Abnormal data collaborative solving system and method based on multi-agent technology

Abstract

The invention relates to an abnormal data cooperative solving system and method based on a multi-agent technology, and is applied to the technical field of electric quantity abnormal data processing, and the method comprises the steps: constructing a multi-agent system based on an EMS (energy management system) and a TMR (electric energy metering system), obtaining a sample related to abnormal data through the integration of the active power of a corresponding telemetering point of the EMS, and obtaining a sample related to the abnormal data; according to the method, a corresponding approximation function expression is obtained through curve fitting, an estimated value corresponding to abnormal data is calculated, then a substitution value of the abnormal data is calculated through the estimated value, automation and intelligentization of abnormal meter bottom code data monitoring and solving and numerical substitution of the electric energy metering system are achieved, new requirements and challenges are flexibly met, and the method is suitable for large-scale popularization and application. The overall operation efficiency of the electricity market is improved; moreover, the method does not depend on the accuracy and linear law of feature selection, and the precision of a correction result is higher than that of an existing Adaboost algorithm and a Newton interpolation method.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal electricity data processing, and in particular to an abnormal data collaborative solving system and method based on multi-agent technology. Background Art

[0002] Electricity data is an important basis for electricity market transaction settlement, and is also a data source for calculating grid line losses and evaluating grid operation indicators. In the electricity settlement system, ensuring the reliability and integrity of electricity data is related to the economic interests of both the buyer and seller of electricity. In order to minimize the impact of meter failures on settlement and ensure fairness, it is currently common to use the main and auxiliary meters of the metering point for simultaneous measurement, and use the metering data of the peer assessment meter and the electric energy metering system (Tele Meter Reading, TMR) data as auxiliary calculation information, and the energy management system (Energy Management System, EMS) data as reference information. However, if there is insufficient basis to determine the electricity during the failure or inaccuracy, the buyer and seller of electricity need to negotiate and determine the settlement electricity. Therefore, the accuracy of the metering data is a basic element of electricity settlement.

[0003] Existing technical solutions include a reverse electricity anomaly recognition method based on the Adaboost algorithm, which constructs a feature vector set and completes the analysis of the electric energy meter state feature rules. However, it relies on the accuracy of feature selection. Improper feature selection may lead to misjudgment. After determining the erroneous table code value sequence fragment, the Newton interpolation method is often used to obtain the data at the time point to be corrected. Since the table code value at each time point does not necessarily follow a linear law, the correction accuracy needs to be improved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide an abnormal data collaborative solving system and method based on multi-agent technology to solve the problem in the prior art that it relies on the accuracy of feature selection. If the feature selection is inappropriate, it may lead to misjudgment. After determining the erroneous table code value sequence fragment, the Newton interpolation method is often used to calculate the data of the time point to be corrected. Since the table code value of each time point does not necessarily follow a linear law, the correction accuracy is low.

[0005] According to a first aspect of an embodiment of the present invention, a system for collaboratively solving abnormal data based on multi-agent technology is provided, the system comprising:

[0006] An abnormal meter bottom code data monitoring agent module and a data processing agent module distributed in the electric energy metering system, a data generation agent module and a numerical estimation agent module distributed in the energy management system;

[0007] The abnormal table bottom code data monitoring agent module is used to monitor abnormal electric energy data in the electric energy metering system;

[0008] Also used for sending a request to generate sample data to the data generation agent module;

[0009] The data generation agent module is used to generate sample data according to the abnormal power data after receiving the sample data request from the data organization agent module;

[0010] Also used for sending the sample data to the numerical estimation agent module;

[0011] The numerical estimation agent module obtains the corresponding approximation function by curve fitting according to the sample data provided by the data generation agent module, and obtains the estimated value of the power at the abnormal moment according to the approximation function;

[0012] Also used for sending the estimated value of the power at the abnormal moment to the data processing agent module;

[0013] After receiving the estimated value of the power at the abnormal moment, the data processing agent module obtains the meter bottom code value at the abnormal moment according to the estimated value of the power at the abnormal moment.

