[go: up one dir, main page]

WO2024177354A1 - Procédé et système de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau - Google Patents

Procédé et système de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau Download PDF

Info

Publication number
WO2024177354A1
WO2024177354A1 PCT/KR2024/002190 KR2024002190W WO2024177354A1 WO 2024177354 A1 WO2024177354 A1 WO 2024177354A1 KR 2024002190 W KR2024002190 W KR 2024002190W WO 2024177354 A1 WO2024177354 A1 WO 2024177354A1
Authority
WO
WIPO (PCT)
Prior art keywords
energy
nanogrid
load
generation
trading
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/KR2024/002190
Other languages
English (en)
Korean (ko)
Inventor
김도현
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industry Academic Cooperation Foundation of Jeju National University
Original Assignee
Industry Academic Cooperation Foundation of Jeju National University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industry Academic Cooperation Foundation of Jeju National University filed Critical Industry Academic Cooperation Foundation of Jeju National University
Publication of WO2024177354A1 publication Critical patent/WO2024177354A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0613—Electronic shopping [e-shopping] using intermediate agents
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for AC mains or AC distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for AC mains or AC distribution networks
    • H02J3/008—Circuit arrangements for AC mains or AC distribution networks involving trading of energy or energy transmission rights
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for AC mains or AC distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/12—Monitoring or controlling equipment for energy generation units, e.g. distributed energy generation [DER] or load-side generation
    • Y04S10/123—Monitoring or controlling equipment for energy generation units, e.g. distributed energy generation [DER] or load-side generation the energy generation units being or involving renewable energy sources
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/30—Smart metering, e.g. specially adapted for remote reading
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
    • Y04S50/10—Energy trading, including energy flowing from end-user application to grid

