Load balancing control method, device, computer equipment, readable storage medium and program product

Abstract

The present application relates to a load balancing control method, device, computer equipment, readable storage medium and program product. The method comprises: obtaining historical load data of an object to be regulated; in the process of analyzing and testing the object to be regulated based on load parameters, obtaining performance data of the object to be regulated; determining the load balancing control scheme corresponding to the object to be regulated according to the performance data; in the case of receiving a load request, processing the historical load data through a load prediction model to obtain a predicted load value, and performing load balancing control on the object to be regulated based on the predicted load value and the load balancing control scheme. The method can dynamically adjust the load distribution ratio according to the load condition of the object to be regulated in real time, accurately realize the load control of the power system, and thus improve the stability of the power system and the resource utilization rate.

Description

Technical Field

[0001] The present application relates to the field of power grid operation and control technology, and in particular to a load balancing control method, device, computer equipment, readable storage medium and program product. Background Art

[0002] Load balance refers to the balance between power supply and demand in the power system. It is crucial to the normal operation of the power system and the guarantee of power supply quality. When there is an imbalance between load and power supply capacity, the power system is prone to overload or underload, resulting in unstable operation of the power system and even possible system collapse. Therefore, through reasonable load balance regulation, the stable operation of the power system can be guaranteed, the power supply quality can be improved, and the utilization of power resources can be optimized.

[0003] In traditional methods, due to limitations of network bandwidth, communication protocols and other factors, data transmission delays and processing lags often occur, which in turn affects the timeliness and accuracy of regulatory decisions. Summary of the invention

[0004] Based on this, it is necessary to provide a load balancing control method, device, computer equipment, readable storage medium and program product that can accurately realize load control of the power system in response to the above technical problems.

[0005] In a first aspect, the present application provides a load balancing control method, comprising:

[0006] Obtain historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters;

[0007] In the process of analyzing and testing the object to be regulated based on the load parameters, obtaining performance data of the object to be regulated;

[0008] Determine the load balancing control scheme corresponding to the object to be controlled based on the performance data; the load balancing control scheme includes load forecasting model, request access strategy, message sending strategy, task allocation strategy, load balancing strategy and connection restriction strategy;

[0009] When a load request is received, the historical load data is processed through the load forecasting model to obtain a predicted load value, and load balancing control is performed on the regulated object based on the predicted load value and the load balancing control scheme.

[0010] In one embodiment, the step of analyzing and testing the object to be regulated based on the load parameters includes:

[0011] Configure and analyze the test environment based on load parameters and resource parameters;

[0012] Determine the target load conditions based on performance requirements. In the analysis and testing environment, analyze and test the regulated object according to the target load conditions. The target load conditions include normal load, peak load and abnormal load.

[0013] In one of the embodiments, the request access strategy includes using an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through a message queue; the task allocation strategy includes using a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters; the load balancing strategy includes using a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0014] In one of the embodiments, the objects to be regulated include multiple processing units; the task allocation strategy also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to perform resource allocation and resource restriction on all processing units.

[0015] In one embodiment, the method further comprises:

[0016] Configure the experimental environment, and perform load testing on the regulated objects according to the load balancing regulation scheme in the experimental environment;

[0017] Obtain the test results of the load test; the test results include response time, throughput and error rate;

[0018] The load balancing control scheme is updated according to the test results, and the step of performing load testing on the control object according to the load balancing control scheme is returned, and the execution is continued until the test results of the load test meet the preset requirements.

[0019] In one embodiment, the step of updating the load balancing control scheme according to the test result includes:

[0020] Determine the performance defects of the load balancing control scheme based on the test results;

[0021] The model parameters of the load forecasting model, as well as the algorithm parameters of the task allocation strategy and load balancing strategy are adjusted according to the performance defects.

[0022] In a second aspect, the present application also provides a load balancing control device, comprising:

[0023] The load acquisition module is used to obtain the historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters;

[0024] A performance acquisition module is used to acquire performance data of the object to be regulated in the process of analyzing and testing the object to be regulated based on load parameters;

[0025] A scheme determination module is used to determine the load balancing control scheme corresponding to the object to be controlled according to the performance data; the load balancing control scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy;

[0026] The load control module is used to process historical load data through the load forecasting model to obtain a predicted load value when a load request is received, and to perform load balancing control on the control object based on the predicted load value and the load balancing control scheme.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method steps of any one of the first aspects are implemented.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements any one of the method steps in the first aspect when the computer program is executed by a processor.

[0029] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the method steps in the first aspect when executed by a processor.

