HK1238065B - Optimizing capacity expansion in a mobile network - Google Patents

Description

Optimizing capacity expansion in mobile networks

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to U.S. Application No. 61/986,462, filed April 30, 2014, entitled “Optimizing Capacity Expansion Using NFV-Based Platforms,” the contents of which are incorporated herein by reference in their entirety.

Technical Field

Embodiments of the present invention generally relate to computerized methods and apparatus for optimizing capacity expansion in mobile networks.

Background Art

Traditional approaches to resource provisioning in mobile networks involve adding additional physical infrastructure when resources are fully utilized. Physical equipment is designed with fixed capacity ratios. Once a specific dimension (e.g., throughput, signaling activity, session capacity) is exhausted, mobile network operators have no choice but to add more equipment, even if all other dimensions are underutilized. This results in increased capital and operating expenses.

Summary of the Invention

In certain embodiments, systems and methods for optimizing the capacity of network devices in a mobile network are disclosed. In certain embodiments, a computing device receives a user identification and user attributes, the user identification corresponding to a characteristic of a mobile network user, the user attributes corresponding to at least one characteristic of mobile network usage by the mobile network user. In certain embodiments, the computing device generates a usage forecast based on the user identification and the user attributes, the usage forecast including information corresponding to expected future data usage of the mobile network user, the expected future mobile network usage corresponding to at least one mobile resource. In certain embodiments, the computing device sends the usage forecast to a serving gateway (SGW), causing the SGW to route the mobile network user to a traditional packet data network gateway (PGW) and a network function virtualization (NFV) PGW based on the usage forecast, the traditional PGW including fixed capacity for at least one mobile resource, and the NFVPGW including configurable capacity for at least one mobile resource.

In some embodiments, the at least one characteristic of the mobile network user's mobile network usage includes an amount of prior mobile network usage, time associated with mobile network usage, a location of a mobile device corresponding to the mobile user, an amount of time spent roaming by the mobile device, a brand and model of the mobile device, applications installed on the mobile device, an operating system and firmware version of the mobile device, a subscription plan, remaining allowance, and demographic information. In some embodiments, the at least one characteristic of the mobile network user includes a mobile device ID or a phone number. In some embodiments, receiving user attributes further includes receiving user attributes from at least one of a Home Subscriber Server (HSS), a Mobility Management Entity (MME), a charging system, and a System Architecture Evolution (SAE) gateway. In some embodiments, the mobile resources include at least one of signaling activity, throughput, session occupancy, encryption, and transcoding.

These and other capabilities of the disclosed subject matter will be more fully understood after careful review of the following drawings, detailed description, and claims.It is to be understood that the phraseology and terminology employed herein is for the purpose of description and should not be regarded as limiting.

BRIEF DESCRIPTION OF THE DRAWINGS

Various objects, features, and advantages of the disclosed subject matter may be more fully appreciated by reference to the following detailed description of the disclosed subject matter when considered in conjunction with the following drawings, in which like reference numerals represent like elements.

FIG1 is a schematic diagram illustrating demands incurred by mobile network users on a mobile network, according to certain embodiments of the present disclosure.

FIG. 2 is a schematic diagram showing a conventional method of dilation using conventional equipment.

3 is a diagram illustrating a method of expansion using traditional equipment and NFV-based equipment according to certain embodiments of the present disclosure.

4 is a system diagram illustrating a user in conjunction with a mobile network, according to certain embodiments of the present disclosure.

FIG5 is a schematic diagram illustrating the use of a prediction engine according to certain embodiments of the present disclosure.

FIG6 is a system diagram of a mobile network according to certain embodiments of the present disclosure.

FIG7 is a system diagram illustrating capacity optimization in a mobile network according to certain embodiments of the present invention.