Definitions

  • the present invention relates to a method and system for energy trading based on predictive optimal control in a nanogrid, and more particularly, to a method and system for energy trading based on predictive optimal control in an intelligent nanogrid that integrates prediction results using BD-LSTM and PSO-based optimization mechanisms to meet real-time energy demands at minimum cost.
  • RES' renewable energy resources
  • solar, wind, tidal, nuclear, hydro, and biomass have promising potential to generate eco-friendly energy. Therefore, RES-based energy resources are generally linked and are also preferred by eco-friendly groups.
  • new and renewable energy produces energy with low production costs and transmission costs.
  • RES distributed power generation and energy storage systems
  • NG nanogrid networks
  • Nanogrid is a simpler form of microgrid that contains a single load, including a single house. That is, the NG is considered as a single entity for management, voltage, and reliability, and there is one or more gateways outside the NG.
  • the main feature of NG is that it can be connected to other NGs to form a nanogrid cluster. This ease of interconnection can reduce the cost of nanogrids by promoting the use of the power grid by introducing the concept of P2P energy trading.
  • P2P energy trading implements the same concept as P2P networking in computer science. Here, the systems of the P2P network are propagated horizontally, indicating that each system has symmetrical interactions.
  • P2P energy trading follows the concept of the 'P2P economy' and takes place within the local energy distribution network.
  • the energy trading process often involves two or more peers, called consumers and prosumers. Energy consumers are peers who can generate energy to meet their energy needs.
  • intelligent smart grid infrastructure can enable peers to generate surplus energy and provide it to the distribution system, thereby acting as prosumers who produce and trade surplus energy with other peers in the network.
  • the core goal of P2P energy trading is to reduce the intermediation of traditional energy suppliers and reduce costs.
  • Energy trading operations enable peer-to-peer interaction using online services based on information and communication technology (ICT).
  • ICT information and communication technology
  • Recent trends in the energy trading field include the paradigm of machine learning that reveals hidden patterns in the energy corpus to form predictive models and use the derived knowledge for efficient decision making.
  • Preemptive information forecasting in the energy trading sector has been proven to help energy providers plan their power loads or predict energy costs to ensure a balance between energy demand and production at optimal cost.
  • Strategies devised from energy forecast parameters reduce production costs and establish better future capacity planning.
  • machine learning-based predictive models have been used to predict energy demand to optimize the overall energy operation of microgrids, or hybrid energy management systems that integrate fuzzy logic and machine learning to solve multi-objective optimization problems using linear programming.
  • same-day pricing can significantly reduce peak load and energy costs, and same-day pricing information has been integrated to schedule appliances according to user convenience while ensuring minimum costs.
  • PV (photovoltaic) energy trading models have used predicted PV power information for load scheduling.
  • the energy purchase cost of solar power generation was minimized by forming a virtual microgrid that connects consumers and prosumers located at a minimum distance, and an energy transaction cost optimization algorithm was implemented to share energy at a minimum cost.
  • most modern nanogrid energy transaction systems focus on energy management within a single entity such as a consumer or prosumer, and a game theory model for microgrid infrastructure has been developed to provide an optimal energy cost plan to prosumers.
  • the present invention has been made to solve the aforementioned problems, and the present invention aims to provide an intelligent P2P nanogrid energy trading platform that integrates prediction results implemented using BD-LSTM and PSO (Particle Swam Optimization)-based optimization mechanisms to meet real-time energy demands at minimum cost.
  • BD-LSTM and PSO Particle Swam Optimization
  • an intelligent P2P energy trading model is provided to minimize the energy transaction cost of consumers and an optimal energy sharing plan between peers is provided, and an analysis data module is implemented based on a data mining method to reveal important hidden aspects related to energy consumption, energy load and PV generation, thereby enabling early prediction of important energy properties and enabling energy distributors and peers to make informed decisions to increase the consumption of local DER generation.
  • an optimal energy transaction cost strategy is implemented by taking actual and predicted energy load values and implementing a PSO-assisted optimization method to use an objective function that returns the minimized cost
  • an intelligent time-aware energy sharing scheme is provided to determine the role of nanogrid as a prosumer or consumer and to prefer the use of PV-generated energy over grid energy for local transactions
  • an optimal energy sharing mechanism is intended to handle the charging and discharging operations of an Energy Storage System (ESS) and to efficiently manage excess power.
  • ESS Energy Storage System