[0030] The above-mentioned load balancing control method, device, computer equipment, computer-readable storage medium and computer program product obtain historical load data of the object to be regulated, and obtain performance data of the object to be regulated in the process of analyzing and testing the object to be regulated based on load parameters. According to the performance data, the load balancing control scheme corresponding to the object to be regulated is determined. When a load request is received, the historical load data is processed by a load prediction model to obtain a predicted load value, and load balancing control is performed on the object to be regulated based on the predicted load value and the load balancing control scheme. The functions of access, transmission, distribution, balancing and balancing of the object to be regulated are realized through the load balancing control scheme. The load distribution ratio can be dynamically adjusted according to the load situation of the object to be regulated in real time, and the load control of the power system can be accurately realized, thereby improving the stability of the power system and the resource utilization rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0032] FIG1 is an application environment diagram of a load balancing control method in one embodiment;

[0033] FIG2 is a schematic diagram of a flow chart of a load balancing control method in one embodiment;

[0034] FIG3 is a schematic flow chart of a load balancing control method in another embodiment;

[0035] FIG4 is a structural block diagram of a load balancing control device in one embodiment;

[0036] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0038] The load balancing control method provided in the embodiment of the present application can be applied in the application environment shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 is used to obtain the historical load data of the object to be regulated, and in the process of analyzing and testing the object to be regulated based on the load parameters, the performance data of the object to be regulated is obtained, and the load balancing control scheme corresponding to the object to be regulated is determined according to the performance data. In the case of receiving a load request through the server 104, the historical load data is processed through the load prediction model to obtain the predicted load value, and the load balancing control scheme is used to control the object to be regulated based on the predicted load value and the load balancing control scheme. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0039] In an exemplary embodiment, as shown in FIG2 , a load balancing control method is provided, which is described by taking the method applied to the terminal 102 in FIG1 as an example, and includes the following steps 202 to 208. Among them:

[0040] S202: Acquire historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters.

[0041] Optionally, the object to be regulated refers to a power system that needs to be load balanced, such as a distribution network. In the power system, load balancing regulation is an important process to ensure a balance between power supply and demand. Before load balancing regulation, the system's load conditions, performance requirements, and resource constraints are tested and analyzed by obtaining historical load data of the object to be regulated, thereby simulating the operating state of the power system under different load conditions.

[0042] S204: In the process of analyzing and testing the object to be regulated based on the load parameters, performance data of the object to be regulated is obtained.

[0043] Optionally, when analyzing and testing the object to be regulated, different load conditions can be simulated through testing tools, such as testing the system performance by simulating concurrent access to the power system by multiple users, and collecting and analyzing the performance data generated during the test. Through these performance data, the performance and resource utilization of the object to be regulated under different load conditions can be evaluated.

[0044] S206: Determine a load balancing control scheme corresponding to the object to be controlled based on the performance data; the load balancing control scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy.

[0045] Optionally, based on the acquired performance data, a suitable algorithm or model is used to implement the access, transmission, distribution, balancing and equalization functions of the power system, wherein the load balancing control scheme refers to a set of all strategies used to implement these functions, including load forecasting models, access request strategies, message sending strategies, task allocation strategies, load balancing strategies and connection restriction strategies, etc., wherein the load forecasting model is used to predict the load value of the regulated object in the future, the access request strategy is used to limit the way other terminals access the power system, the message sending strategy is used to realize asynchronous data transmission within the power system, the task allocation strategy is used to realize the distribution of load tasks within the power system, the load balancing strategy is used to realize load balancing, and the connection restriction strategy is used to limit the number of connections or bandwidth connected to the power system to protect the stability of the system and resource utilization.

[0046] Alternatively, the load forecasting model can be established by a time series analysis method (such as ARIMA), the input variable of the model is time (t), the output variable is the predicted load value (l), and the load forecasting model is expressed as: l_t = f(t). Alternatively, load forecasting is performed by using a linear regression model, the input variables of the linear regression model are time (t) and weather conditions (w), and the output variable is the predicted load value (l), then the load forecasting model can be expressed as: l = a * t + b * w + c, where a, b, and c are regression coefficients, representing the degree of influence of time and weather on the load.

[0047] S208: When a load request is received, the historical load data is processed by a load forecasting model to obtain a predicted load value, and load balancing control is performed on the object to be controlled based on the predicted load value and the load balancing control scheme.

[0048] Optionally, when a new load request is received, the load forecasting model is combined with historical load data to predict the possible future predicted value of the system, that is, the load value that the object to be regulated needs to bear. The load balancing control scheme is used to perform load balancing control on the object to be regulated, so that the object to be regulated meets the requirements of the predicted load value while ensuring the stability and processing efficiency of the power system.

[0049] In the above-mentioned load balancing control method, by obtaining the historical load data of the object to be regulated, in the process of analyzing and testing the object to be regulated based on the load parameters, the performance data of the object to be regulated is obtained, and the load balancing control scheme corresponding to the object to be regulated is determined according to the performance data. When a load request is received, the historical load data is processed by the load prediction model to obtain a predicted load value, and load balancing control is performed on the object to be regulated based on the predicted load value and the load balancing control scheme. The functions of access, transmission, distribution, balancing and balancing of the object to be regulated are realized through the load balancing control scheme, and the load distribution ratio can be dynamically adjusted according to the load situation of the object to be regulated in real time, and the load control of the power system can be accurately realized, thereby improving the stability of the power system and the resource utilization rate.

