Power consumer demand control method based on edge calculation

Abstract

The invention belongs to the technical field of edge computing, and particularly relates to a power consumer demand control method based on edge computing, which comprises the following steps: acquiring consumer edge historical load data; performing load curve clustering based on the user historical load data to obtain a typical load curve; establishing a user side energy storage configuration model and a user side energy storage income model considering demand control; and based on the typical load curve and the user-side energy storage income model, calculating an optimal configuration parameter in the user-side energy storage configuration model. According to the method, the computing nodes are deployed at the edge of the power grid, so that real-time acquisition, processing and optimal control of data are realized, the problems caused by centralized control are effectively solved, and the real-time performance and accuracy of power grid management are improved.

Description

Technical Field

[0001] The present invention belongs to the field of edge computing technology, and specifically relates to a method for controlling power user demand based on edge computing. Background Art

[0002] With the rapid development of smart grids, the requirements for refined management of power grids are increasing. Demand control, as an important means of power management, limits the power consumption of users in a specific time period to balance the load of the power grid and avoid overload of the power grid. At the same time, the peak shaving and valley filling technology discharges the energy storage system during peak loads and charges during valley loads to smooth the load curve of the power grid and improve the operation efficiency of the power grid. However, the coordinated control of demand control and peak shaving and valley filling in the existing technology often relies on a centralized computing platform, which has problems such as data transmission delay and limited computing resources. In addition, the load curve corresponding to each edge device is affected by the environment in which it is located and has different localized characteristics.

[0003] The importance of existing demand control to the refined management of power grids is increasing day by day. Through demand control, grid load balancing, overload avoidance, peak shaving and valley filling can be achieved to smooth the load curve, thereby improving grid operation efficiency, reducing demand electricity charges, and saving electricity costs. Therefore, research on demand control is being carried out from all angles. However, in the existing mainstream technology, the coordinated control of demand control and peak shaving and valley filling is completed by the cloud computing center. The cloud platform collects the power consumption data of each device, analyzes the grid load operation according to the corresponding algorithm, obtains relevant results, and then sends the corresponding control strategy to each device to realize the function of demand control. Based on the above choices, the existing demand control strategy has problems such as data transmission delay, data loss, limited computing resources, and response lag. Summary of the invention

[0004] The purpose of the present invention is to provide a method for demand control of power users based on edge computing. By deploying computing nodes at the edge of the power grid, real-time collection, processing and optimization control of data can be realized, which effectively solves the problems caused by centralized control and improves the real-time and accuracy of power grid management.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A power user demand control method based on edge computing, comprising:

[0007] Obtain historical load data of user edge;

[0008] Perform load curve clustering based on the user's historical load data to obtain a typical load curve;

[0009] Establish a user-side energy storage configuration model and a user-side energy storage revenue model that considers demand control;

[0010] Based on the typical load curve and the user-side energy storage benefit model, the optimal configuration parameters in the user-side energy storage configuration model are calculated.

[0011] In a preferred solution, the step of obtaining user edge historical load data includes:

[0012] Install edge computing equipment and energy storage systems on the power user side and ensure smooth communication between the two;

[0013] After the edge computing device is started, it automatically collects user load data, device status information and external environment parameters, and uploads them to the local database.

[0014] In a preferred embodiment, the typical load curve is a load variation curve generated during the operation of the distribution network system in the past period of time, and is determined by the average value of the load at the same time in three months, that is, Where ob represents the edge device number, · represents the range of all working days, j∈[0~23] represents hours, and Mean represents the average value.

[0015] In a preferred solution, the step of clustering load curves based on the user's historical load data to obtain a typical load curve includes:

[0016] Obtain user load curves, and randomly select several load curves from the user load curves as initial load clustering centers;

[0017] Calculate the Euclidean distance from each load curve to each cluster center;

[0018] For each load curve, compare the Euclidean distances to the cluster centers and find the minimum value to classify;

[0019] Calculate the average value of each type of load data, and use the averaged load curve as the new cluster center of each type;

[0020] Compare the distance between the new cluster center and the previous cluster center;

[0021] In response to the distance being greater than an initially set threshold, after recalculating the Euclidean distance from each load curve to each cluster center, the distance between the new cluster center and the previous cluster center is compared;

[0022] In response to the distances of all cluster centers being less than a set threshold, a clustering curve and a final cluster center are output;

[0023] The optimal number of clusters with the minimum DBI index in the final cluster center is obtained through the traversal method, and the clustering curve corresponding to the optimal number of clusters is the typical load curve.