  • a method for energy trading in a nanogrid based on predictive optimal control comprises: a parameter acquisition and storage step in which a data storage acquires parameters including energy load, energy consumption, photovoltaic (PV) generation, and electricity cost of a nanogrid that acts as a producer or prosumer as a peer of P2P of energy trading; a data analysis step in which a data analysis unit analyzes data of the energy load, the energy consumption, the photovoltaic (PV) generation, the PV generation marginal cost, and the electricity cost included in the parameters; a prediction step in which a prediction unit calculates a predicted load including the energy load, the energy consumption, and the photovoltaic (PV) generation using BD-LSTM (BIDIRECTIONAL LONG SHORT-TERM MEMORY) for the analyzed data; and an optimization step in which an optimization unit configures an energy sharing plan that minimizes an energy transaction cost by using the actual load and the predicted load.
  • BD-LSTM biDIRECTIONAL LONG SHORT-TERM MEMORY
  • a predictive optimal control-based energy trading system in a nanogrid comprises: a data storage for obtaining parameters including energy load, energy consumption, photovoltaic (PV) generation, and electricity cost of a nanogrid that acts as a producer or prosumer as a peer of P2P of energy trading; a data analysis unit for analyzing data of the energy load, the energy consumption, the PV generation, the PV generation marginal cost, and the electricity cost included in the parameters; a prediction unit for calculating a predicted load including the energy load, the energy consumption, and the PV generation using BD-LSTM (BIDIRECTIONAL LONG SHORT-TERM MEMORY) for the analyzed data; and an optimization unit for configuring an energy sharing plan that minimizes energy transaction cost by using the actual load and the predicted load.
  • BD-LSTM biDIRECTIONAL LONG SHORT-TERM MEMORY
  • an intelligent P2P nanogrid energy trading platform can be provided that integrates prediction results implemented using BD-LSTM and PSO (Particle Swam Optimization)-based optimization mechanisms to meet real-time energy demands at minimum cost.
  • the present invention provides an intelligent P2P energy trading model that minimizes energy transaction costs for consumers and an optimal energy sharing plan between peers, and implements an analysis data module based on a data mining method that reveals important hidden aspects related to energy consumption, energy load and PV generation, thereby enabling early prediction of important energy properties and enabling energy distributors and peers to make informed decisions to increase the consumption of local DER generation.
  • an optimal energy transaction cost strategy is implemented by taking actual and predicted energy load values and implementing a PSO-assisted optimization method to use an objective function that returns the minimized cost
  • an intelligent time-aware energy sharing scheme is provided to determine the role of the nanogrid as a prosumer or consumer and to prefer the use of PV-generated energy over grid energy for local transactions, and the optimal energy sharing mechanism can efficiently manage excess power by handling the charging and discharging operations of an Energy Storage System (ESS).
  • ESS Energy Storage System
  • FIG. 1 is a drawing for explaining an energy trading method and system based on predictive optimal control in a nanogrid according to the present invention.
  • FIG. 2 is a diagram for explaining energy cost minimization and energy sharing based on predictive optimal control for a nanogrid according to the present invention.
  • FIGS. 3 to 13 are graphs for explaining the verification results of an energy trading method and system based on predictive optimal control in a nanogrid according to the present invention.
  • the present invention can provide a method used to implement energy trading proposed for optimal P2P energy exchange within a nanogrid cluster, and the present invention will be described with an example of 12 nanogrid houses including rooftop PV panels to meet the energy requirements of energy devices.
  • FIG. 1 is a drawing for explaining an energy trading method and system based on predictive optimal control in a nanogrid according to the present invention, and illustrates the overall structure of a model according to the present invention.
  • a nanogrid according to the present invention may be configured to include a smart meter that monitors, records, and transmits information related to energy load demand and PV power production.
  • the data storage (110) obtains parameters (parameter: 101) including energy load, energy consumption, solar photovoltaic (PV) generation, and electricity cost of a nanogrid that acts as a producer or prosumer as a peer of P2P energy trading.
  • parameters including energy load, energy consumption, solar photovoltaic (PV) generation, and electricity cost of a nanogrid that acts as a producer or prosumer as a peer of P2P energy trading.
  • the data analysis unit (120) analyzes data of the energy load, the energy consumption, the solar photovoltaic (PV) power generation, the marginal cost of the solar photovoltaic (PV) power generation, and the electricity cost included in the parameters.
  • the data analysis unit (120) can interpolate the missing portion of the parameter using the KNN imputer.
  • the prediction unit (130) uses BD-LSTM (BIDIRECTIONAL LONG SHORT-TERM MEMORY) on the analyzed data to calculate the predicted load including the energy load, energy consumption, and solar power (PV) generation.
  • BD-LSTM BIODIRECTIONAL LONG SHORT-TERM MEMORY
  • the prediction unit (130) can predict the energy load, the energy consumption, the solar photovoltaic (PV) power generation, the marginal cost of solar photovoltaic (PV) power generation, and the electricity cost by searching the parameters in the forward and backward directions using two individual LSTM layers of the BD-LSTM.
