises: transmitting control command to the gateway device at the first customer site to cause one or more energy assets at the first customer site to change operation state so that load at the first customer site is reduced.

15. A non-transitory computer readable medium containing program instructions that, when executed, cause one or more processors to perform operations comprising: receiving, at a first time, historical energy usage data from a gateway device installed at a first customer site on the power network, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the first customer site; using a trained artificial intelligence (Al) model to forecast future energy capacity of the first customer site that may occur during a time period after the first time; determining a recommendation of a sellable energy capacity for the first customer site based at least in part on the forecasted future energy capacity of the first customer site; receiving a sell request to sell energy capacity from a user device associated with the first customer site, the sell request indicating an energy capacity to sell; aggregating a capacity pool with the sell request; receiving a buy request to buy energy capacity from a user device associated with a second customer site on the power network, the buy request indicating an energy capacity in need; assessing the capacity pool to determine a match to the buy request from the capacity pool; and sending a notice to the user device associated with the first customer site indicating an exchange of energy capacity between the first customer site and the capacity pool has been made, and/or a notice to the user device associated with the second customer site indicating an exchange of energy capacity between the second customer site and the capacity pool has been made.

16. The non-transitory computer readable medium of claim 15, wherein the operations further comprise: receiving, at a second time, historical energy usage data from a gateway device installed at the second customer site, wherein the gateway device includes one or more sensors configured to measure energy capacity of one or more energy assets at the second customer site; using the trained Al model to forecast future energy capacity of the second customer site that may occur during a time period after the second time; determining a recommendation of an energy capacity to buy for the second customer site based at least in part on the forecasted future energy capacity of the second customer site; and transmitting the recommendation of the energy capacity to buy to the user device associated with the second customer site.

17. The non-transitory computer readable medium of claim 15, wherein the operations further comprise: receiving, auxiliary information associated with the first customer site, the auxiliary information including one or more of: weather of a location in which the first customer site resides or a holiday schedule of a country in which the first customer site is located; wherein determining the recommendation of the sellable energy capacity for the first customer site is additionally based on the auxiliary information associated with the first customer site.

18. The non-transitory computer readable medium of claim 15, wherein the recommended sellable energy capacity is determined based at least in part on a difference between an overall peak load and a baseline peak load of the first customer site, wherein: the overall peak load is a highest peak load of the forecasted future energy capacity of the first customer within a time window; and the baseline peak load is an average of a number of highest peak loads of the forecasted future energy capacity of the first customer within the time window.

19. The non-transitory computer readable medium of claim 15, wherein the operations further comprise: determining a load management threshold for the first customer site based at least in part on an amount of energy capacity in the exchange of energy capacity between the first customer site and the capacity pool; receiving real-time energy usage data from the gateway device at the first customer site; determining, based on the real-time energy usage data, whether energy capacity for the first customer site is approaching the load management threshold; and in response to determining that the energy capacity for the first customer site has approached the load management threshold, activating a load management program.

20. The non-transitory computer readable medium of claim 19, wherein activating the load management program comprises: transmitting control command to the gateway device at the first customer site to cause one or more energy assets at the first customer site to change operation state so that load at the first customer site is reduced.