[0024] In a preferred embodiment, the load curve clustering calculation process is to complete real-time calculation and response in an edge computing device.

[0025] In a preferred embodiment, the energy storage configuration model includes an energy storage system device cost model, an energy storage system power balance model, an energy storage device charging and discharging power model, and a peak shaving and valley filling model.

[0026] In a preferred solution, the user-side energy storage revenue model has a built-in user-side energy storage revenue objective function, and the formula of the user-side energy storage revenue objective function is:

[0027] F max =D+C trans -W inv -C oper

[0028] In the formula, F max The energy storage income at the user side; C trans The transformer cost reduction due to the maximum demand reduction; W inv Energy storage investment cost for users; C oper It is the energy storage operation and maintenance cost throughout the entire life cycle.

[0029] A second object of the present invention is to provide an edge computing-based power user demand control system, using the edge computing-based power user demand control method, the system comprising:

[0030] A data collection module is used to obtain historical load data of user edges;

[0031] An edge load curve clustering module, used for clustering load curves based on the user's historical load data to obtain a typical load curve;

[0032] Energy storage configuration model building module, used to build a user-side energy storage configuration model and a user-side energy storage benefit model considering demand control;

[0033] Optimal configuration parameter calculation module: Based on the typical load curve and the user-side energy storage benefit model, it calculates the optimal configuration parameters in the user-side energy storage configuration model.

[0034] In a preferred solution, the edge load curve clustering module performs load curve clustering calculation process by first completing real-time calculation and response in the edge computing device, the edge computing device stores historical iterative clustering results, and obtains the latest clustering data according to the load data acquisition module;

[0035] The cloud control center comprehensively processes the calculation results of each edge device;

[0036] The control decision module of the cloud platform will adjust the cloud demand control algorithm based on the data uploaded by each edge device. The adjustment result will generate a control strategy and send the corresponding adjustment instructions to the relevant edge devices;

[0037] The edge device sets its own charging and discharging power again according to the control strategy instructions received.

[0038] A third object of the present invention is to provide a control terminal, comprising:

[0039] A storage medium, which is used to store instructions and is also used for local data calculation and receiving remote scheduling from a cloud control center;

[0040] A processor, the processor is used to execute the power user demand control method based on edge computing according to the instruction

[0041] The technical effect achieved by the present invention is: by deploying computing resources on edge devices, real-time monitoring and prediction of power user loads and intelligent scheduling of energy storage equipment are achieved. This algorithm can not only effectively reduce the demand electricity charges of power users and improve the economic benefits of energy storage systems, but also improve the stability and reliability of power systems, providing strong technical support for the development of smart grids.

[0042] The collaborative control method of the present invention comprehensively considers the needs of demand control and energy storage optimization, and realizes effective collaboration between the two through the real-time data processing and decision-making capabilities of edge computing nodes. During the control process, the edge computing node dynamically adjusts the demand control threshold and the charging and discharging strategy of the energy storage system according to the real-time changes in the grid load to ensure that the grid load fluctuates within a safe and economical range;

[0043] of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the process of the present invention;

[0045] Figure 2 It is a module schematic diagram of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0049] Please refer to the attached Figure 1 As shown, it is a first embodiment of the present invention, which provides a power user demand control method based on edge computing, including:

[0050] Obtain historical load data of user edge;

[0051] Based on the user's historical load data, load curves are clustered to obtain typical load curves, and the clustering process is to complete real-time calculation and response in the edge computing device;

[0052] Establish a user-side energy storage configuration model and a user-side energy storage revenue model that considers demand control;

[0053] Based on the typical load curve and the user-side energy storage benefit model, the optimal configuration parameters in the user-side energy storage configuration model are calculated.

[0054] In this embodiment, the energy storage configuration model includes an energy storage system device cost model, an energy storage system power balance model, an energy storage device charging and discharging power model, and a peak shaving and valley filling model. Based on the above models.

[0055] The process of obtaining the historical load data of the user edge is to install edge computing equipment and energy storage systems on the power user side.

[0056] and ensure smooth communication between the two;

[0057] After the edge computing device is started, it automatically collects user load data, device status information and external environment parameters, and uploads them to the local database.