  • the optimization unit (140) configures an energy sharing plan that minimizes energy transaction costs using the actual load and the predicted load.
  • the optimization unit (140) can optimize the solar power (PV) generation marginal cost and the electricity cost using the PSO (Particle Swam Optimization).
  • the fitness function is calculated, and the local and global optimization values are obtained, and then the position and rate are updated, and if the optimization criteria are met, the optimal solution can be calculated.
  • the nanogrid is connected to a utility grid via a BD (BIDIRECTIONAL)-DC-AC converter, and an energy sharing control unit can perform an energy exchange step in which, when the nanogrid has surplus energy according to the energy sharing plan, the BD-DC-AC converter sends the surplus energy to the utility grid, and when the nanogrid is short of energy, the BD-DC-AC converter supplies energy from the utility grid to the nanogrid.
  • BD BIODIRECTIONAL
  • the energy cost data considered SMP cost and DR cost data provided by KEPCO.
  • the analyzed parameters are transferred to the prediction module to implement the BD-LSTM model to predict energy load, energy consumption, photovoltaic (PV) generation, and electricity cost.
  • the present invention focuses on two important aspects related to energy trading: energy transaction cost optimization and optimal energy exchange scheme between connected nanogrid houses in a cluster.
  • the actual and predicted energy parameters are also used as inputs to the optimization module.
  • Each nanogrid contains a smart meter that monitors, records, and transmits information related to energy load demand and PV power production.
  • nanogrid clusters i.e., connected nanogrids
  • Nanogrids in the network are assigned a consumer or prosumer role before implementing the optimization module of the present invention. Therefore, the energy 'sell' or 'buy' trading mode is activated before starting the trading process.
  • the supply-demand relationship between nanogrids must be secured first. Once the relationship is secured, nanogrids can exchange energy in a peer-to-peer manner.
  • Nanogrids rely on two energy resources to meet their energy requirements: utility and photovoltaic (PV) generation. All nanogrids in the network are connected to the utility grid in the form of a Point of Common Coupling (PCC).
  • PCC Point of Common Coupling
  • the utility grid is used to meet energy requirements when a local cluster cannot meet its energy requirements due to adverse conditions caused by renewable energy.
  • a nearby nanogrid meets its energy requirements and has surplus energy generated by PV, energy can be sold in a peer-to-peer manner between connected nanogrids.
  • Energy parameters including energy load, energy consumption, PV generation and energy cost are predicted using the BD-LSTM model. Prediction of these important energy parameters can play a vital role in uncovering useful time series-based hidden patterns in data that will be useful in applications related to future energy demand.
  • Equations 1 to 6 represent the gates that are part of the LSTM that converts to BD-LSTM.
  • X l represents a weight metric between cells (l-1) of a layer
  • Y l represents a weight matrix between consecutive cells of layer l
  • C l represents a bias vector of each layer.
  • the weight matrix and bias values of the cell are broadcast along with the length of the sequence to reduce the number of hidden neurons and weights in the network.
  • the '*' symbol indicates element-wise multiplication.
  • BD-LSTM utilizes two separate LSTM layers to explore the information in the forward and backward directions.
  • the hidden state for the forward direction is computed using Equation 6.
  • the same formula is used to compute the backward hidden state and proceeds in the backward direction.
  • Equation 7 l represents the input layer.
  • BD-LSTM can process information in both directions and interpret the association between elements in the entire sequence.
  • the parameter sharing method used by BD-LSTM consumes less memory than existing CNNs and DNNs. Therefore, in this invention, BD-LSTM is used as a prediction model for predicting load demand, energy consumption, PV generation, and energy costs.
  • the model consists of six hidden layers. Trial and error technique is used to determine the parameters for the input layer and the number of hidden layers in the BD-LSTM model.
  • the number of inputs and outputs to be passed to the prediction model is determined by evaluating the root mean square (RMSE).
  • the ADAM optimizer is utilized to find the weights and accuracy at each epoch.
  • the RMSE measure is considered as a log loss function that verifies the performance of the proposed model and is calculated using Equation 8.
  • A represents the actual predicted value and P represents the same predicted value at time interval t, where t ranges from 1 to k.
  • the objective function is implemented using Particle Swam Optimization (PSO).
  • PSO Particle Swam Optimization
  • Table 1 shows the abbreviations used in the two optimization modules.
  • Mathematical expressions 9 to 14 represent the objective function for reducing transaction costs between connected peers.
  • Equation 10 The constraints in Equation 10 represent the b/w total load relationship of the interval and energy for individual consumers for energy trading.
  • Equation 13 represents the final energy of the m th consumer at the end of an interval no greater than the allowable energy.
  • Equation 14 The constraints shown in Equation 14 specify lower and upper bounds on the energy flow to the consumer.