[0050] In an exemplary embodiment, the steps of analyzing and testing the regulated object based on load parameters include: configuring an analysis and testing environment according to load parameters and resource parameters; determining target load conditions according to performance requirements, and analyzing and testing the regulated object according to the target load conditions in the analysis and testing environment; the target load conditions include normal load, peak load and abnormal load.

[0051] Optionally, the analysis test environment can be configured through a load testing tool. In the analysis test environment, by simulating different load conditions, the load conditions, performance requirements and resource constraints of the object to be regulated are tested and analyzed to obtain the performance parameters of the object to be regulated.

[0052] In this embodiment, by analyzing and testing the object to be regulated according to the target load conditions in the analysis and testing environment, the load conditions, performance requirements and resource constraints of the object to be regulated can be accurately analyzed, thereby accurately realizing load regulation of the power system.

[0053] In an exemplary embodiment, the request access strategy includes adopting an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through message queues; the task allocation strategy includes adopting a weighted polling algorithm to distribute load tasks according to load parameters and resource parameters; the load balancing strategy includes adopting a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0054] Optionally, the request access strategy includes adopting an HTTP-based API (such as a RESTful API) as the access protocol of the object to be regulated, and sending user data or requests to the power system through an HTTP request. The message sending strategy includes realizing data transmission through a message queue. When data or a request is received, the data is sent to the message queue, and when processing, the corresponding data is received by subscribing to the message. The task allocation strategy includes adopting a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters. The load balancing strategy includes adopting a load balancing algorithm to balance load tasks according to latency and queue length. When allocating load tasks, the load balancing algorithm is combined to achieve the purpose of load balancing. The connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements to protect the stability of the system and resource utilization.

[0055] In this embodiment, the functions of access, transmission, distribution, balancing and equalization of the object to be regulated are realized through the load balancing control scheme. The load distribution ratio can be dynamically adjusted in real time according to the load conditions of the object to be regulated, and the load control of the power system can be accurately realized, thereby improving the stability of the power system and resource utilization.

[0056] In an exemplary embodiment, the objects to be regulated include multiple processing units; the task allocation strategy also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to perform resource allocation and resource restriction on all processing units.

[0057] Optionally, the object to be regulated includes multiple processing units. During regulation, the task allocation strategy also includes load task allocation according to the performance parameters of each processing unit. For example, there are n processing units, the load of each processing unit is Li (i=1,2, ..., n), and the performance parameter is represented by Ci (i=1,2, ..., n). Then the task allocation strategy can be expressed as: Pi = (Ci / ΣC) * Ltotal, where Pi is the load proportion allocated to the i-th processing unit, and Ltotal is the total load (i.e., the predicted load value). In addition, the least connection algorithm can be used to preferentially allocate load tasks to processing units with fewer connections to ensure the resource utilization of the processing units. The load balancing strategy also includes load task balancing according to the processing speed and queue length of each processing unit. For example, the queue length of processing unit i is Qi, and the processing speed is Si, then the load balancing strategy is expressed as: Bi = Qi / Si, where Bi is the load balancing index of the i-th processing unit. The connection limitation strategy also includes using a cluster resource manager to allocate and limit resources for all processing units. For example, a bandwidth limitation formula is used to limit the bandwidth of the power system. The preset total bandwidth is Btotal, and the bandwidth requirement of each connection is Bi. The bandwidth limitation formula can be expressed as: ΣBi≤Btotal, where Bi is the bandwidth requirement of the i-th connection.

[0058] In this embodiment, the functions of access, transmission, distribution, balancing and equalization of the object to be regulated are realized through the load balancing control scheme. The load distribution ratio can be dynamically adjusted in real time according to the load conditions of the object to be regulated, and the load control of the power system can be accurately realized, thereby improving the stability of the power system and resource utilization.

[0059] In an exemplary embodiment, the method also includes: configuring an experimental environment, in which a load test is performed on the regulated object according to the load balancing control scheme; obtaining the test results of the load test; the test results include response time, throughput and error rate; updating the load balancing control scheme according to the test results, returning to the step of performing a load test on the regulated object according to the load balancing control scheme, and continuing to execute until the test results of the load test meet the preset requirements.