[0058] The above control method includes edge computing, energy storage system, smart meter and power grid control center. The edge computing node is deployed at the key node of the power grid, responsible for collecting power grid operation data, executing demand control algorithm, monitoring load curve, and sending control instructions to energy storage system and smart meter. Among them, edge computing refers to an open platform that integrates network, computing, storage and application core capabilities at the edge of the network close to the source of objects or data, providing edge intelligent services nearby, and meeting the key requirements of industry digitalization in agile connection, real-time business, data optimization, application intelligence, security and privacy protection. The demand control method in the present invention is based on the real-time data processing capability of edge computing nodes, dynamically adjusting the user's power usage restrictions, first according to historical data and real-time load forecasts, set the demand threshold for each time period (such as more than 90% of the transformer load, of course, it can also be other settings, specifically set according to actual conditions); then, monitor the user's actual power consumption in real time, and when the actual power consumption exceeds the demand threshold, send a control signal to the user through the smart meter to limit its power usage. By utilizing the computing power of edge computing devices, combined with historical load data, user production plan information, weather forecasts and other factors, an accurate load forecasting method is constructed to predict the power load curve in the future. The model uses advanced machine learning algorithms, such as long short-term memory networks (LSTM), to improve the accuracy and robustness of the forecast. According to the predicted load curve and the status information of the energy storage system, an intelligent energy storage scheduling strategy is executed. This strategy comprehensively considers the charging and discharging efficiency, remaining power, life cycle cost and grid constraints of the energy storage equipment, and dynamically adjusts the charging and discharging strategy of the energy storage equipment to maximize the reduction of demand electricity charges and improve the economic benefits of the energy storage system while meeting the user's electricity demand.

[0059] In order to further understand and explain the typical load curve, the following is a specific discussion of it. The typical load curve is a load change curve generated during the operation of the distribution network system in the past period of time, and is determined by the average value of the load at the same time in three months, that is, Where ob represents the edge device number, · represents the range of all working days, j∈[0~23] represents hours, and Mean represents the average value.

[0060] In a preferred embodiment, referring to FIG. X, the steps of clustering load curves based on the user's historical load data to obtain a typical load curve include:

[0061] Obtain user load curves, and randomly select several load curves from the user load curves as initial load clustering centers;

[0062] Calculate the Euclidean distance from each load curve to each cluster center;

[0063] For each load curve, compare the Euclidean distances to the cluster centers and find the minimum value to classify;

[0064] Calculate the average value of each type of load data, and use the averaged load curve as the new cluster center of each type;

[0065] Compare the distance between the new cluster center and the previous cluster center;

[0066] In response to the distance being greater than an initially set threshold, after recalculating the Euclidean distance from each load curve to each cluster center, the distance between the new cluster center and the previous cluster center is compared;

[0067] In response to the distances of all cluster centers being less than a set threshold, a clustering curve and a final cluster center are output;

[0068] The optimal number of clusters with the minimum DBI index in the final cluster center is obtained through the traversal method, and the clustering curve corresponding to the optimal number of clusters is the typical load curve.

[0069] In order to better understand the energy storage configuration model, it is further analyzed below, wherein the energy storage configuration model includes an energy storage system device cost model, an energy storage system power balance model, an energy storage device charging and discharging power model, and a peak shaving and valley filling model.

[0070] Furthermore, the energy storage system device cost model is:

[0071] The investment in energy storage configuration mainly includes fixed investment costs and subsequent operation and maintenance costs, where W = W 1 +W 2 +W 3 , W is the total fixed investment cost; W 1 Expressed as investment cost of battery cells, etc.; W 2 Represents the investment cost of PCS equipment; W 3 Expressed as the investment cost of EMS control module;

[0072] The operation and maintenance cost is C = fQ, where C represents the annual system operation and maintenance cost; f represents the actual annual operation investment per unit of power; and Q represents the rated power of the system.