[0014] Preferably,

[0015] The abnormal table bottom code data monitoring agent module is also used to generate an abnormal data point number and an abnormal time stamp according to the abnormal electric energy data.

[0016] Preferably,

[0017] The electric energy metering system further includes: a data organization agent module;

[0018] The abnormal table bottom code data monitoring agent module is also used to send an abnormal data processing request to the data organization agent module, and the abnormal data processing request includes the abnormal data point number and the abnormal time stamp;

[0019] The data organization agent module is used to generate the point number and integration time period of the energy management system's electricity integration according to the abnormal data point number and abnormal time stamp after receiving the abnormal data processing request sent by the abnormal table bottom code data monitoring agent module;

[0020] The data organization agent module is also used to send a sample data generation request to the data generation agent module, and the sample data request includes the point number and integration time period of the electric quantity integration;

[0021] The data generation agent module is used to generate sample data according to the point number and integration time period of the electric quantity integration at the abnormal moment after receiving the sample data request of the data organization agent module.

[0022] Preferably, it also includes:

[0023] The data processing agent module sends the table bottom code value at the abnormal moment to the data organization agent module;

[0024] The data organization proxy module replaces the original electric energy data at the abnormal moment according to the meter bottom code value at the abnormal moment, and implements recalculation and re-statistical processing of the electric energy through the replaced meter bottom code value at the abnormal moment.

[0025] Preferably,

[0026] The data organization agent module is also used to generate an abnormal data record log according to the abnormal data point number and abnormal time stamp contained in the abnormal data processing request after receiving the abnormal data processing request issued by the abnormal table bottom code data monitoring agent module.

[0027] Preferably,

[0028] The method of obtaining a corresponding approximation function by curve fitting and obtaining an estimated value of power at the abnormal moment according to the approximation function includes:

[0029] According to the sample data, using a curve fitting method to obtain various approximation functions of the energy management system;

[0030] It is also used to calculate the sum of square errors of each approximation function, and select the approximation function with the smallest sum of square errors as the optimal approximation function;

[0031] The estimated value of the electric quantity at the abnormal moment is obtained according to the optimal approximation function.

[0032] Preferably,

[0033] The method of using curve fitting to obtain various approximation functions of the energy management system includes:

[0034] The sample data is curve-fitted using basis functions of a polynomial method, a hyperbolic method, and an exponential method, respectively, to obtain approximation functions corresponding to the polynomial method, the hyperbolic method, and the exponential method.

[0035] According to a second aspect of an embodiment of the present invention, a method for collaboratively solving abnormal data based on multi-agent technology is provided. The method is based on any one of the above systems, and the method includes:

[0036] Acquire abnormal electric energy data in the electric energy metering system, and generate an abnormal data point number and an abnormal time stamp according to the abnormal electric energy data;

[0037] Generate a point number and an integration time period for the electric quantity integration at the abnormal moment according to the abnormal data point number and the abnormal moment time stamp;

[0038] Generate sample data according to the point number and integration time period of the electric quantity integration at the abnormal moment;

[0039] According to the sample data, using approximation functions corresponding to a plurality of curve fitting methods;

[0040] Calculate the sum of square errors of each approximation function, and select the approximation function with the smallest sum of square errors as the optimal approximation function;

[0041] Obtaining an estimated value of the power at the abnormal moment according to the optimal approximation function;

[0042] The meter bottom code value at the abnormal moment is obtained according to the estimated power value at the abnormal moment.

[0043] Preferably, it also includes:

[0044] The original electric energy data at the abnormal moment is replaced according to the meter bottom code value at the abnormal moment, and the electric energy is recalculated and re-statistically processed through the replaced meter bottom code value at the abnormal moment.