  • the nanogrid is connected to the utility grid through a BD (BIDIRECTIONAL)-DC-AC converter to maintain energy balance.
  • BD BIODIRECTIONAL
  • the converter turns on the inverter mode and feeds the surplus energy back to the utility grid.
  • the converter supplies energy from the utility grid.
  • the proposed energy export/import strategy is illustrated in Fig. 2.
  • NG is called a set of nanogrids and n is called the number of nanogrids.
  • ESS represents a set of energy storage systems installed in each nanogrid.
  • n the total number of ESSs equal to the number of nanogrid houses.
  • D k (t) represents the load demand of the k th nanogrid at time t.
  • PV k (t) be the energy generated by the photovoltaic (PV) of the k th nanogrid at time t. It charges the ess k or satisfies D k (t).
  • the surplus energy produced by PV is used to sell to other NGs in need.
  • the self-supplied energy generated by PV to meet the load demand of the nanogrid is as follows.
  • the ESS device consists of a battery that stores energy generated by solar power generation and a bidirectional DC-DC converter.
  • the energy remaining in the ESS in a time period t is called R k (t). Both factors determine the decision taken for the ESS charging, i.e., D k (t) and PV k (t), and the energy traded with other nanogrids.
  • the energy remaining after energy transaction at time interval t is expressed as follows.
  • re represents the energy remaining in ess of k nanogrid at time t.
  • re (max,k) is the total capacity of the ESS (kWh) and re (min,k) is the minimum energy of the ESS set by the DoD to avoid over-discharge.
  • S K (t) The energy shared by each nanogrid is called S K (t), which represents the energy shared by the k th nanogrid at time t.
  • S K (t) is used as a determinant of energy trading.
  • the shared energy also helps to determine the amount of surplus energy of each nanogrid. For example, if the shared energy is greater than 0, the trading function becomes +1, otherwise -1.
  • the following are the constraints imposed on energy sharing.
  • S K (t) represents the energy remaining in NG.
  • S K (t) must be between 0 and the maximum energy share at time t.
  • the maximum value of S max,k is The interface of NG k is determined by the rated power of the BD-DC-DC converter.
  • the following function specifies the energy value to be traded.
  • Surplus k (t) is (1) the maximum amount of energy in essk at time t, which is determined by the rated power of the DC-DC converter and (2) re max,k .
  • the energy released from ess k which is used to meet the energy load for the nanogrid, is:
  • DE max,k is the maximum energy released from ess k . It is determined by the residual energy of ess and the rated power of the BD-DC-DC converter within the time range t.
  • the mathematical equation that determines the energy flow of +- 1 is constructed as shown in the following mathematical equation 17.
  • NG +1
  • TE transaction energy
  • nanogrid data sets collected from residential communities in Jeju City, Korea were used.
  • the data were obtained from smart meters installed in nanogrids mixed with other essential parameters to implement the proposed model. It is assumed that the smart meter can control and monitor the energy operation of all loads and devices.
  • the smart meter contains current signals and raw voltages. The energy consumed by the nanogrid is calculated through discrete signals.
  • Table 2 presents an overview of the energy usage data including the energy load and PV generation data produced daily and weekly in the household and the corresponding discharge power (kW).
  • the minimum SoC level of the ESS system is 30% and the PV generation capacity is 2.5kWp.
  • the simulation was performed in MATLAB. Considering the situation where the considered NGs maintain a minimum geographical distance, the PVs of the 12 NGs will have similar data obtained from the actually installed rooftop PVs.
  • NG-10 has the highest energy load value of 32.2kW
  • NG-4 maintains the lowest energy load of 2.6kW
  • NG-3 follows with about 5.9kWh per week. The rest of the houses can see the same days while having moderate energy loads.
  • FIG. 5 illustrates the analysis of PV energy generation for 7 days of the week for all the considered NGs.
  • NG3 shows the lowest PV energy generation value of about 8.47 kWh, followed by NG-4, NG-11, NG-7, and N-12.
  • the weekly rate shows the lowest value for NG5 with 59.33 kWh, and the highest value for NG-6 with about 76 kWh.
  • the electricity rate data considered in this invention is taken from the demand response (DR) scheme proposed by Korea Electric Power Corporation (KEPCO).
  • the DR scheme provides incentives to consumers who use less energy during peak hours.
  • the DR scheme helps reduce power plan emissions, increase the reliability of the power system, and reduce dependence on foreign fuels.
  • Korea Electric Power Corporation (KEPCO) determines electricity rates using the DR (demand response) program.
  • the DR program specifies the rate of energy supplied from the utility grid. As shown in Fig. 6, the range of electricity rates determined by the DR scheme is $0.05/kWh for the 23:00-09:00 time slot, $0.1/kWh for the 9:00-10:00, 12:00-13:00, and 17:00-23:00 time slots, and $0.18/kWh for the 10:00-12:00, 13:00-17:00 time slots.
  • the energy transaction rate which is regulated by the renewable energy certificate and the system marginal price (SMP), is determined by the Korea Power Exchange (KPX).
  • BD-LSTM uses 10-fold cross-validation technique to predict energy load, energy consumption, PV generation, and energy cost, respectively.
  • Figs. 7 to 10 show the actual and predicted values for the above four.
  • RMSE predicted prediction results