[0073] Furthermore, the power balance model of the energy storage system is:

[0074] T load (t) = P load (t)+P EES (t)

[0075] T peak,m =(1-δ m )peak,m

[0076] In the formula, P load (t) is the actual load of the user, P EES (t) is the power of the energy storage device, P EES (t)>0 is charging state, P EES (t)<0 is the discharge state, T load (t) is the actual power of the user's grid connection point, δ m is the peak reduction rate after configuring the energy storage device, P peak,m is the peak power of the user's grid connection point when no energy storage device is equipped (natural month), T peak,m It is the peak power of the user's grid connection point after the energy storage device is installed (natural month);

[0077] Furthermore, the charging and discharging power model of the energy storage device is:

[0078] P EES (t) = P c (t)B c (t)-P dc (t)B dc (t)

[0079] 0≤P c (t)≤B c (t)P cmax

[0080] 0≤P dc (t)≤B dc (t)P dcmax

[0081] B c (t)+B dc (t)≤1

[0082] In the formula, P EES (t) is the power of the energy storage device, P c (t) is the energy storage charging power, P dc (t) is the energy storage discharge power, P cmax is the rated charging power, P dcmax is the rated discharge power, B c (t) and B dc (t) is a Boolean variable (corresponding to the charging and discharging status);

[0083] Furthermore, the peak shaving and valley filling model is:

[0084] P load (t)+P EES (t)≤(1-δ m ) peak,m .

[0085] It is also necessary to further explain that the optimal configuration parameters in the user-side energy storage configuration model are calculated based on the typical load curve and the user-side energy storage benefit objective function.

[0086] The peak-shaving and valley-filling effect achieved by energy storage equipment can generate peak-valley price difference benefits. D represents the cost-benefit value of electricity purchased by users; P 1 And P 2 Respectively represent the discharge and charging power values ​​in a certain period of time; c represents the actual electricity price data in a certain period of time; x represents time.

[0087] The user-side energy storage revenue model has a built-in user-side energy storage revenue objective function, and the formula of the user-side energy storage revenue objective function is:

[0088] F max =D+C trans -W inv -C oper

[0089] In the formula, F max The energy storage income at the user side; C trans The transformer cost is reduced due to the reduction of maximum demand (peak load); W inv Energy storage investment cost for users; C oper It is the energy storage operation and maintenance cost throughout the entire life cycle.

[0090] like Figure 2 As shown, the second object of the present invention is to provide an edge computing-based power user demand control system, using the edge computing-based power user demand control method, the system includes:

[0091] A data collection module is used to obtain historical load data of user edges;

[0092] An edge load curve clustering module, used for clustering load curves based on the user's historical load data to obtain a typical load curve;

[0093] Energy storage configuration model building module, used to build a user-side energy storage configuration model and a user-side energy storage benefit model considering demand control;

[0094] Optimal configuration parameter calculation module: Based on the typical load curve and the user-side energy storage benefit model, it calculates the optimal configuration parameters in the user-side energy storage configuration model.

[0095] Among them, when the data acquisition module is executed, it is necessary to install edge computing equipment and energy storage systems on the power user side and ensure smooth communication between the two. After the edge computing device is started, it automatically collects user load data, equipment status information, external environmental parameters, etc., and uploads them to the local database.

[0096] The edge load curve clustering module performs load curve clustering calculation process by first completing real-time calculation and response in the edge computing device, the edge computing device stores historical iterative clustering results, and obtains the latest clustering data according to the load data acquisition module;

[0097] The cloud control center comprehensively processes the calculation results of each edge device;

[0098] The control decision module of the cloud platform will adjust the cloud demand control algorithm based on the data uploaded by each edge device. The adjustment result will generate a control strategy and send the corresponding adjustment instructions to the relevant edge devices;

[0099] The edge device sets its own charging and discharging power again according to the control strategy instructions received.

[0100] In the above system, by installing edge computing equipment and energy storage system on the power user side and ensuring smooth communication between the two, after the edge computing equipment is started, it automatically collects user load data, equipment status information and external environmental parameters, and uploads them to the local database. The load forecasting model (using the average value of the load at the same time in 3 months) is used to predict the power load curve in the future, and the prediction results are stored in the edge computing device. According to the predicted load curve and energy storage system status information, the energy storage scheduling strategy is formulated, and the charging and discharging strategy of the energy storage equipment is adjusted in real time. The actual power demand of the user is monitored in real time through the edge computing device, and compared and analyzed with the predicted load curve. According to the default set threshold (such as exceeding 90% of the transformer load), the scheduling instruction of the energy storage system is triggered, and the charging and discharging work of the corresponding edge device is suspended. The comprehensive benefit evaluation module monitors and evaluates the operation effect of the algorithm in real time, and generates visual reports and charts for users to view and analyze.

[0101] A third object of the present invention is to provide a control terminal, comprising:

[0102] A storage medium, which is used to store instructions and is also used for local data calculation and receiving remote scheduling from a cloud control center;

[0103] A processor is used to execute the power user demand control method based on edge computing according to the instruction.