DETAILED DESCRIPTION

Mobile networks can include mobile users with vastly different usage characteristics. For example, some mobile users are highly engaged and consume large amounts of data, increasing the total amount of data throughput the network needs to support. Other users may be very signaling-intensive and complete numerous connections (e.g., using a "chatty" mobile application that frequently sends updates) but only transmit small amounts of data. Even though they only use a small amount of data, they increase the amount of signal processing required by the network. Some other users may be relatively idle in both the data throughput and signaling dimensions (e.g., networked power meter readers), but their presence is substantial and they consume a significant amount of session capacity simply by signing them up to the network. To accommodate all types of users, network operators need to deploy enough networking equipment to cover the worst-case scenarios for all of these dimensions (e.g., throughput, signaling activity, session capacity, and possibly other dimensions). Because traditional networking equipment is designed with fixed capacity ratios (supporting X number of users, Y amount of signaling, and Z amount of data throughput), covering the worst-case scenario for one dimension will result in underutilization of other dimensions. For example, a traditional platform deployed in a network may be hitting 100% of session capacity but utilizing only 20% of throughput capacity. Even if there is excess throughput capacity, new equipment needs to be installed to increase the number of users supported. This increases both capital and operating costs.

Previously, the user base was separated into separate applications. For example, regular consumers were separated from machine-to-machine devices. Devices can be categorized so that they have similar needs. Devices with similar needs can be assigned to devices with different performance characteristics, often from different manufacturers. Even with this approach, the problem of optimizing capacity is not solved due to at least the following: (1) A broad range of user types does not guarantee that users within a group have similar usage needs. Devices serving one type of user may still be underutilized in some dimensions; (2) Capital and operating expenses will increase because the operator now needs to potentially deal with devices from multiple vendors (which may or may not work well together); and (3) As the needs from different user groups change over time, the operator will need to re-segment users and reallocate network resources, which can be time-consuming and expensive.

Preferred embodiments of the present disclosure include using network function virtualization (NFV) on platforms with different capabilities and cost characteristics to handle the demands introduced by different types of users. Differently configured (in terms of both hardware and software), different NFV-based platforms can have different strengths and weaknesses. For example, one NFV-based platform can be designed so that it can accommodate a large number of users (e.g., by using servers with large amounts of memory), but has limited throughput and signaling capabilities. Another NFV-based platform can be designed so that it can handle a large amount of throughput (e.g., by using dedicated network adapter cards). Another NFV-based platform can be designed so that it can handle a large amount of signaling (e.g., with a high-power CPU). These NFV-based platforms with different characteristics can be put together in a network to meet the different demands introduced by different types of users. In order to maximize effectiveness and minimize costs, users with different characteristics are directed to servers with matching advantages so that each server is best utilized. In this way, the advantages of traditional and NFV-based platforms complement each other's weaknesses. Network equipment can therefore be better utilized, resulting in lower overall capital and operating costs.

Preferred embodiments of the present disclosure include a function for classifying and directing mobile users or subscribers to different network devices based on past and predicted future usage characteristics to match the capacity characteristics of the network devices. There is no need to separate users into different groups (e.g., separating users into different access point names or APNs). The network can appear seamless to the end user, and therefore there is little variation in the user experience. Operators can use NFV to deploy platforms with different cost and performance characteristics. NFV is suitable for such applications because it allows the same network function to run on different hardware platforms. These hardware platforms range from high-end blade server chassis to low-cost server chassis, which provide different performance and capacity.

In some cases, additional capabilities may be gained by building servers with specialized hardware (such as a chip for hardware encryption) to support certain groups of users.

Preferred embodiments of the present disclosure can be used as a greenfield solution (e.g., a new network consisting solely of an NFV-based platform) or to supplement an existing legacy network that has exhausted its capacity. In the latter case, the NFV server can be designed to specifically alleviate bottlenecks in legacy equipment and achieve a more balanced utilization of all performance dimensions. Below, we describe techniques for determining bottlenecks in existing legacy platforms, building NFV-based platforms to alleviate these bottlenecks, predicting and identifying user usage characteristics, and directing them to the NFV-based platform that can best handle their needs.

Preferred embodiments of the present disclosure utilize network function virtualization-based platforms with different capabilities and cost characteristics to supplement existing traditional equipment with fixed capacity ratios. Traditional and NFV-based platforms can work seamlessly as a single network. In certain embodiments, the NFV-based platform is designed to supplement the weaknesses of the traditional platform so that when they work together, they reduce the chance of overloading a certain capacity dimension and better utilize all network nodes overall.

In certain embodiments, to best utilize the different capabilities of traditional and NFV-based platforms, when a user attempts to access the network, the user's usage characteristics are predicted based on a number of factors, including the user's past usage patterns. The user is then directed to the network node that can best handle the user's needs.