[0045] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0046] The present application constructs a multi-agent system based on EMS (energy management system) and TMR (electricity metering system). By integrating the active power of the corresponding telemetering point of EMS, samples related to abnormal data are obtained, and the corresponding approximate function is obtained by curve fitting and the estimated value corresponding to the abnormal data is calculated. Then, the estimated value is used to calculate the replacement value of the abnormal data, thereby realizing the automation and intelligence of abnormal table bottom code data monitoring, solution and numerical replacement of the electric energy metering system, flexibly adapting to new needs and challenges, and improving the overall operation efficiency of the power market. Moreover, the method of obtaining relevant samples by integration, obtaining the corresponding approximate function by curve fitting and calculating the estimated value corresponding to the abnormal data does not rely on the accuracy and linear law of feature selection, and the accuracy of the correction result is higher than that of the existing Adaboost algorithm and Newton interpolation method.

[0047] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0049] Figure 1 is a system schematic diagram of an abnormal data collaborative solution system based on multi-agent technology according to an exemplary embodiment;

[0050] Figure 2is a schematic diagram of a framework of an abnormal data collaborative solution system based on multi-agent technology according to another exemplary embodiment;

[0051] Figure 3 is a flowchart of a method for collaboratively solving abnormal data based on multi-agent technology according to another exemplary embodiment;

[0052] In the attached drawings: 1- abnormal table bottom code data monitoring agent module, 2- data organization agent module, 3- data processing agent module, 4- data generation agent module, 5- numerical estimation agent module. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0054] Embodiment 1

[0055] Figure 1 is a system diagram of an abnormal data collaborative solution system based on multi-agent technology according to an exemplary embodiment. Figure 1 As shown, the system includes:

[0056] An abnormal table bottom code data monitoring agent module 1, a data organization agent module 2 and a data processing agent module 3 distributed in an electric energy metering system (TMR), a data generation agent module 4 and a numerical estimation agent module 5 distributed in an energy management system (EMS);

[0057] It can be understood that an agent is an entity with active behavior capability obtained by abstracting the decision-making or control tasks in the process operation. It can use mathematical calculations or rule reasoning to complete specific operation tasks, and interact with process objects and other agents through message mechanisms to complete information transmission and coordination. The general characteristics of an agent include autonomy, spontaneity, social ability and responsiveness; Multi-Agent System (MAS) System) is usually used to solve problems that a single agent cannot handle. Using MAS, distributed problems can be easily solved, and the system has strong scalability. For the application of multi-agent technology in power systems, the existing related technologies summarize the scope of application: ① Data, control and resources are in a distributed environment and need to be coordinated; ② The software modules in the system are independent of each other but communicate with each other, and certain functions or tasks need to be achieved through cooperation or competition; ③ Use different programming languages ​​or different hardware platforms to achieve certain functions or tasks that require mutual cooperation in the system, and then the original software needs to be packaged and communication functions added. At the same time, it is pointed out that multi-agent technology is not only suitable for distributed computing and design of power systems, power market calculation and simulation, etc., but is also expected to be more widely used in research related to power systems; Since the research content of abnormal moment electric energy estimation in this application is a typical numerical collaborative solution problem in a resource and task distribution environment, the use of multi-agent technology is an ideal choice.

[0058] This application mainly includes five Agent entities. The logical relationship between the agents is as shown in the attached Figure 2 As shown;

[0059] Among them, the abnormal table bottom code data monitoring agent module 1, that is, the attached Figure 2 The DMA in the system is used to monitor the abnormal data of the TMR system and form the abnormal data point number and abnormal time stamp;

[0060] The abnormal table bottom code data monitoring agent module 1 is also used to send data to the data organization agent module 2, that is, the attached Figure 2 The DOA in the sends an abnormal data processing request;

[0061] The data organization agent module 2 forms and maintains an abnormal data record log according to the abnormal data processing request;

[0062] The data organization agent module 2 is also used to form the point number and integration time period of the EMS system electricity integration according to the request of the meter bottom code data monitoring agent module 1;

[0063] The data organization agent module 2 is also used to generate data for the agent module 4, that is, the attached Figure 2 The SGA in the generates a request for sample data;

[0064] The data generation agent module 4 realizes the electric quantity integration of the corresponding measuring point of the EMS system and forms sample data according to the request of the data organization agent module 2;

[0065] The data generation agent module 4 is also used to provide the value estimation agent module 5, that is, the attached Figure 2 The NEA in provides sample data for curve fitting;

[0066] The numerical estimation agent module 5 uses the curve fitting method (selecting polynomial, hyperbola and exponential type basis functions respectively) to obtain the approximate function of the EMS power corresponding to the corresponding curve fitting method according to the samples provided by the data generation agent module 4. It is worth noting that polynomial fitting is a mathematical and machine learning method that uses a polynomial function to fit a set of data points. The purpose of polynomial fitting is to find a polynomial that satisfies the distribution of sample points among a large number of sample points. Based on the properties of the polynomial function, it can be expressed as y=w0+w1x+w2x 2 +……, can approximate the actual data distribution by adjusting the degree and coefficient of the polynomial. Polynomial fitting can adapt to various complex data distributions by adjusting the degree of the polynomial, thereby capturing the nonlinear relationship of the data; while hyperbola fitting is to fit the curve by taking the logarithm of the measured data of the two variables, and use the fitted curve equation to analyze the relationship between the two variables. Commonly used fitting methods include least squares method and visual inspection method. Hyperbola fitting can handle data with nonlinear relationships and can fit a smooth curve, especially the values ​​within a limited range. Exponential type fitting refers to the process of fitting data points using exponential functions. Exponential functions are usually used to describe processes that grow or decay over time. This fitting method adjusts the parameters of the exponential function to make it as close to the actual data points as possible, thereby describing the growth or decay trend of the data; by adjusting the parameters of the exponential function, different types of data trends, including growth and decay, can be flexibly fitted;

[0067] The present application calculates the sum of square errors of the three approximation functions obtained based on the three fitting methods, and selects the approximation function with the smallest value as the optimal approximation function, that is, selects the approximation function of the electric energy value closest to the abnormal moment of the present application;

[0068] The optimal approximation function is used to obtain the estimated value of the power at the abnormal time and send the value to the data processing agent module 3, that is, the attached Figure 2 DDA in

[0069] The data processing agent module 3 completes the calculation of the abnormal timetable base code value according to the estimated value provided by the numerical estimation agent module 5;

[0070] The data processing agent module 3 also completes the replacement of the table bottom code value of the abnormal data point and the recalculation and re-statistical processing of the electricity through interaction with the data organization agent module 2;

[0071] The data processing agent module 3 notifies the data organizing agent module 2 that the task is completed.

[0072] Embodiment 2

[0073] Figure 3 is a flow chart of a method for collaboratively solving abnormal data based on multi-agent technology according to another exemplary embodiment, the method comprising:

[0074] S1, obtaining abnormal electric energy data in the electric energy metering system, and generating an abnormal data point number and an abnormal time stamp according to the abnormal electric energy data;

[0075] S2, generating a point number and an integration time period for the electric quantity integration at the abnormal moment according to the abnormal data point number and the abnormal moment time stamp;

[0076] S3, generating sample data according to the point number and integration time period of the electric quantity integration at the abnormal moment;

[0077] S4, using approximation functions corresponding to a plurality of curve fitting methods according to the sample data;

[0078] S5, calculating the sum of square errors of each approximation function, and selecting the approximation function with the smallest sum of square errors as the optimal approximation function;

[0079] S6, obtaining an estimated value of the power at the abnormal moment according to the optimal approximation function;

[0080] S7, obtaining the meter bottom code value at the abnormal moment according to the estimated power value at the abnormal moment.

[0081] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0082] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0083] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0084] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0085] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0086] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0087] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0088] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0089] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. The abnormal data collaborative solution system based on multi-agent technology is characterized by: The system comprises: An abnormal meter bottom code data monitoring agent module and a data processing agent module distributed in the electric energy metering system, a data generation agent module and a numerical estimation agent module distributed in the energy management system; The abnormal table bottom code data monitoring agent module is used to monitor abnormal electric energy data in the electric energy metering system; Also used for sending a request to generate sample data to the data generation agent module; The data generation agent module is used to generate sample data according to the abnormal power data after receiving the sample data request from the data organization agent module; Also used for sending the sample data to the numerical estimation agent module; The numerical estimation agent module obtains the corresponding approximation function by curve fitting according to the sample data provided by the data generation agent module, and obtains the estimated value of the power at the abnormal moment according to the approximation function; Also used for sending the estimated value of the power at the abnormal moment to the data processing agent module; After receiving the estimated value of the power at the abnormal moment, the data processing agent module obtains the meter bottom code value at the abnormal moment according to the estimated value of the power at the abnormal moment.

2. The system according to claim 1, characterized in that The abnormal table bottom code data monitoring agent module is also used to generate an abnormal data point number and an abnormal time stamp according to the abnormal electric energy data.

3. The system according to claim 2, characterized in that The electric energy metering system further includes: a data organization agent module; The abnormal table bottom code data monitoring agent module is also used to send an abnormal data processing request to the data organization agent module, and the abnormal data processing request includes the abnormal data point number and the abnormal time stamp; The data organization agent module is used to generate the point number and integration time period of the energy management system's electricity integration according to the abnormal data point number and abnormal time stamp after receiving the abnormal data processing request sent by the abnormal table bottom code data monitoring agent module; The data organization agent module is also used to send a sample data generation request to the data generation agent module, and the sample data request includes the point number and integration time period of the electric quantity integration; The data generation agent module is used to generate sample data according to the point number and integration time period of the electric quantity integration at the abnormal moment after receiving the sample data request of the data organization agent module.

4. The system according to claim 1, characterized in that Also includes: The data processing agent module sends the table bottom code value at the abnormal moment to the data organization agent module; The data organization agent module replaces the original electric energy data at the abnormal moment according to the meter bottom code value at the abnormal moment, and implements recalculation and re-statistical processing of the electric energy through the replaced meter bottom code value at the abnormal moment.

5. The system according to claim 3, characterized in that The data organization agent module is also used to generate an abnormal data record log according to the abnormal data point number and abnormal time stamp contained in the abnormal data processing request after receiving the abnormal data processing request issued by the abnormal table bottom code data monitoring agent module.

6. The system according to claim 1, characterized in that The method of obtaining a corresponding approximation function by curve fitting and obtaining an estimated value of power at the abnormal moment according to the approximation function includes: According to the sample data, using a curve fitting method to obtain various approximation functions of the energy management system; It is also used to calculate the sum of square errors of each approximation function, and select the approximation function with the smallest sum of square errors as the optimal approximation function; The estimated value of the electric quantity at the abnormal moment is obtained according to the optimal approximation function.

7. The system according to claim 6, characterized in that The method of using curve fitting to obtain various approximation functions of the energy management system includes: The sample data is curve-fitted using basis functions of a polynomial method, a hyperbolic method, and an exponential method, respectively, to obtain approximation functions corresponding to the polynomial method, the hyperbolic method, and the exponential method.

8. The method for collaboratively solving abnormal data based on multi-agent technology is characterized by: The method is based on the system according to any one of claims 1 to 7, and the method comprises: Acquire abnormal electric energy data in the electric energy metering system, and generate an abnormal data point number and an abnormal time stamp according to the abnormal electric energy data; Generate a point number and an integration time period for the electric quantity integration at the abnormal moment according to the abnormal data point number and the abnormal moment time stamp; Generate sample data according to the point number and integration time period of the electric quantity integration at the abnormal moment; According to the sample data, using approximation functions corresponding to a plurality of curve fitting methods; Calculate the sum of square errors of each approximation function, and select the approximation function with the smallest sum of square errors as the optimal approximation function; Obtaining an estimated value of the power at the abnormal moment according to the optimal approximation function; The meter bottom code value at the abnormal moment is obtained according to the estimated power value at the abnormal moment.

9. The method according to claim 8, characterized in that Also includes: The original electric energy data at the abnormal moment is replaced according to the meter bottom code value at the abnormal moment, and the electric energy is recalculated and re-statistically processed through the replaced meter bottom code value at the abnormal moment.

Images