[0104] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A power user demand control method based on edge computing, characterized in that: include Obtain historical load data of user edge; Perform load curve clustering based on the user's historical load data to obtain a typical load curve; Establish a user-side energy storage configuration model and a user-side energy storage revenue model that considers demand control; Based on the typical load curve and the user-side energy storage benefit model, the optimal configuration parameters in the user-side energy storage configuration model are calculated.

2. The power user demand control method based on edge computing according to claim 1 is characterized in that: The step of obtaining user edge historical load data includes: Install edge computing equipment and energy storage systems on the power user side and ensure smooth communication between the two; After the edge computing device is started, it automatically collects user load data, device status information and external environment parameters, and uploads them to the local database.

3. The power user demand control method based on edge computing according to claim 1 is characterized in that: The typical load curve is a load variation curve generated during the operation of the distribution network system in the past period of time, and is determined by the average value of the load at the same time in three months, that is, Where ob represents the edge device number, · represents all working days in 3 months, j∈[0~23] represents hours, and Mean represents the average value.

4. The power user demand control method based on edge computing according to claim 1 is characterized in that: The step of clustering load curves based on the user's historical load data to obtain a typical load curve comprises: Obtain user load curves, and randomly select several load curves from the user load curves as initial load clustering centers; Calculate the Euclidean distance from each load curve to each cluster center; For each load curve, compare the Euclidean distances to the cluster centers and find the minimum value to classify; Calculate the average value of each type of load data, and use the averaged load curve as the new cluster center of each type; Compare the distance between the new cluster center and the previous cluster center; In response to the distance being greater than an initially set threshold, after recalculating the Euclidean distance from each load curve to each cluster center, the distance between the new cluster center and the previous cluster center is compared; In response to the distances of all cluster centers being less than a set threshold, a clustering curve and a final cluster center are output; The optimal number of clusters with the minimum DBI index in the final cluster center is obtained through the traversal method, and the clustering curve corresponding to the optimal number of clusters is the typical load curve.

5. The power user demand control method based on edge computing according to claim 1 is characterized in that: The load curve clustering calculation process is to complete real-time calculation and response in the edge computing device.

6. The power user demand control method based on edge computing according to claim 1 is characterized in that: The energy storage configuration model includes an energy storage system device cost model, an energy storage system power balance model, an energy storage device charging and discharging power model, and a peak shaving and valley filling model.

7. The power user demand control method based on edge computing according to claim 1 is characterized in that: The user-side energy storage revenue model has a built-in user-side energy storage revenue objective function, and the formula of the user-side energy storage revenue objective function is: F max =D+C trans -W inv -C oper In the formula, F max The energy storage income at the user side; C trans The transformer cost reduction due to the maximum demand reduction; W inv Energy storage investment cost for users; C oper It is the energy storage operation and maintenance cost throughout the entire life cycle.

8. An edge computing-based power user demand control system, characterized in that: Using the method for power user demand control based on edge computing according to any one of claims 1 to 7, the system comprises: A data collection module is used to obtain historical load data of user edges; An edge load curve clustering module, used for clustering load curves based on the user's historical load data to obtain a typical load curve; Energy storage configuration model building module, used to build a user-side energy storage configuration model and a user-side energy storage benefit model considering demand control; Optimal configuration parameter calculation module: Based on the typical load curve and the user-side energy storage benefit model, it calculates the optimal configuration parameters in the user-side energy storage configuration model.

9. The power user demand control system based on edge computing according to claim 8, characterized in that: The edge load curve clustering module performs load curve clustering calculation process by first completing real-time calculation and response in the edge computing device, which stores historical iterative clustering results and obtains the latest clustering data according to the load data acquisition module; The cloud control center comprehensively processes the calculation results of each edge device; The control decision module of the cloud platform will adjust the cloud demand control algorithm based on the data uploaded by each edge device. The adjustment result will generate a control strategy and send the corresponding adjustment instructions to the relevant edge devices; The edge device sets its own charging and discharging power again according to the control strategy instructions received.

10. A control terminal, characterized in that: include: A storage medium, which is used to store instructions and is also used for local data calculation and receiving remote scheduling from a cloud control center; A processor, wherein the processor is used to execute the power user demand control method based on edge computing according to any one of claims 1-7.

Images