FIG1 is a schematic diagram illustrating demands incurred by mobile network users on a mobile network according to certain embodiments of the present disclosure. FIG1 illustrates mobile devices 101 , signaling activity 102 , throughput 103 , session occupancy 104 , and other dimensions 105 .

As shown in Figure 1, a mobile network user 101 places demands on the mobile network in many different dimensions. A user generates signaling activity 102 when registering with and deregistering from the network, when roaming, and so on. A user creates demands on the throughput dimension 103 when browsing the web or sending status updates. While a user is attached to the network, they also occupy one or more session spaces 104. Finally, if, for example, the user requires encryption or image/video transcoding services, demands on other dimensions 105 exist. Not all users behave the same. Data-heavy users consume large amounts of data and place demands on the throughput dimension. Other users may be very signaling-intensive and complete numerous connections (e.g., using "chatty" applications that frequently send numerous updates) while only transmitting small amounts of data. Some users may place demands on the signaling dimension of the network. Some other users may be relatively idle in both the data throughput and signaling dimensions (e.g., networked power meter readers), but are numerous and require a significant amount of session capacity simply to remain signed in to the network.

Network operators often have to install more network equipment to handle the total demand across these different dimensions. Because traditional networking equipment is designed to support fixed capacity ratios (supporting X number of users, Y amount of signaling, and Z amount of data throughput), covering the worst-case scenario in one dimension often leads to underutilization in other dimensions. For example, a network node may be hitting 100% of its session capacity but utilizing only 50% of its throughput capacity. Even if there is excess throughput capacity, new traditional equipment is installed to increase the number of users supported. Installing new traditional equipment can increase both capital and operating costs.

Figure 2 shows a schematic diagram of a conventional method of expansion using conventional equipment. Figure 2 shows a network operator reaching maximum session capacity for a first conventional platform 201 , the capacity of the first conventional platform 202 after 2x expansion 210 , and the capacity of the second conventional platform 203 after 2x expansion 210 .

As shown at 201, a network operator reaches maximum capacity on a first legacy platform. The first legacy platform has a maximum throughput of 100 units and a maximum of 100 sessions. 50 of the 100 units of throughput are used, while 100 of the 100 sessions are used. When the network operator anticipates a doubling of demand (e.g., 100 units of throughput and 200 sessions), the network operator must find a way to increase capacity. To double the capacity 210, the network operator installs a second legacy platform. In some embodiments, the operator can determine the platform's capacity utilization by monitoring the device's peak usage levels (e.g., monitoring usage during busy hours). The platform can specify a maximum value for each dimension (e.g., 10 million sessions, such as 50 Gbps throughput at an 80% CPU limit). For example, to determine session usage, the operator can use statistical counters to see how many sessions are used during busy hours. As another example, the operator can determine the amount of throughput by measuring throughput at a specific CPU limit during busy hours. The operator can determine capacity by measuring CPU usage during busy hours. In both the first legacy platform 202 and the second legacy platform 203, 50 of the 100 units of throughput are used, while 100 of the 100 sessions are used. After expansion, both legacy platforms are still constrained by the session dimension. The capacity ratios in the expanded legacy platforms (e.g., equal capacity for sessions and throughput) do not match the user's needs (e.g., a large number of sessions but not as much throughput).

In contrast, the preferred embodiment of the present invention requires understanding the causes of bottlenecks for existing traditional platforms, current and future usage patterns of users, and building an NFV-based platform to complement the traditional platforms so that all capacity dimensions can be better utilized.

FIG3 is a diagram illustrating a method for scaling using traditional devices and NFV-based devices according to certain embodiments of the present disclosure. FIG3 illustrates a network operator reaching maximum session capacity for a first traditional platform 201, the capacity of the first traditional platform 302 after 2x scaling 310, and the capacity of a second NFV-based platform 303 after 2x scaling 310. While FIG3 illustrates scaling in two dimensions (e.g., sessions and throughput), similar techniques can be applied to any number of dimensions.

As described above, the operator has reached capacity in the first legacy platform, where 50 of 100 units of throughput are being used and 100 of 100 sessions are being used. When the network operator anticipates a doubling of demand (e.g., 100 units of throughput and 200 sessions), the network operator doubles capacity 210 by installing NFV-based platform 303. As shown after expansion 310, the combination of first legacy platform 302 and NFV-based platform 303 takes into account the current and future usage patterns of users. For example, if 20% of users are using 80% of the throughput, this means that among 100 users:

20 heavy users are using 40 units of throughput; and

80 light users are using 10 units of throughput.