  • Table 3 The numbers represent the difference between the actual output and the predicted output. It can be seen that the best value of RMSE is 1.26 for PV generation prediction, followed by 1.45 for energy load, and 1.98 for energy consumption.
  • the value of RMSE implies a good prediction behavior that can have a positive impact on the energy-oriented prediction model and energy supplier entity to form effective decision-making. Accurately estimating energy load, energy consumption, and solar power generation can help optimize resources and loads for specific time periods in the future.
  • Fig. 10 shows the energy cost results in three aspects: actual energy cost, predicted energy cost, and optimized energy cost.
  • the X-axis represents the timestamp information, i.e., the day of the week, and the y-axis represents the energy price in dollars ($).
  • the actual energy cost data can be obtained from SMP/DER.
  • the graph in Fig. 10 shows the average value calculated for all 12 nanogrid houses in the proposed energy trading framework.
  • the predicted energy price can help make timely decisions related to energy cost before trading. Energy price prediction helps individual prosumers and consumers to predict future market trends.
  • the optimal energy price can be calculated based on the objective function to find the optimal energy price.
  • the PSO-based optimization function is estimated through the graph that finds the optimal real-time energy price between the original energy price and the predicted energy price. It can be inferred that the optimal energy price can help achieve the optimized real-time energy cost used in the energy trading system.
  • Fig. 11, Fig. 12, and Fig. 13 represents 'one week' and the Y-axis represents 'power (kW)'.
  • a positive value indicates that the nanogrid acts as a prosumer and exchanges its surplus energy with other nanogrids connected to the network.
  • a negative value indicates that the nanogrid acts as a consumer and purchases energy from other NGs.
  • NG-10 plays the role of a consumer since its produced PV energy is not self-sufficient to meet its energy requirements.
  • nanogrids 1, 2, and 4 act as prosumers since the load demand of these NGs is less than their respective PV energy. Therefore, the surplus energy is used to sell to the consumers NGs who need it.
  • the remaining NGs play alternative roles in the energy sharing process. The role of the NGs depends entirely on their respective produced energy. For example, if a nanogrid has surplus PV energy, it acts as a prosumer, otherwise it acts as a consumer NG.
  • the present invention proposes an intelligent energy trading model that takes into account important aspects that the latest technology in energy trading has overlooked.
  • the present invention proposes an optimal predictive energy trading scheme that focuses on two main factors: an intelligent time-aware energy sharing scheme between nanogrid clusters to determine the role of peers as prosumers and to facilitate the utilization of PV-generated energy for energy trading within the nanogrid; and an objective function is designed to minimize the nanogrid energy trading cost by implementing the objective function using the PSO algorithm and taking predictor variables as inputs.
  • the results of the present invention are evaluated using energy parameters of 12 nanogrid houses through simulation.
  • detailed analysis and prediction of important energy parameters including energy load, energy consumption and PV generation are also performed using the validated BD-LSTM algorithm using the standard evaluation metric RMSE.
  • the prediction results can positively contribute to efficient decision-making in smart grid-based systems.
  • the detailed experimental results through simulation show that the energy sharing scheme tends to meet the energy requirements of nanogrid houses in P2P clusters, and the energy cost is significantly reduced.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Power Engineering (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Tourism & Hospitality (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention concerne un procédé et un système de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau, et le procédé de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau, selon la présente invention, comprend : une étape d'acquisition et de stockage de paramètres dans laquelle un référentiel de données acquiert des paramètres comprenant une charge d'énergie, une consommation d'énergie, une génération photovoltaïque (PV) et un coût d'électricité d'un nanoréseau servant de consommateur ou de producteur en tant qu'homologue dans une négociation d'énergie entre homologues ; une étape d'analyse de données dans laquelle une unité d'analyse de données analyse des données sur la charge d'énergie, la consommation d'énergie, la génération PV, le coût marginal de la génération PV, et le coût d'électricité inclus dans les paramètres ; une étape de prédiction dans laquelle une unité de prédiction calcule une charge prédite comprenant la charge d'énergie, la consommation d'énergie et la génération PV par application d'une longue mémoire à court terme bidirectionnelle (BD-LSTM) aux données analysées ; et une étape d'optimisation dans laquelle une unité d'optimisation configure un plan de partage d'énergie pour réduire au minimum le coût de transaction d'énergie en utilisant la charge réelle et la charge prédite.
PCT/KR2024/002190 2023-02-22 2024-02-20 Procédé et système de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau Ceased WO2024177354A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2023-0023883 2023-02-22
KR1020230023883A KR20240130924A (ko) 2023-02-22 2023-02-22 나노그리드에서 예측 최적 제어 기반 에너지 거래 방법 및 시스템