[0060] Optionally, by configuring an experimental environment (for example, using a Docker container), in the experimental environment, a load test is performed on the regulated object according to the load balancing regulation scheme, and by simulating the load and sending requests, the performance and stability of the power system are analyzed according to the test results, thereby verifying the regulation effect of the load balancing regulation scheme. Among them, the test results include response time, throughput and error rate. By analyzing the test results, the performance bottlenecks and problems of the power system are determined, and the load balancing regulation scheme is adjusted, including adjusting algorithm parameters, increasing hardware resources, etc., to optimize the performance and stability of the power system. Among them, the response time refers to the average response time calculated by recording the response time of each request. The throughput refers to the throughput calculated by counting the number of requests processed per unit time, such as the number of requests processed per second. The error rate refers to the error situation of each request recorded, such as connection failure, timeout, and calculating the error rate.

[0061] In this embodiment, by performing a load test on the regulated object according to the load balancing control scheme in an experimental environment, obtaining the test results of the load test, and updating the load balancing control scheme according to the test results, it is possible to ensure the control effect of adjusting the load balancing control scheme and improve the performance and stability of the power system.

[0062] In an exemplary embodiment, the step of updating the load balancing control scheme according to the test results includes: determining the performance defects of the load balancing control scheme according to the test results; adjusting the model parameters of the load prediction model, and the algorithm parameters of the task allocation strategy and the load balancing strategy according to the performance defects.

[0063] Optionally, based on the test results obtained, analyze the performance defects of the load balancing control scheme, such as long response time, low throughput, or high error rate, and adjust the algorithm parameters in a targeted manner based on the analysis results. For example, in the load balancing algorithm, adjust parameters such as weight distribution and task scheduling strategy to improve the load balancing effect. In the prediction model, adjust the model training parameters such as window size, sliding step size, etc. according to the verification results to improve the prediction accuracy.

[0064] In this embodiment, by performing a load test on the regulated object according to the load balancing control scheme in an experimental environment, obtaining the test results of the load test, and updating the load balancing control scheme according to the test results, it is possible to ensure the control effect of adjusting the load balancing control scheme and improve the performance and stability of the power system.

[0065] In an exemplary embodiment, as shown in FIG3 , a load balancing control method is provided, the method comprising the following steps:

[0066] Obtain historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters;

[0067] Configure the analysis and testing environment according to load parameters and resource parameters; determine the target load conditions according to performance requirements, and in the analysis and testing environment, analyze and test the regulated objects according to the target load conditions; the target load conditions include normal load, peak load and abnormal load.

[0068] In the process of analyzing and testing the object to be regulated based on the load parameters, obtaining performance data of the object to be regulated;

[0069] Determine the load balancing control scheme corresponding to the object to be controlled based on the performance data; the load balancing control scheme includes load forecasting model, request access strategy, message sending strategy, task allocation strategy, load balancing strategy and connection restriction strategy;

[0070] Among them, the request access strategy includes using HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through message queues; the task allocation strategy includes using a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters; the load balancing strategy includes using a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0071] Among them, the objects to be regulated include multiple processing units; the task allocation strategy also includes load task allocation according to the performance parameters of each processing unit; the load balancing strategy also includes load task balancing according to the processing speed and queue length of each processing unit; the connection restriction strategy also includes using the cluster resource manager to allocate and restrict resources for all processing units.

[0072] When a load request is received, the historical load data is processed through the load forecasting model to obtain a predicted load value, and load balancing control is performed on the regulated object based on the predicted load value and the load balancing control scheme.

[0073] Configure the experimental environment, in which load test is performed on the regulated object according to the load balancing control scheme; obtain the test results of the load test; the test results include response time, throughput and error rate; update the load balancing control scheme according to the test results, return to the steps of performing load test on the regulated object according to the load balancing control scheme, and continue to execute until the test results of the load test meet the preset requirements.

[0074] Determine the performance defects of the load balancing control scheme based on the test results; adjust the model parameters of the load forecasting model, as well as the algorithm parameters of the task allocation strategy and the load balancing strategy based on the performance defects.

[0075] In this embodiment, by obtaining historical load data of the object to be regulated, in the process of analyzing and testing the object to be regulated based on load parameters, the performance data of the object to be regulated is obtained, and the load balancing control scheme corresponding to the object to be regulated is determined according to the performance data. When a load request is received, the historical load data is processed by a load prediction model to obtain a predicted load value, and load balancing control is performed on the object to be regulated based on the predicted load value and the load balancing control scheme. The functions of access, transmission, distribution, balancing and balancing of the object to be regulated are realized through the load balancing control scheme. The load distribution ratio can be dynamically adjusted in real time according to the load situation of the object to be regulated, and the load control of the power system can be accurately realized, thereby improving the stability of the power system and the resource utilization rate.

[0076] In an exemplary embodiment, taking the object to be regulated as an electric vehicle charging pile as an example, the method includes:

[0077] (1) Collect historical load and performance data of each charging pile by testing and analyzing the load conditions, performance requirements, and resource constraints of the charging piles.