When the demand doubles, there are 200 users in total, of which

80 units of throughput for 40 heavy users; and

160 light users using 20 units of throughput.

An NFV-based platform could be built to support 200 users, but only support 40 units of throughput, likely at a fraction of the cost compared to a traditional platform. This is possible due to the flexible nature of the NFV solution—a platform could be built with a large amount of memory to support more sessions, but only a moderately powerful CPU for throughput processing to reduce costs. 160 light users could be directed to the NFV-based platform 303, while heavy users could be directed to the traditional platform 302. If the traditional platform costs $1M and the NFV platform costs $0.2M, the cost to double the capacity would be:

$2M if only traditional platforms are used (e.g., as shown in Figure 2); and

$1.2M if an NFV-based platform is added to the traditional platform (e.g., as shown in Figure 3).

Using an NFV-based platform can save $0.8M or 40% of the cost of using only a traditional platform. As shown in Figures 2 and 3, traditional platforms have high throughput capacity but insufficient session capacity. NFV-based platforms complement traditional platforms by providing high session capacity but low throughput capacity to keep costs low. There are many different ways to build an NFV-based platform to complement traditional platforms. Operators can determine the cost and performance balance of different components (such as memory, CPU or other specialized chips) and how future demand will change. Using an NFV-based platform allows operators to analyze the needs of different users, build an NFV-based platform with the ability to complement traditional platforms, and appropriately guide users to different platforms to achieve optimal use of capacity on all platforms.

In certain embodiments, the systems and methods described herein guide and categorize users based on past and expected demand. Predicting user capacity needs can help balance capacity usage on both traditional platforms and NFV-based platforms.

Figure 4 is a system diagram illustrating a user in conjunction with a mobile network according to certain embodiments of the present disclosure. Figure 4 illustrates a mobile network user 401, a classifier 402, a usage prediction engine 403, a traditional network platform, an NFV-based platform 405, and a mobile network 406.

Mobile network user 401 may include a mobile network subscriber who accesses the mobile network via one or more mobile network devices (e.g., smartphones, laptops, tablets). As described in more detail below, mobile network 406 includes multiple network devices. Briefly, the network devices in mobile network 406 can route and analyze user traffic.

As user 401 signs onto network 406, classifier 402 queries usage prediction engine 403 to predict resource usage patterns. Classifier 402 is a component that obtains information from the user and his/her device (e.g., mobile device identifier), consults usage engine 403, and makes a decision about which platform to place the user on in mobile network 406. Classifier 402 can be implemented as a separate component or as part of a network device in the mobile network (e.g., on a load balancer). Usage prediction engine 403, described in more detail below, is a component that obtains user identification and other attributes related to the user and predicts the user's future network resource usage. Based on the results from usage prediction engine 403, user 401 is directed to services provided by traditional network platform 404 or NFV-based platform 405. As described above, the classifier also receives input from traditional and NFV-based platforms corresponding to their available capacity levels and their capabilities (e.g., encryption, video transcoding).

In some embodiments, users can be directed to either a traditional platform or an NFV-based platform based on their or the platform's characteristics. For example, users can be directed when they join the network (e.g., when they turn on their phone in the morning). Additionally, existing users can be proactively migrated from one system to another if the existing system's load reaches a certain threshold or if the user's characteristics change significantly.

Figure 5 is a schematic diagram illustrating a usage prediction engine according to certain embodiments of the present disclosure. Figure 5 illustrates user identification 501, usage prediction engine 502, usage prediction 503, past usage patterns and trends 504, time information 505, location 506, past mobility patterns 507, brand and model of mobile device 508, installed applications 509, operating system (OS) and firmware version 501, subscription plan 511, remaining quota 512, and demographic information 513.

The usage prediction engine 502 receives a user identification 501 and user attributes 504-513. As described in more detail below, the user prediction engine 502 predicts the future usage needs of the user 503 based on the input. The user identification 501 corresponds to information about the user's mobile device (e.g., International Mobile Equipment Identity (IMEI)). The user attributes can be collected from various components in the mobile network, as described in more detail in FIG6.