Publications (1)

Publication Number Publication Date
WO2024177354A1 true WO2024177354A1 (fr) 2024-08-29

Family

ID=92501421

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2024/002190 Ceased WO2024177354A1 (fr) 2023-02-22 2024-02-20 Procédé et système de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau

Country Status (2)

Country Link
KR (1) KR20240130924A (fr)
WO (1) WO2024177354A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119359090A (zh) * 2024-12-24 2025-01-24 杭州品联科技有限公司 一种基于大数据分析的作业经济性评估方法及系统
CN120033751A (zh) * 2025-04-24 2025-05-23 华侨大学 一种基于多源集成的双向dc-dc能量回馈系统及其控制方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102847313B1 (ko) * 2024-11-11 2025-08-19 주식회사 이아이피그리드 에너지 입찰 관리를 위한 동적 하이브리드 접근 방식

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210012630A (ko) * 2019-07-26 2021-02-03 한국전기연구원 P2p 전력거래 메커니즘 설계 방법 및 그 시스템
KR20210061823A (ko) * 2019-11-20 2021-05-28 한국전력공사 에너지 관리 시스템 및 이를 이용한 전력 구매 비용 결정 방법
KR20210092682A (ko) * 2020-01-16 2021-07-26 한국전자통신연구원 마이크로그리드 시뮬레이션 장치 및 방법

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210012630A (ko) * 2019-07-26 2021-02-03 한국전기연구원 P2p 전력거래 메커니즘 설계 방법 및 그 시스템
KR20210061823A (ko) * 2019-11-20 2021-05-28 한국전력공사 에너지 관리 시스템 및 이를 이용한 전력 구매 비용 결정 방법
KR20210092682A (ko) * 2020-01-16 2021-07-26 한국전자통신연구원 마이크로그리드 시뮬레이션 장치 및 방법