[0078] Optionally, assuming that the charging pile number is: (i): 1, 2, 3; time: (t): 1, 2, 3, ... , n; historical load data (l_history): contains the load value of each charging pile in the past n time units. For example, the acquired historical load data can be expressed as: l_history= {"1": [10, 15, 20, ... , 25],"2": [5, 10, 12,... , 8],"3": [8, 10, 9, ... , 12]}.

[0079] (2) Based on the results of testing and analysis, observe the behavior of the system and determine the appropriate load balancing control scheme, including access, sending, allocation, and balancing strategies; use HTTP-based API as the access protocol and send the charging pile data or requests to the system through HTTP requests.

[0080] (3) Use machine learning algorithms (such as decision trees and random forests) or deep learning algorithms (such as neural networks) to predict and optimize loads. Use historical load data and real-time data to predict the load conditions of each charging pile in the future, and perform task allocation and load balancing based on the prediction results.

[0081] Optionally, the load forecasting model formula is expressed as: l = f(t, i), where the input variables are time (t) and charging pile number (i), and the output variable is the predicted load value (l).

[0082] Optionally, for each charging pile i, its historical load data l_history[i] is used as the input variable and time t is used as the output variable; the feature matrix X of the training set is the historical load data l_history[i] of each charging pile, and the target vector y is time t; the load forecasting model is trained using the decision tree algorithm; the training set (X, y) is used to fit the decision tree model to obtain the load forecasting model f(t, i).

[0083] (4) Based on the algorithm and prediction model, implement access, sending, allocation and balancing strategies, and build an experimental environment for load and stress testing. Use Docker container technology to build an experimental environment for the charging pile management center, simulate different load conditions through load testing tools, and verify the performance and stability of the system.

[0084] Optionally, when a new load request arrives, it is converted into an HTTP request, which contains the charging pile number i and time t; the load value in the future period is predicted by the load prediction model f(t, i).

[0085] (5) Based on the test and verification results, obtain the system's performance indicators and feedback information, analyze the test results, identify performance bottlenecks and problems, and optimize based on the analysis results. For example, monitor the system's response time, throughput, error rate and other performance indicators, and record the test results.

[0086] In this embodiment, distributed access, transmission, distribution and balancing can be achieved through the load balancing control scheme to improve the performance, scalability and stability of the charging pile management center, ensure that each charging pile can obtain a reasonable power supply, and improve the utilization of the overall system.

[0087] In an exemplary embodiment, taking the object to be regulated as an energy device as an example, the method includes:

[0088] (1) Test and analyze the load conditions, performance requirements, and resource constraints of energy equipment, and collect historical load and performance data of each energy device.

[0089] Optionally, assume that the energy device type (e) is: wind turbine, solar panel, energy storage device; time (t): 1, 2, 3, ... , n; historical load data (l_history): contains the load value of each energy device in the past n time units; illustratively, the acquired historical load data can be expressed as: l_history = {"wind turbine":[100, 150, 200, ... , 250],"solar panel": [50, 60, 70, ... , 80],"energy storage device":[80, 90, 85, ... , 95]}.

[0090] (2) Based on the results of testing and analysis, observe the behavior of the system and determine the appropriate load balancing control scheme, including access, sending, distribution, and balancing strategies; use HTTP-based API as the access protocol to send data or requests from energy devices to the system through HTTP requests.

[0091] (3) Use machine learning algorithms (such as decision trees and random forests) or deep learning algorithms (such as neural networks) for load forecasting and optimization. Use historical load data and real-time data to predict the load conditions of various energy equipment in the future, and perform task allocation and load balancing based on the prediction results.

[0092] Optionally, the load forecasting model formula is expressed as: l = f(t, e), where the input variables are time (t) and energy equipment type (e), and the output variable is the predicted load value (l).

[0093] (4) Based on the algorithm and prediction model, implement access, sending, allocation and balancing strategies, and build an experimental environment for load and stress testing. Use Docker container technology to build an experimental environment for the charging pile management center, simulate different load conditions through load testing tools, and verify the performance and stability of the system.

[0094] Optionally, when a new load request arrives, it is converted into an HTTP request, which contains the energy device type i and time t; the load value in the future period is predicted by the load forecasting model f(t, e).

[0095] (5) Based on the test and verification results, obtain the system's performance indicators and feedback information, analyze the test results, identify performance bottlenecks and problems, and optimize based on the analysis results. For example, monitor the system's response time, throughput, error rate and other performance indicators, and record the test results.

[0096] In this embodiment, distributed access, transmission, distribution and balancing can be achieved through the load balancing control scheme to improve the performance of the smart city energy management system, ensure the load balance of various energy devices, and achieve efficient use and conservation of energy.

[0097] In an exemplary embodiment, taking the object to be regulated as a power grid as an example, the method includes:

[0098] (1) Collect historical load and performance data of each charging pile by testing and analyzing the load conditions, performance requirements, and resource constraints of the power grid.

[0099] Optionally, assume that the number of electricity consumers (n_consumers): 10000; time (t): 1, 2, 3, ..., n; historical load data (l_history): contains the total load value in the past n time units;

[0100] The calculation formula required to predict future loads is:

[0101] Predicted load value (l_prediction) = a * l_history[t-1] + b * l_history[t-2] + c* l_history[t-3];

[0102] Among them, l_prediction: predicted load value, indicating the grid load in the future; a, b, c: coefficients, used to weigh the role of historical load data in load forecasting, they are preset parameters and can be adjusted according to actual conditions; l_history[t-1]: indicates the historical load value of the past time unit; l_history[t-2]: indicates the historical load value of the past two time units; l_history[t-3]: indicates the historical load value of the past three time units.

[0103] (2) Based on the test and analysis results, observe the system behavior and determine the appropriate load balancing control scheme, where the load forecasting model performs load forecasting by using a preset calculation formula.

[0104] (3) Use the preset calculation formula to predict and optimize the load, use historical load data and real-time data to predict the load conditions of each charging pile in the future, and perform task allocation and load balancing based on the prediction results.

[0105] Optionally, define the values ​​of coefficients a, b, c in the calculation formula, for example, select a=0.6, b=0.3, c=0.1, and repeat the test several times until the optimal values ​​of coefficients a, b, c are found.

[0106] (4) Based on the algorithm and prediction model, implement access, sending, allocation and balancing strategies, and build an experimental environment for load and stress testing. Use Docker container technology to build an experimental environment for the charging pile management center, simulate different load conditions through load testing tools, and verify the performance and stability of the system.

[0107] Optionally, assuming that the received load request is l_request = 3000, the preset calculation formula is used to perform load prediction and obtain: l_prediction = a * l_history[t-1] + b * l_history[t-2] + c * l_history[t-3]; l_prediction = 0.6 * l_history[n] + 0.3 * l_history[n-1] + 0.1 *l_history[n-2]; l_prediction = 0.6 * 2500 + 0.3 * 2000 + 0.1 * 1500, where l_prediction = 2400.

[0108] (5) Based on the test and verification results, obtain the system's performance indicators and feedback information, analyze the test results, identify performance bottlenecks and problems, and optimize based on the analysis results. For example, monitor the system's response time, throughput, error rate and other performance indicators, and record the test results.

[0109] In this embodiment, distributed access, transmission, distribution and balancing can be achieved through the load balancing control scheme to improve the performance of the power grid system, ensure the load balance of each processing unit, and achieve efficient utilization and conservation of resources.

[0110] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a load balancing control device for implementing the load balancing control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more load balancing control device embodiments provided below can refer to the limitations of the load balancing control method above, and will not be repeated here.

[0112] In an exemplary embodiment, as shown in FIG4 , a load balancing control device is provided, comprising: a load acquisition module 10, a performance acquisition module 20, a solution determination module 30 and a load control module 40, wherein:

[0113] The load acquisition module 10 is used to acquire the historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters.

[0114] The performance acquisition module 20 is used to acquire performance data of the object to be regulated during the process of analyzing and testing the object to be regulated based on load parameters.

[0115] The scheme determination module 30 is used to determine the load balancing control scheme corresponding to the object to be controlled based on the performance data; the load balancing control scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy.

[0116] The load control module 40 is used to process historical load data through a load prediction model to obtain a predicted load value when a load request is received, and perform load balancing control on the object to be controlled based on the predicted load value and the load balancing control scheme.

[0117] In an exemplary embodiment, the performance acquisition module 20 is also used to configure an analysis and testing environment based on load parameters and resource parameters; determine target load conditions based on performance requirements, and perform analysis and testing on the regulated object in the analysis and testing environment according to the target load conditions; the target load conditions include normal load, peak load and abnormal load.

[0118] In an exemplary embodiment, the request access strategy involved in the solution determination module 30 includes using an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through a message queue; the task allocation strategy includes using a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters; the load balancing strategy includes using a load balancing algorithm to balance load tasks according to latency and queue length; the connection limitation strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0119] In an exemplary embodiment, the object to be regulated includes multiple processing units; the task allocation strategy involved in the solution determination module 30 also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to allocate and restrict resources for all processing units.

[0120] In an exemplary embodiment, the load control module 40 is also used to configure an experimental environment, in which a load test is performed on the regulated object according to the load balancing control scheme; the test results of the load test are obtained; the test results include response time, throughput and error rate; the load balancing control scheme is updated according to the test results, and the step of performing a load test on the regulated object according to the load balancing control scheme is returned, and the execution continues until the test results of the load test meet the preset requirements.

[0121] In an exemplary embodiment, the load control module 40 is also used to determine the performance defects of the load balancing control scheme according to the test results; and adjust the model parameters of the load prediction model, as well as the algorithm parameters of the task allocation strategy and the load balancing strategy according to the performance defects.

[0122] Each module in the above-mentioned load balancing control device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0123] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a load balancing control method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0124] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining historical load data of an object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters; in the process of analyzing and testing the object to be regulated based on the load parameters, obtaining performance data of the object to be regulated; determining a load balancing control scheme corresponding to the object to be regulated based on the performance data; the load balancing control scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy; when a load request is received, processing the historical load data through the load prediction model to obtain a predicted load value, and performing load balancing control on the object to be regulated based on the predicted load value and the load balancing control scheme.

[0126] In one embodiment, the analysis and testing of the regulated object based on load parameters involved in the execution of a computer program by a processor includes: configuring an analysis and testing environment according to load parameters and resource parameters; determining target load conditions according to performance requirements, and analyzing and testing the regulated object according to the target load conditions in the analysis and testing environment; the target load conditions include normal load, peak load and abnormal load.

[0127] In one embodiment, the request access strategy involved when the processor executes the computer program includes using an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through a message queue; the task allocation strategy includes using a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters; the load balancing strategy includes using a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0128] In one embodiment, the object to be regulated includes multiple processing units; the task allocation strategy involved when the processor executes a computer program also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to allocate and restrict resources for all processing units.

[0129] In one embodiment, the processor also implements the following steps when executing the computer program: configuring an experimental environment, in which a load test is performed on the regulated object according to the load balancing control scheme; obtaining the test results of the load test; the test results include response time, throughput and error rate; updating the load balancing control scheme according to the test results, returning to the step of performing a load test on the regulated object according to the load balancing control scheme, and continuing to execute until the test results of the load test meet the preset requirements.

[0130] In one embodiment, the processor executes a computer program that involves updating the load balancing control scheme based on the test results, including: determining the performance defects of the load balancing control scheme based on the test results; adjusting the model parameters of the load prediction model, as well as the algorithm parameters of the task allocation strategy and the load balancing strategy based on the performance defects.

[0131] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: obtaining historical load data of an object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters; in the process of analyzing and testing the object to be regulated based on the load parameters, obtaining performance data of the object to be regulated; determining a load balancing regulation scheme corresponding to the object to be regulated based on the performance data; the load balancing regulation scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy; when a load request is received, the historical load data is processed through the load prediction model to obtain a predicted load value, and load balancing regulation is performed on the object to be regulated based on the predicted load value and the load balancing regulation scheme.

[0132] In one embodiment, when a computer program is executed by a processor, analysis and testing of a regulated object based on load parameters is involved, including: configuring an analysis and testing environment according to load parameters and resource parameters; determining target load conditions according to performance requirements, and analyzing and testing the regulated object according to the target load conditions in the analysis and testing environment; the target load conditions include normal load, peak load and abnormal load.

[0133] In one embodiment, the request access strategy involved when the computer program is executed by the processor includes using an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through a message queue; the task allocation strategy includes using a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters; the load balancing strategy includes using a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0134] In one embodiment, the object to be regulated includes multiple processing units; the task allocation strategy involved when the computer program is executed by the processor also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to allocate and restrict resources for all processing units.

[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the task allocation strategy also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using the cluster resource manager to allocate and restrict resources for all processing units.

[0136] In one embodiment, when a computer program is executed by a processor, the update of a load balancing control scheme based on test results is involved, including: determining performance defects of the load balancing control scheme based on the test results; adjusting model parameters of the load prediction model, as well as algorithm parameters of the task allocation strategy and the load balancing strategy based on the performance defects.

[0137] In one embodiment, a computer program product is provided, including a computer program, which implements the following steps when executed by a processor: obtaining historical load data of an object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters; in the process of analyzing and testing the object to be regulated based on the load parameters, obtaining performance data of the object to be regulated; determining a load balancing regulation scheme corresponding to the object to be regulated based on the performance data; the load balancing regulation scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy; when a load request is received, processing the historical load data through the load prediction model to obtain a predicted load value, and performing load balancing regulation on the object to be regulated based on the predicted load value and the load balancing regulation scheme.

[0138] In one embodiment, when a computer program is executed by a processor, analysis and testing of a regulated object based on load parameters is involved, including: configuring an analysis and testing environment according to load parameters and resource parameters; determining target load conditions according to performance requirements, and analyzing and testing the regulated object according to the target load conditions in the analysis and testing environment; the target load conditions include normal load, peak load and abnormal load.

[0139] In one embodiment, the request access strategy involved when the computer program is executed by the processor includes using an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through a message queue; the task allocation strategy includes using a weighted polling algorithm to allocate load tasks according to load parameters and resource parameters; the load balancing strategy includes using a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the number of accesses to the object to be regulated according to bandwidth requirements.

[0140] In one embodiment, the object to be regulated includes multiple processing units; the task allocation strategy involved when the computer program is executed by the processor also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to allocate and restrict resources for all processing units.

[0141] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the task allocation strategy also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using the cluster resource manager to allocate and restrict resources for all processing units.

[0142] In one embodiment, when a computer program is executed by a processor, the update of a load balancing control scheme based on test results is involved, including: determining performance defects of the load balancing control scheme based on the test results; adjusting model parameters of the load prediction model, as well as algorithm parameters of the task allocation strategy and the load balancing strategy based on the performance defects.

[0143] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0145] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A load balancing control method, characterized in that: The method comprises: Acquire historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters; In the process of analyzing and testing the object to be regulated based on the load parameters, obtaining performance data of the object to be regulated; Determine the load balancing control scheme corresponding to the object to be regulated according to the performance data; the load balancing control scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy; the load prediction model is used to predict the load value of the object to be regulated in a future period of time, the request access strategy is used to limit the way other terminals access the object to be regulated, the message sending strategy is used to realize asynchronous data transmission within the object to be regulated, the task allocation strategy is used to realize the allocation of load tasks within the object to be regulated, the load balancing strategy is used to realize load balancing, and the connection restriction strategy is used to limit the number of connections or bandwidth accessing the object to be regulated, so as to protect the stability and resource utilization of the object to be regulated; When a load request is received, the historical load data is processed by the load forecasting model to obtain a predicted load value, and load balancing control is performed on the object to be regulated based on the predicted load value and the load balancing control scheme so that the object to be regulated meets the requirements of the predicted load value; the predicted load value is the load value that the object to be regulated needs to bear.

2. The method according to claim 1, characterized in that The analyzing and testing the object to be regulated based on the load parameters includes: According to the load parameters and the resource parameters, configure the analysis test environment; The target load condition is determined according to the performance requirement, and in the analysis and testing environment, the object to be regulated is analyzed and tested according to the target load condition; the target load condition includes normal load, peak load and abnormal load.

3. The method according to claim 1, characterized in that The request access strategy includes adopting an HTTP-based API as the access protocol of the object to be regulated; the message sending strategy includes realizing data transmission through a message queue; the task allocation strategy includes adopting a weighted polling algorithm to allocate load tasks according to the load parameters and the resource parameters; the load balancing strategy includes adopting a load balancing algorithm to balance load tasks according to latency and queue length; the connection restriction strategy includes limiting the access quantity of the object to be regulated according to bandwidth requirements.

4. The method according to claim 3, characterized in that The objects to be regulated include multiple processing units; the task allocation strategy also includes load task allocation based on the performance parameters of each processing unit; the load balancing strategy also includes load task balancing based on the processing speed and queue length of each processing unit; the connection restriction strategy also includes using a cluster resource manager to perform resource allocation and resource restriction on all processing units.

5. The method according to claim 1, characterized in that The method further comprises: Configuring an experimental environment, in which a load test is performed on the object to be regulated according to the load balancing regulation scheme; Obtaining the test results of the load test; the test results include response time, throughput and error rate; The load balancing control scheme is updated according to the test result, and the step of performing a load test on the object to be controlled according to the load balancing control scheme is returned to, and the step is continued until the test result of the load test meets the preset requirements.

6. The method according to claim 5, characterized in that The updating of the load balancing control scheme according to the test result includes: Determining the performance defects of the load balancing control scheme according to the test results; The model parameters of the load forecasting model and the algorithm parameters of the task allocation strategy and the load balancing strategy are adjusted according to the performance defect.

7. A load balancing control device, characterized in that: The device comprises: A load acquisition module is used to acquire historical load data of the object to be regulated; the historical load data includes load parameters, performance requirements and resource parameters; A performance acquisition module, used to acquire performance data of the object to be regulated in the process of analyzing and testing the object to be regulated based on the load parameters; A scheme determination module is used to determine the load balancing control scheme corresponding to the object to be regulated according to the performance data; the load balancing control scheme includes a load prediction model, a request access strategy, a message sending strategy, a task allocation strategy, a load balancing strategy and a connection restriction strategy; the load prediction model is used to predict the load value of the object to be regulated in a future period of time, the request access strategy is used to limit the way other terminals access the object to be regulated, the message sending strategy is used to realize asynchronous data transmission within the object to be regulated, the task allocation strategy is used to realize the allocation of load tasks within the object to be regulated, the load balancing strategy is used to realize load balancing, and the connection restriction strategy is used to limit the number of connections or bandwidth accessing the object to be regulated to protect the stability and resource utilization of the object to be regulated; The load control module is used to, upon receiving a load request, process the historical load data through the load prediction model to obtain a predicted load value, and perform load balancing control on the object to be regulated based on the predicted load value and the load balancing control scheme so that the object to be regulated meets the requirements of the predicted load value; the predicted load value is the load value that the object to be regulated needs to bear.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images