User attributes 504-513 include but are not limited to:

(1) Past usage patterns and trends of user 504 - a data-heavy user is likely to be data-heavy in the future.

(2) Time of day, day of week, and day of year 505 - Time information provides clues about what services the user uses on the mobile device. The occurrence of any large event (eg, Super Bowl) can be helpful in predicting the user's usage pattern.

(3) User's location 506 - Similar to temporal location, geographic location information can be helpful in predicting usage patterns. For example, if the user is located in a city where there are more cell sites of smaller size, it is likely that the user will experience a higher volume of handoff events as he/she moves back and forth between cell sites. Whereas if the user is located in a suburban area, the cell sites are likely to cover a larger area, and the chance of handoffs will be smaller.

(4) Past Mobility Pattern 507 - Users who roamed extensively in the past are likely to roam extensively in the future.

(5) Brand and model of mobile device 508 - Sometimes a particular type of mobile device has vastly different resource usage. For example, a user with a touch screen phone will use more data services than a user with a feature phone that does not have touch screen support.

(6) Installed Mobile Applications 509 - Some mobile applications are more "chatty" than others and trigger many more connections.

(7) OS and firmware version of the mobile device 510 - With different OS versions, the requirements may be different. For example, the messenger application on Apple iOS 8 supports voice and text messaging in addition to text. That is likely to translate into higher throughput usage.

(8) The user's subscription plan 511 - for example, a user with a low data cap will use less data than a user with a large data cap.

(9) Remaining Quota 512 for the current billing period - for example, a user with a low remaining quota is likely to be more constrained in bandwidth usage than a user with a large quota remaining.

(10) Demographic profile of the user 513 - For example, usage behavior is likely to be significantly different between a teenage user and an adult user. A teenage user is likely to consume more data through his/her social activities, while an adult user may use more voice calls than data in his/her daily activities.

Figure 6 is a system diagram of a mobile network according to certain embodiments of the present disclosure. Figure 6 shows a Home Subscriber Server (HSS) 601, a Mobility Management Entity (MME) 602, a Charging System 603, an eNodeB 604, a System Architecture Evolution (SAE) Gateway 605, and an Analysis Server 606. All elements shown in Figure 6 may be traditional or virtual.

In some embodiments, some operators may have an analysis server 606 that collects and analyzes usage statistics about users. This information can be fed directly into the prediction engine. In other embodiments, the prediction engine includes the analysis capabilities of the analysis server 606, and the two components are classified into one unit.

The Home Subscriber Server (HSS) 601 contains information about the user's mobility. The mobility information may be periodically fed into the analysis server 606 to calculate the user's past mobility patterns.

Mobility Management Entity (MME) 602 tracks the current location of the device and may send the location information to analysis server 606 for further processing.

The billing system contains the user's subscription plan, remaining quota and other billing related information. The billing information can be fed to the analysis server 606 for use in usage trend determination.

The SAE gateway 605 can inspect all traffic to and from users. Using deep packet inspection (DPI) technology, usage information can be extracted from data traffic, including device brand and model, installed and recently used applications, OS and firmware versions, etc. In some embodiments, DPI data is fed into the analytics server 606 for further analysis before being used by the prediction engine.

In some embodiments, a user's usage trends change slowly over time. When usage trends change slowly, the usage prediction engine does not need to update its predictions for the user in real time. For example, the prediction for a particular user may be updated weekly, with different intervals for different users. In some embodiments, usage trends change more rapidly. For example, when certain events occur, the predictions can be triggered to update on demand. For example, if the user switches to a different subscription plan or a new phone, the predictions can be updated immediately.

When a new subscriber joins the network, there will be no further usage history from which to construct predictions. Initially, the new user can be treated as an "average" user with average throughput and signaling load. Alternatively, predictions can be made based on the limited amount of information available. For example, if the new subscriber is a teenager, he/she is likely to have more talkative applications such as Facebook, Instagram, or Snapchat, which will incur more signaling load. If instead the new subscriber is a business account that has signed up for tethering, he/she is likely to be a heavier data user. The prediction update frequency for new users can be higher so that the prediction can converge quickly based on newly acquired factors. At this stage, the user can be placed on either the traditional system or the NFV system. Once the user is classified, he/she can then be moved between the traditional and NFV systems to achieve optimal use of network resources.