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
QAYYUM FAIZA, JAMIL HARUN, JAMIL FAISAL, KIM DOHYEUN: "Predictive Optimization Based Energy Cost Minimization and Energy Sharing Mechanism for Peer-to-Peer Nanogrid Network", IEEE ACCESS, IEEE, USA, vol. 10, 1 January 2022 (2022-01-01), USA , pages 23593 - 23604, XP093203227, ISSN: 2169-3536, DOI: 10.1109/ACCESS.2022.3153837 *
ULLAH FATH U MIN; ULLAH AMIN; HAQ IJAZ UL; RHO SEUNGMIN; BAIK SUNG WOOK: "Short-Term Prediction of Residential Power Energy Consumption via CNN and Multi-Layer Bi-Directional LSTM Networks", IEEE ACCESS, IEEE, USA, vol. 8, 30 December 2019 (2019-12-30), USA , pages 123369 - 123380, XP011799353, DOI: 10.1109/ACCESS.2019.2963045 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119359090A (zh) * 2024-12-24 2025-01-24 杭州品联科技有限公司 一种基于大数据分析的作业经济性评估方法及系统
CN120033751A (zh) * 2025-04-24 2025-05-23 华侨大学 一种基于多源集成的双向dc-dc能量回馈系统及其控制方法

Also Published As

Publication number Publication date
KR20240130924A (ko) 2024-08-30

Similar Documents

Publication Publication Date Title
Murty et al. RETRACTED ARTICLE: Multi-objective energy management in microgrids with hybrid energy sources and battery energy storage systems
WO2024177354A1 (fr) Procédé et système de négociation d'énergie basée sur une commande optimale prédictive dans un nanoréseau
Sanseverino et al. An execution, monitoring and replanning approach for optimal energy management in microgrids
Ahmethodžić et al. Microgrid energy management: Classification, review and challenges
Liu et al. Distributed energy management for interconnected operation of combined heat and power-based microgrids with demand response
CN108734350A (zh) 一种含微电网的配电网独立与联合调度的求解方法
Qayyum et al. Predictive optimization based energy cost minimization and energy sharing mechanism for peer-to-peer nanogrid network
Darbali-Zamora et al. Solar irradiance prediction model based on a statistical approach for microgrid applications
Haidar et al. An effective power dispatch strategy for clustered microgrids while implementing optimal energy management and power sharing control using power line communication
Zhang et al. Research on two-level energy optimized dispatching strategy of microgrid cluster based on IPSO algorithm
Meydani et al. Optimizing microgrid energy management: Metaheuristic versus conventional techniques
Thirunavukkarasu et al. Smart microgrid integration and optimization
Salameh et al. A digital ecosystem cooperative model: An application on microgrids
Kumar et al. Energy Management in Microgrids with Uncertainty in EV and Renewable Sources
Klaimi et al. Energy management algorithms in smart grids: state of the art and emerging trends
Aghdam et al. Energy management requirements for microgrids
Wang et al. A hybrid agent-based model predictive control scheme for smart community energy system with uncertain DGs and loads
Schirmer et al. Reducing grid distortions utilizing energy demand prediction and local storages
Seddigh et al. Reliability assessment of multi-microgrids considering collaborations at PCC
Li et al. Multi-timescale scheduling strategy for multi-microgrids with accelerated alternating direction method of multipliers and stochastic model predictive control
Desai Smart Grid and Energy Management
Liu et al. Multilayer Collaborative Optimization for the System Configuration, Operation, and Maintenance of Smart Community Microgrids
Wang et al. Distributed optimal scheduling for multi-prosumers with CHP and heat storage based on ADMM
CN113988907A (zh) 一种基于对偶单纯型灵敏度分析的边际机组定位方法及定位系统
Sokolovskyi et al. Estimation of PV systems power production efficiency in the dense urban development condition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24760543

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE