Energy consumption data accuracy online evaluation method and system

Abstract

The invention discloses an energy consumption data accuracy online evaluation method and system, and relates to the technical field of data evaluation, and the method comprises the steps: a collection port is connected with a client energy data management system, collects and builds a historical energy consumption database, and obtains energy consumption data according to a preset time interval; preprocessing the energy consumption data, and initializing BP neural network model parameters based on historical data samples; inputting the preprocessed data into a BP neural network, training the BP neural network, and optimizing model parameters through a training error of a minimum sample to obtain a BP neural network model meeting a preset condition; the trained BP neural network model is applied to predict newly transmitted energy consumption data, an absolute error between a predicted value and an actual value is calculated, whether the value is an abnormal value or not is judged according to a preset threshold value, meanwhile, a correction suggestion is provided, and an abnormal judgment threshold value is dynamically adjusted. According to the invention, potential loss caused by data errors is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data evaluation, and in particular to an online evaluation method and system for energy consumption data accuracy. Background Art

[0002] Patent: "A method for detecting the quality of streaming data of energy equipment based on Flinkx" provides a method for detecting the quality of streaming data of energy equipment based on Flinkx. First, the Flinkxjob task is initialized, and the source reading end is constructed to read the data to be inspected, and then the rule engine processing end is created to process the data to be inspected, and then the verification result stream data and the statistical result stream data are written through the sink writing end; the rule engine processing end of the invention adopts the Rete algorithm to quickly verify the data to be inspected by forward reasoning, ensuring the stability of the data verification under high throughput and low latency. For abnormal data, the system provides three inspection methods: null value check, value range check, and fluctuation check. Due to the one-size-fits-all value range detection method, the accuracy of its detection needs to be improved. Paper: "Research on the Quality Assessment of Electric Power Data Based on Hierarchy Analysis Method" adopts the hierarchical analysis method to establish a data quality evaluation index system and evaluation model to achieve effective evaluation of the quality of electric power data, help power grid companies to timely discover and solve power data quality problems, and improve the practicality of the power metering system and the level of power data quality management. The evaluation rule construction is used to evaluate the index score, and the "1-9" scaling method is used to process the index weight. However, this method relies heavily on manual experience in the process of scoring indicators and processing indicator weights, which requires a lot of labor costs, is inefficient, and its accuracy and professionalism need to be considered. Patent: The article "A method for evaluating the quality of online monitoring data of power quality" proposes a method that can effectively and conveniently screen out "distorted" data and ensure the reliability of online monitoring data of power quality. This method checks for outliers by checking the rate of change of k data before and after the data point. This method requires manual determination of the screening threshold and k, which is accidental. In addition, the data used to calculate the rate of change is limited. "Research on the quality evaluation method of online monitoring data of energy consumption" constructs multiple dimensions of data evaluation indicators, including completeness, accuracy, compliance, etc., scores each dimension separately, and summarizes the weighted scores of the scoring agencies as the final scoring results. However, when evaluating data accuracy, the evaluation object is the quality of the measuring instrument, and the evaluation of data accuracy is not intuitive and accurate enough.

[0003] The current research field mainly relies on some relatively traditional methods in data quality monitoring. These methods often lack intuitiveness and effectiveness when evaluating data accuracy. This lag may not only cause data errors to be ignored or delayed in processing, but may also have an adverse impact on the final data quality assessment results of the system. Therefore, the existing data quality monitoring methods urgently need to be improved and innovated to identify and process anomalies in data in a more efficient and accurate way, so as to ensure the reliability and stability of system data quality. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides an online evaluation method and system for energy consumption data accuracy, which can solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides an online evaluation method for the accuracy of energy consumption data, which includes connecting a collection port to a customer energy data management system, collecting and establishing a historical energy consumption database, and acquiring energy consumption data at preset time intervals;

[0009] Preprocessing the energy consumption data and initializing BP neural network model parameters based on historical data samples;

[0010] The preprocessed data is input into the BP neural network, and the BP neural network is trained. The model parameters are optimized by minimizing the training error of the samples to obtain a BP neural network model that meets the preset conditions.

[0011] The trained BP neural network model is used to predict the newly-incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, and determine whether it is an abnormal value based on the preset threshold. At the same time, correction suggestions are provided and the abnormal judgment threshold is dynamically adjusted.

[0012] As a preferred solution of the online evaluation method for energy consumption data accuracy of the present invention, the collecting and establishing of the historical energy consumption database includes:

[0013] Establish an interface with the customer's energy data management system to obtain and store historical energy consumption data.

[0014] The historical energy consumption data includes electricity consumption, water consumption, coal consumption, natural gas consumption and oil consumption;

[0015] Update energy consumption data from the customer energy data management system to the historical energy consumption database based on preset time intervals.

[0016] As a preferred solution of the online evaluation method for energy consumption data accuracy of the present invention, the preprocessing of the obtained data includes:

[0017] The collected energy consumption data is normalized, and the normalization formula is as follows:

[0018]

[0019] in, represents the normalized data, x j (i) represents the original data, max(x j ) and min(x j ) represent the minimum and maximum values ​​in the data respectively;

[0020] The normalized data is divided into training set and test set according to the set ratio.

[0021] As a preferred solution of the online evaluation method for energy consumption data accuracy of the present invention, the training of the BP neural network includes:

[0022] Initialize the learning rate, batch size, number of iterations, number of hidden layers and number of nodes of the BP neural network;

[0023] Use the rand function to initialize all connection weights and thresholds so that w,θ∈(0,1); where w represents the connection weight and θ represents the threshold;

[0024] The hidden layer uses the S-type tangent function tansig as the transfer function, that is,

[0025]

[0026] Where x represents the input signal;

[0027] The output layer uses logsig as the transfer function, that is,

[0028]

[0029] The trainlm algorithm is used as the training function;

[0030] The optimization goal is to minimize the training error of the sample, where the training error calculation formula is as follows:

[0031]

[0032] Among them, y represents the actual value, represents the predicted value;

[0033] The parameters are optimized by gradient descent method, and the parameter update formula is as follows:

[0034]

[0035] Among them, w(t) represents the current weight, η represents the learning rate, represents the gradient of the training error.

[0036] As a preferred solution of the online evaluation method for energy consumption data accuracy of the present invention, the determination of whether it is an abnormal value includes:

[0037] Apply the denormalization formula to restore the normalized output result. The calculation formula is as follows:

[0038] x=x′·(x max -x min )+x min

[0039] Among them, x′ represents the normalized data;

[0040] Calculate the absolute error between the predicted value and the actual value, and calculate the root mean square error. The calculation formula is as follows:

[0041]

[0042] Among them, y i represents the ith actual value, represents the i-th predicted value, n represents the number of samples, and RMSE represents the root mean square error;

[0043] Set the outlier tolerance P, and the calculation formula is as follows:

[0044]

[0045] Among them, P represents the tolerance of outliers;

[0046] Determine whether it exceeds the preset threshold. If it exceeds the preset threshold, the data point is judged to be an outlier, otherwise it is not.

[0047] As a preferred solution of the online energy consumption data accuracy evaluation method of the present invention, the provision of correction suggestions and data quality evaluation reports includes:

[0048] When an outlier is detected, the system sends a warning message to the client and provides a predicted value;

[0049] Regularly generate key data quality reports for each system, analyze and display data quality fluctuations and rule proportions.

[0050] As a preferred solution of the online evaluation method for energy consumption data accuracy of the present invention, the dynamically adjusting abnormality judgment threshold comprises:

[0051] Adjust the setting value of outlier tolerance P;

[0052] The data correction suggestions provided based on deep learning of historical data include:

[0053] Based on the learning results of historical data, corresponding numerical modifications are made according to the detected abnormal values.

[0054] In a second aspect, the present invention provides an online evaluation system for energy consumption data accuracy, which includes: a data acquisition and storage module, a model initialization module, a model training module, and an abnormality judgment module;

[0055] The data collection and storage module is used to connect the collection port to the customer energy data management system, collect and establish a historical energy consumption database, and obtain energy consumption data at preset time intervals;

[0056] The model training module is used to pre-process the energy consumption data and initialize the BP neural network model parameters based on historical data samples;

[0057] The model training module is used to input the preprocessed data into the BP neural network and train the BP neural network, optimize the model parameters by minimizing the training error of the samples, and obtain a BP neural network model that meets the preset conditions;

[0058] The abnormality judgment module is used to apply the trained BP neural network model to predict the newly incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, judge whether it is an abnormal value according to the preset threshold, and provide correction suggestions and dynamically adjust the abnormality judgment threshold.

[0059] In a third aspect, the present invention provides 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 for online evaluation of energy consumption data accuracy are implemented.

[0060] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a method for online evaluation of energy consumption data accuracy are implemented.

[0061] Compared with the prior art, the beneficial effect of the present invention is that this patent aims to provide users with a highly customized and precise information accuracy assessment solution; it can not only cleverly use the enterprise's massive historical information data as a cornerstone to more accurately judge the abnormal situation of its energy consumption monitoring data, but also support timely updating of the abnormal judgment threshold according to the development status of the enterprise, thereby ensuring the continued effectiveness and applicability of the method; the system can accurately test various types of energy consumption data, support the energy big data center to better realize multi-source and multi-field data fusion, realize efficient integration, fusion and management of energy data, and help build an efficient and technologically advanced energy big data center, provide support for data sharing and deep mining of value mining, provide comprehensive analysis support for the energy industry, and help upstream and downstream enterprises quickly build data decision-making analysis capabilities; at the same time, it is helpful to serve the government's scientific decision-making and serve the energy statistics supervision of power grid enterprises, so as to facilitate the government and power grid enterprises to manage enterprises whose energy consumption does not meet the requirements of national policies in a targeted manner, and help the implementation of the "dual carbon" policy; more advanced is that this patent not only stays at the level of abnormal warning, it also further provides customers with modification suggestions for abnormal values; these suggestions are based on deep learning and understanding of historical data, aiming to help enterprise users more effectively correct data errors and improve the overall quality of data. In this way, the company's data quality management process can run more efficiently and smoothly, reducing potential losses caused by data errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0063] Figure 1 A method flow chart of an online evaluation method and system for energy consumption data accuracy provided by an embodiment of the present invention;

[0064] Figure 2 An internal structural diagram of a computer device of an online energy consumption data accuracy evaluation method and system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0067] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0068] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present invention, provides an online evaluation method for accuracy of energy consumption data, comprising:

[0069] This application provides a method that can effectively solve the above-mentioned problems. Next, we will combine multiple embodiments to explain in detail how to implement the online evaluation method of energy consumption data accuracy.

[0070] Figure 1 A method flow chart of an online evaluation method and system for energy consumption data accuracy is shown, including:

[0071] S1: The collection port is connected to the customer's energy data management system to collect and establish a historical energy consumption database, and obtain energy consumption data at preset time intervals;

[0072] Furthermore, the historical energy consumption database is collected and established, including:

[0073] Establish an interface with the customer's energy data management system to obtain and store historical energy consumption data.

[0074] Historical energy consumption data include electricity consumption, water consumption, coal consumption, natural gas consumption, and oil consumption;

[0075] Update energy consumption data from the customer energy data management system to the historical energy consumption database based on preset time intervals.

[0076] S2: Preprocess the energy consumption data and initialize the BP neural network model parameters based on historical data samples;

[0077] Furthermore, the obtained data is preprocessed including:

[0078] The collected energy consumption data is normalized, and the normalization formula is as follows:

[0079]

[0080] in, represents the normalized data, x j (i) represents the original data, max(x j ) and min(x j ) represent the minimum and maximum values ​​in the data respectively;

[0081] The normalized data is divided into training set and test set according to the set ratio.

[0082] S3: input the preprocessed data into the BP neural network, and train the BP neural network, optimize the model parameters by minimizing the training error of the samples, and obtain a BP neural network model that meets the preset conditions;

[0083] Furthermore, the training of the BP neural network includes:

[0084] Initialize the learning rate, batch size, number of iterations, number of hidden layers and number of nodes of the BP neural network;

[0085] Use the rand function to initialize all connection weights and thresholds so that w,θ∈(0,1); where w represents the connection weight and θ represents the threshold;

[0086] The hidden layer uses the S-type tangent function tansig as the transfer function, that is,

[0087]

[0088] Where x represents the input signal;

[0089] The output layer uses logsig as the transfer function, that is,

[0090]

[0091] The trainlm algorithm is used as the training function;

[0092] The optimization goal is to minimize the training error of the sample, where the training error calculation formula is as follows:

[0093]

[0094] Among them, y represents the actual value, represents the predicted value;

[0095] The parameters are optimized by gradient descent method, and the parameter update formula is as follows:

[0096]

[0097] Among them, w(t) represents the current weight, η represents the learning rate, represents the gradient of the training error.

[0098] S4: Use the trained BP neural network model to predict the newly incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, determine whether it is an abnormal value based on the preset threshold, and provide correction suggestions and dynamically adjust the abnormal judgment threshold.

[0099] Further, judging whether it is an outlier includes:

[0100] Apply the denormalization formula to restore the normalized output result. The calculation formula is as follows:

[0101] x=x′·(x max -x min )+x min

[0102] Among them, x′ represents the normalized data;

[0103] Calculate the absolute error between the predicted value and the actual value, and calculate the root mean square error. The calculation formula is as follows:

[0104]

[0105] Among them, y i represents the ith actual value, represents the i-th predicted value, n represents the number of samples, and RMSE represents the root mean square error;

[0106] Set the outlier tolerance P, and the calculation formula is as follows:

[0107]

[0108] Among them, P represents the tolerance of outliers;

[0109] Determine whether it exceeds the preset threshold. If it exceeds the preset threshold, the data point is judged to be an outlier, otherwise it is not.

[0110] Furthermore, correction suggestions and data quality assessment reports are provided, including:

[0111] When an outlier is detected, the system sends a warning message to the client and provides a predicted value;

[0112] Regularly generate key data quality reports for each system, analyze and display data quality fluctuations and rule proportions.

[0113] Furthermore, the abnormality judgment threshold is dynamically adjusted, including:

[0114] Adjust the setting value of outlier tolerance P;

[0115] Providing data correction suggestions based on deep learning of historical data, including:

[0116] Based on the learning results of historical data, corresponding numerical modifications are made according to the detected abnormal values.

[0117] Furthermore, this embodiment also provides an online evaluation system for energy consumption data accuracy, including:

[0118] Data acquisition and storage module, model initialization module, model training module and abnormality judgment module;

[0119] The data collection and storage module is used to connect the collection port to the customer's energy data management system, collect and establish a historical energy consumption database, and obtain energy consumption data at preset time intervals;

[0120] The model training module is used to pre-process the energy consumption data and initialize the BP neural network model parameters based on historical data samples;

[0121] The model training module is used to input the preprocessed data into the BP neural network and train the BP neural network, optimize the model parameters by minimizing the training error of the samples, and obtain a BP neural network model that meets the preset conditions;

[0122] The anomaly judgment module is used to apply the trained BP neural network model to predict the newly incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, and determine whether it is an anomaly based on the preset threshold. It also provides correction suggestions and dynamically adjusts the anomaly judgment threshold.

[0123] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, 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 communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an online evaluation method for the accuracy of energy consumption data is implemented. The display screen of the computer device 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 covered on the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse, etc.

[0124] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which implements the following steps when executed by a processor: the collection port is connected to a customer energy data management system, collects and establishes a historical energy consumption database, and obtains energy consumption data at preset time intervals;

[0125] Preprocessing the energy consumption data and initializing BP neural network model parameters based on historical data samples;

[0126] The preprocessed data is input into the BP neural network, and the BP neural network is trained. The model parameters are optimized by minimizing the training error of the samples to obtain a BP neural network model that meets the preset conditions.

[0127] The trained BP neural network model is used to predict the newly-incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, and determine whether it is an abnormal value based on the preset threshold. At the same time, correction suggestions are provided and the abnormal judgment threshold is dynamically adjusted.

[0128] Example 2, reference Figure 1 - Figure 2 , which is the second embodiment of the present invention, and this embodiment provides an online evaluation method for the accuracy of energy consumption data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0129] In order to evaluate the accuracy of the energy consumption data of a manufacturing enterprise in Guizhou, the hourly energy consumption historical data of a certain enterprise from 1:00 on January 1, 2022 to 24:00 on September 30, 2024 were extracted from the system. The fields included are time point and energy consumption (including electricity consumption, water consumption, coal consumption, natural gas consumption, diesel and gasoline consumption, etc., which can be adjusted according to the specific energy consumption type).

[0130] Taking the energy consumption data of the enterprise at 1:00 on January 1, 2022 as an example, the data structure is shown as follows:

[0131] Table 1: Daily energy consumption data of a certain enterprise at 1:00 on January 1, 2022

[0132]

[0133] The hourly energy consumption historical data of a certain enterprise from 1:00 on January 1, 2022 to 24:00 on September 30, 2024 is shown in the following table:

[0134] Table 2: Data anomalies of a certain enterprise from 1:00 on January 1, 2022 to 24:00 on September 30, 2024

[0135]

[0136] The categorical variables were time-point encoded, the numerical data were normalized, and the training set and test set were divided into 8:2 ratios.

[0137] Table 3: Processed data

[0138] Time Water consumption Power Consumption Coal consumption Natural gas consumption Oil consumption 0.08 0.72 0.43 0.58 0.23 0.74

[0139] Next, build a BP neural network for model training.

[0140] First, the initialization parameters are set, the learning rate η is set to 0.003, the epochs is set to 5000, and the batch is set to 300. Next, the number of hidden layers and hidden nodes is determined, the neuron transfer function and transmission function of the hidden layer are set to tansig, the training function uses trainlm, and the loss function is set to mean square error. The training errors of the network structures of 6*64*5, 6*64*64*5, 6*64*64*64*5 and 6*64*64*64*64*5 are compared. The experiment shows that when the network structure is 6*64*64*64*5, the training error is the smallest. The grid search method is then used to determine the number of hidden layer nodes. When the network structure is 6*64*128*64*5, the training error is further reduced.

[0141] Next, set the function and compare the activation functions such as tansig, logsig, ReLU, linear, tanh, sigmoid, etc. When the activation function of each layer is set to tansig, tansig, tansig, logsig, the training error is the smallest. Then compare the optimization functions GDS, MGDS, ADAM, and trainlm. The trainlm optimization function converges the fastest and has the best effect.

[0142] The rand function is used to initialize the connection weights of the network, and the data is input into the network for training. Since the data output by the network is a normalized value, it is restored to obtain the predicted data.

[0143] Calculate the root mean square error between the predicted data and the actual data, and the results are as follows:

[0144] Table 4: Root mean square error of each variable

[0145] variable Water consumption Power Consumption Coal consumption Natural gas consumption Oil consumption Root mean square error 2.433 3.324 2.234 3.75 3.40

[0146] Set the tolerance value, calculate Recall and FAR. When the tolerance value is 3.25, the effect is best. The prediction effect of the model in the test set is shown in the following table:

[0147] Table 5: Recall and FAR data of each variable

[0148] variable Water consumption / % Power consumption / % Coal consumption / % Natural gas consumption / % Oil consumption / % Recall 96.4 97.5 94.9 95.7 98.3 FAR 0.7 1.2 0.9 2.3 2.1

[0149] Abnormal values ​​are basically marked out and the system will send a warning to the client, and provide the client with suggestions for using predicted values ​​instead of uploaded values. It also provides the results of the data accuracy assessment and can issue a data quality assessment report.

[0150] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0151] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0152] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0155] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0156] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An online evaluation method for energy consumption data accuracy, characterized by: Including, the collection port is connected to the customer energy data management system, collecting and establishing a historical energy consumption database, and obtaining energy consumption data at preset time intervals; Preprocessing the energy consumption data and initializing BP neural network model parameters based on historical data samples; The preprocessed data is input into the BP neural network, and the BP neural network is trained. The model parameters are optimized by minimizing the training error of the samples to obtain a BP neural network model that meets the preset conditions. The trained BP neural network model is used to predict the newly-incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, and determine whether it is an abnormal value based on the preset threshold. At the same time, correction suggestions are provided and the abnormal judgment threshold is dynamically adjusted.

2. The method for online evaluation of energy consumption data accuracy according to claim 1, characterized in that: The collection and establishment of a historical energy consumption database includes: Establish an interface with the customer's energy data management system to obtain and store historical energy consumption data. The historical energy consumption data includes electricity consumption, water consumption, coal consumption, natural gas consumption and oil consumption; Update energy consumption data from the customer energy data management system to the historical energy consumption database based on preset time intervals.

3. The method for online evaluation of energy consumption data accuracy according to claim 2, characterized in that: The preprocessing of the obtained data includes: The collected energy consumption data is normalized, and the normalization formula is as follows: in, represents the normalized data, x j (i) represents the original data, max(x j ) and min(x j ) represent the minimum and maximum values ​​in the data respectively; The normalized data is divided into training set and test set according to the set ratio.

4. The method for online evaluation of energy consumption data accuracy according to claim 3, characterized in that: The training of the BP neural network includes: Initialize the learning rate, batch size, number of iterations, number of hidden layers and number of nodes of the BP neural network; Use the rand function to initialize all connection weights and thresholds so that w,θ∈(0,1); where w represents the connection weight and θ represents the threshold; The hidden layer uses the S-type tangent function tansig as the transfer function, that is, Where x represents the input signal; The output layer uses logsig as the transfer function, that is, The trainlm algorithm is used as the training function; The optimization goal is to minimize the training error of the sample, where the training error calculation formula is as follows: Among them, y represents the actual value, represents the predicted value; The parameters are optimized by gradient descent method, and the parameter update formula is as follows: Among them, w(t) represents the current weight, η represents the learning rate, represents the gradient of the training error.

5. The method for online evaluation of energy consumption data accuracy according to claim 4, characterized in that: The determination of whether it is an abnormal value includes: Apply the denormalization formula to restore the normalized output result. The calculation formula is as follows: x=x′·(x max -x min )+x min Among them, x′ represents the normalized data; Calculate the absolute error between the predicted value and the actual value, and calculate the root mean square error. The calculation formula is as follows: Among them, y i represents the ith actual value, represents the i-th predicted value, n represents the number of samples, and RMSE represents the root mean square error; Set the outlier tolerance P, and the calculation formula is as follows: Among them, P represents the tolerance of outliers; Determine whether it exceeds the preset threshold. If it exceeds the preset threshold, the data point is judged to be an outlier, otherwise it is not.

6. The method for online evaluation of energy consumption data accuracy according to claim 5, characterized in that: The provision of correction suggestions and data quality assessment reports includes: When an outlier is detected, the system sends a warning message to the client and provides a predicted value; Regularly generate key data quality reports for each system, analyze and display data quality fluctuations and rule proportions.

7. The method for online evaluation of energy consumption data accuracy according to claim 6, characterized in that: The dynamic adjustment of the abnormality judgment threshold includes: Adjust the setting value of outlier tolerance P; The data correction suggestions provided based on deep learning of historical data include: Based on the learning results of historical data, corresponding numerical modifications are made according to the detected abnormal values.

8. An online evaluation system for energy consumption data accuracy, based on the online evaluation method for energy consumption data accuracy according to any one of claims 1 to 7, characterized in that: Including data acquisition and storage module, model initialization module, model training module and abnormality judgment module; The data collection and storage module is used to connect the collection port to the customer energy data management system, collect and establish a historical energy consumption database, and obtain energy consumption data at preset time intervals; The model training module is used to pre-process the energy consumption data and initialize the BP neural network model parameters based on historical data samples; The model training module is used to input the preprocessed data into the BP neural network and train the BP neural network, optimize the model parameters by minimizing the training error of the samples, and obtain a BP neural network model that meets the preset conditions; The abnormality judgment module is used to apply the trained BP neural network model to predict the newly incoming energy consumption data, calculate the absolute error between the predicted value and the actual value, judge whether it is an abnormal value according to the preset threshold, and provide correction suggestions and dynamically adjust the abnormality judgment threshold.

9. 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 for online evaluation of energy consumption data accuracy according to any one of claims 1 to 7 are implemented.

10. 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 for online evaluation of energy consumption data accuracy according to any one of claims 1 to 7 are implemented.

Images