Figure 7 is a system diagram illustrating capacity optimization in a mobile network according to some embodiments of the present invention. Figure 7 shows a prediction engine 701, a serving gateway (SGW) 702, a traditional packet data network gateway (PGW) 703, and an NFV-based PGW 704.

When a subscriber answers a call, the phone attempts to establish a session with the mobile network. This request is ultimately sent to the SGW 701, which selects a PGW 703 or 704 to direct the user session to. One of the PGW nodes includes legacy equipment 703, and the other PGW node includes an NFV-based platform. Normally, the SGW selects a PGW based solely on the Access Point Name (APN). The APN identifies the Packet Data Network (PDN) with which a mobile data user wants to communicate and is assigned to the user when the user activates their subscription plan. In a preferred embodiment, the SGW consults a prediction engine to determine the best location to direct the user session to based on the user's characteristics. For example, the classifier/prediction engine may provide an API based on Simple Object Access Protocol (SOAP) or Representational State Transfer (REST), which the SGW can call to obtain information about where to establish the session. Once the SGW decides to establish a session on, for example, an NFV-based PGW, all future signaling and data traffic related to the subscriber will be handled by the selected PGW.

The subject matter described herein can be realized with digital electronic circuits or with computer software, firmware or hardware (including structural components disclosed in this specification and structural equivalents thereof) or with a combination thereof. The subject matter described herein can be realized as one or more computer program products, such as tangibly embodied in an information carrier (for example, in a machine-readable storage device) or embodied in a propagation signal so as to be executed or controlled by a data processing device (for example, a programmable processor, a computer or a plurality of computers) One or more computer programs of its operation. A computer program (also referred to as a program, software, software application or code) can be written in any form of programming language (including compiled or interpreted language), and it can be deployed in any form, including as an independent program or as a module, component, subroutine or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file. The program can be stored in a part of a file that keeps other programs or data, in a single file dedicated to the program in question or in multiple coordination files (for example, files storing one or more modules, subroutines or code portions). A computer program can be deployed to execute on a computer or on multiple computers located at one location or distributed across multiple locations and interconnected by a communication network.

The processes and logic flows described in this specification (including the method steps of the subject matter described herein) can be performed by one or more programmable processors executing one or more computer programs to perform the functions of the subject matter described herein by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuitry, and the apparatus of the subject matter described herein can also be implemented as special purpose logic circuitry such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

Processors suitable for executing computer programs include, by way of example, general-purpose and special-purpose microprocessors, and any one or more processors of any type of digital computer. Typically, a processor will receive instructions and data from a read-only memory or a random-access memory, or both. Essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include, or be operatively coupled to, one or more mass storage devices (e.g., magnetic, magneto-optical, or optical disks) to receive data from, transfer data to, or both for storing data. Suitable information carriers for embodying computer program instructions and data include all forms of non-volatile memory, including, by way of example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks (e.g., internal hard disks or removable disks); magneto-optical disks; and optical disks (e.g., CD and DVD disks). The processor and memory may be supplemented by, or incorporated into, specialized logic circuitry.

To provide for interaction with a user, the subject matter described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and pointing device (e.g., a mouse or trackball) that the user can use to provide input to the computer. Other types of devices can also be used to provide for interaction with the user. For example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback) and input from the user can be received in any manner, including but not limited to acoustic, voice, or tactile input.

The subject matter described herein can be implemented in a computing system that includes a back-end component (e.g., a data server), a middleware component (e.g., an application server), or a front-end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an embodiment of the subject matter described herein), or any combination of such back-end, middleware, and front-end components. The components of the system can be interconnected using any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LANs") and wide area networks ("WANs"), such as the Internet.

It should be understood that the disclosed subject matter is not limited in its application to the details of the arrangement and construction of components set forth in the following description or illustrated in the drawings. The disclosed subject matter is capable of other embodiments and of being practiced and carried out in various ways. Furthermore, it should be understood that the phraseology and terminology employed herein are for descriptive purposes only and should not be construed as limiting.

Likewise, those skilled in the art will recognize that the concepts upon which this disclosure is based may be readily utilized as a basis for designing other structures, methods, and systems for carrying out the multiple purposes of the disclosed subject matter. It is important, therefore, that the claims be regarded as including such equivalent constructions as long as they do not depart from the spirit and scope of the disclosed subject matter.

While the disclosed subject matter has been described and illustrated in the foregoing exemplary embodiments, it should be understood that the disclosure is made by way of example only and that numerous changes in details of the embodiments of the disclosed subject matter may be made without departing from the spirit and scope of the disclosed subject matter, which is limited only by the following claims.

Claims (10)

1. A computerized method for optimizing the capacity of network devices in a mobile network, the computerized method comprising: A computing device receives a usage prediction based on a user identifier and a user attribute, wherein the user identifier corresponds to a characteristic of a mobile network user and the user attribute corresponds to at least one characteristic of mobile network usage by the mobile network user, and the usage prediction includes information corresponding to the expected future data usage of the mobile network user, wherein the expected future data usage corresponds to at least one mobile resource. The computing device receives a capacity level from at least one of a conventional packet data network gateway (PGW) and a network function virtualization (NFV) PGW, wherein the conventional packet data network gateway includes a fixed capacity for the at least one mobile resource and the NFV PGW includes a configurable capacity for the at least one mobile resource; A computing device determines a routing decision based on usage predictions and capacity levels, the routing decision being associated with a Guiding Service Gateway (SGW) to route mobile network users to at least one of a legacy packet data network gateway and an NFV PGW; and The computing device sends the routing decision to the SGW. 2. The computerized method of claim 1, wherein the at least one characteristic of mobile network use by the mobile network user includes the amount of prior mobile network use, the time associated with mobile network use, the location of the mobile device corresponding to the mobile user, the amount of time spent roaming on the mobile device, the brand and model of the mobile device, the applications installed on the mobile device, the operating system and firmware version of the mobile device, the subscription plan, the remaining credit limit, and demographic information. 3. The computerized method according to claim 1, wherein the at least one characteristic of the mobile network user includes a mobile device ID or a telephone number. 4. The computerized method according to claim 1, wherein receiving user attributes further includes receiving user attributes from at least one of the Home Subscriber Server (HSS), Mobility Management Entity (MME), Billing System, and System Architecture Evolution (SAE) Gateway. 5. The computerized method according to claim 1, wherein the mobile resources include at least one of signaling activity, throughput, session occupancy, encryption, and code conversion. 6. A system for optimizing the capacity of network devices in a mobile network, the system comprising: Processor; and A memory coupled to the processor and storing computer-readable instructions thereon, which, when executed by the processor, cause the processor to: Receive a usage prediction based on a user identifier and user attributes, wherein the user identifier corresponds to a characteristic of a mobile network user and the user attributes correspond to at least one characteristic of mobile network usage by the mobile network user, and the usage prediction includes information corresponding to the expected future data usage of the mobile network user, wherein the expected future data usage corresponds to at least one mobile resource. The receiving capacity level is from at least one of a conventional packet data network gateway (PGW) and a network function virtualization (NFV) PGW, wherein the conventional packet data network gateway includes a fixed capacity for the at least one mobile resource and the NFV PGW includes a configurable capacity for the at least one mobile resource; Routing decisions are determined based on usage predictions and capacity levels, and these decisions are associated with a Guiding Serving Gateway (SGW) to route mobile network users to at least one of a Legacy Packet Data Network Gateway (LPRG) and an NFV PGW; and The routing decision is sent to the SGW. 7. The system of claim 6, wherein the at least one characteristic of mobile network use by the mobile network user includes the amount of prior mobile network use, the time associated with mobile network use, the location of the mobile device corresponding to the mobile user, the amount of time spent roaming on the mobile device, the brand and model of the mobile device, the applications installed on the mobile device, the operating system and firmware version of the mobile device, the subscription plan, the remaining credit limit, and demographic information. 8. The system of claim 6, wherein the at least one characteristic of the mobile network user includes a mobile device ID or a telephone number. 9. The system of claim 6, wherein the processor is further prompted to receive user attributes from at least one of the Home Subscriber Server (HSS), Mobility Management Entity (MME), Billing System, and System Architecture Evolution (SAE) Gateway. 10. The system of claim 6, wherein the mobile resources include at least one of signaling activity, throughput, session occupancy, encryption, and code conversion.