Electric power new capital construction assessment method and system based on big data analysis
Through big data analysis and deep neural network model, combined with geographic information and time series data, the problem of incomplete and accurate evaluation of new power infrastructure projects has been solved, and more accurate and scientific evaluation results have been achieved, providing an important reference for decision-making.
Patent Information
- Application Number
- CN202411352826.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2025-01-03
AI Technical Summary
The evaluation of new power infrastructure projects in the existing technology is not comprehensive and accurate enough, and mainly relies on traditional qualitative analysis methods and a small number of quantitative indicators to evaluate, and cannot fully and accurately reflect the actual situation of the project.
Using a method based on big data analysis, the geographic information data and project index data are obtained through the power big data platform, combined with time series data, spatial distribution characteristics and predict changes, and comprehensive evaluation is used for data mining and deep neural network models to output power. Evaluation results of new infrastructure projects.
A comprehensive, in-depth and dynamic assessment of new power infrastructure projects has been achieved, which improves the accuracy and scientificity of the evaluation results, provides a more scientific basis for decision-making, and reduces interference from subjective factors.
Smart Images
Figure CN119250626A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of power big data analysis, and specifically relates to a new power infrastructure evaluation method and system based on big data analysis. Background Art
[0002] With the transformation of the global energy structure and the rapid development of smart grids, the construction scale and complexity of new power infrastructure projects, as an important cornerstone to support the safe, efficient and green operation of future power systems, are increasing. These projects cover a wide range of fields, from smart grids, UHV transmission, clean energy access to energy storage facilities, and are of great significance for promoting the optimization of energy structure and improving the level of smart grids.
[0003] In the existing technology, the evaluation of new power infrastructure projects mainly relies on traditional qualitative analysis methods and a small amount of quantitative indicator evaluation, which are often not comprehensive and accurate enough for project evaluation. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for evaluating new power infrastructure based on big data analysis, so as to solve the problem that the evaluation of new power infrastructure projects in the prior art is not comprehensive and accurate enough.
[0005] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for evaluating new power infrastructure based on big data analysis, comprising the following steps: Based on the power big data platform, obtain the geographic information data and project indicator data of each power new infrastructure project, as well as the time series data corresponding to the project indicators of each power new infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data; Determine the spatial distribution characteristics of new power infrastructure projects based on project indicator data and geographic information data; Determine the predicted change trend of each project indicator based on time series data; Mining the indicator data of each project to obtain the significant association rules between the indicator data of each project; The spatial distribution characteristics, the predicted change trend and the significant association rules are input into a pre-trained comprehensive evaluation model for new electric power infrastructure, and the comprehensive evaluation model for new electric power infrastructure outputs evaluation results of new electric power infrastructure projects.
[0006] Furthermore, based on project indicator data and geographic information data, the spatial distribution characteristics of new power infrastructure projects are determined, including: Integrate project indicator data and geographic information data so that each new power infrastructure project has a corresponding geographical location; Based on the geographical location of each new power infrastructure project, determine the spatial weight value between each new power infrastructure project; The spatial weight matrix is constructed according to the spatial weight value; The Moran's I index of each new power infrastructure project is calculated based on the spatial weight matrix; Based on Moran's I index, the spatial correlation between the indicators of various projects in the current power new infrastructure projects is determined; Based on spatial correlation, spatially concentrated areas and spatially dispersed areas are determined as the spatial distribution characteristics of new power infrastructure projects.
[0007] Furthermore, the predicted change trend of each project indicator is determined based on the time series data, including: The time series data is analyzed using the ARIMA model to obtain the trend of each project indicator over time; Based on the changing trend of each project indicator over time, the predicted changing trend of each project indicator is obtained.
[0008] Furthermore, the indicator data of each project is mined to obtain significant association rules between the indicator data of each project, including: The Apriori algorithm is used to mine the project indicator data of the new power infrastructure projects, obtain the association rules between the project indicator data, and screen out significant association rules through the preset threshold standards.
[0009] Furthermore, the spatial distribution characteristics, the predicted change trend and the significant association rules are input into a pre-trained comprehensive evaluation model for new power infrastructure, and the comprehensive evaluation model for new power infrastructure outputs the evaluation results of the new power infrastructure project, wherein: The comprehensive evaluation model of new power infrastructure is constructed and trained as follows: Obtain geographic information data corresponding to new power infrastructure projects, as well as time series data of indicators of each project of new power infrastructure projects, as well as the results of mining association rules between indicators of each project, and construct a training data set for the comprehensive evaluation model of new power infrastructure; A basic model for building a comprehensive evaluation model for new power infrastructure based on deep neural networks; The basic model is trained using a training data set to obtain a trained comprehensive evaluation model for new power infrastructure.
[0010] Furthermore, the basic model includes a multimodal input layer, a processing layer, a fusion layer, an evaluation layer and an output layer; The multimodal input layer includes multiple input layers, which are respectively used to receive geographic information data, time series data and association rule mining results; The processing layer includes a convolutional neural network, a recurrent neural network and a fully connected layer, wherein the convolutional neural network is used to process geographic information data, the recurrent neural network is used to process time series data, and the fully connected layer is used to process association rule mining results; The fusion layer is used to fuse the outputs of the convolutional neural network, the recurrent neural network and the fully connected layer by splicing to obtain fusion features; The evaluation layer is used to learn from the fusion features to obtain an evaluation result.
[0011] Furthermore, based on the power big data platform, the geographic information data and project indicator data of each power new infrastructure project, as well as the time series data corresponding to the project indicators of each power new infrastructure project, are obtained, including: Receive data requests and authenticate; After the identity verification is passed, the required data in the data request is determined; the data source is located in the power big data platform according to the required data, and the required data is extracted from the data source; The extracted required data is encrypted and returned.
[0012] In a second aspect, the present invention provides a device for evaluating new power infrastructure based on big data analysis, comprising the following steps: The data acquisition module is used to obtain the geographic information data and project indicator data of each new power infrastructure project based on the power big data platform, as well as the time series data corresponding to the project indicators of each new power infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data; The first determination module is used to determine the spatial distribution characteristics of the new power infrastructure project based on the project indicator data and geographic information data; The second determination module is used to determine the predicted change trend of each project indicator based on the time series data; The data mining module is used to mine the indicator data of each project and obtain the significant association rules between the indicator data of each project; An evaluation module is used to input the spatial distribution characteristics, the predicted change trend and the significant association rules into a pre-trained comprehensive evaluation model for new power infrastructure, and the comprehensive evaluation model for new power infrastructure outputs the evaluation results of the new power infrastructure project.
[0013] According to a third aspect of the present invention, there is provided an electronic device comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the above-mentioned new power infrastructure assessment method based on big data analysis.
[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for evaluating new power infrastructure based on big data analysis as described above is implemented.
[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a method for evaluating new power infrastructure based on big data analysis. Through the power big data platform, the geographic information data and project indicator data (including construction cost, electricity consumption, environmental protection data, etc.) of each new power infrastructure project, as well as the time series data of these indicators, are obtained, and the richness and real-time nature of big data are fully utilized to provide comprehensive and multi-dimensional data support for the evaluation. Based on project indicator data and geographic information data, this scheme can determine the spatial distribution characteristics of new power infrastructure projects, effectively evaluate the rationality of project layout, the matching degree of regional development, and the efficiency of resource utilization, and provide a scientific basis for project planning and decision-making. Through the analysis of time series data, this scheme can predict the future trend of indicators of each project, identify potential risks and opportunities of the project in advance, and provide forward-looking guidance for project management and decision-making. Through data mining, this scheme discovers significant association rules between the indicator data of each project, can reveal the interaction and influence mechanism between the internal elements of the project, and provide support for the comprehensive evaluation of the comprehensive performance of the project. By inputting the spatial distribution characteristics, predicted change trends and significant association rules into the pre-trained comprehensive evaluation model of new power infrastructure, it is possible to output the comprehensive evaluation results of new power infrastructure projects, overcome the one-sidedness and subjectivity of traditional evaluation methods, and improve the accuracy and scientificity of the evaluation results. In summary, the method of the present invention can make full use of the data resources of the power big data platform, combine data mining and machine learning, and achieve a comprehensive, in-depth and dynamic evaluation of new power infrastructure projects, more accurately grasp the actual situation and development trend of the project, and provide decision makers with a more scientific and reasonable decision-making basis. The new power infrastructure evaluation device, electronic device and computer-readable storage medium based on big data analysis provided by the present invention also solve the problems raised in the background technology section.
[0016] This application comprehensively evaluates the current status and development trend of new power infrastructure projects based on the analysis results of spatial correlation, temporal change trends and correlation rules between indicators. Its comprehensive and data-driven characteristics enable it to more comprehensively and accurately evaluate the benefits and impacts of new power infrastructure projects, providing important reference for relevant decision-making; This application reduces the interference of subjective factors through data analysis and model calculation, and the evaluation results are more objective and scientific. The weights and importance of each analysis result are reasonably set, and the weights can be adjusted according to actual conditions to make the evaluation results more in line with actual needs; This application constructs a deep learning model for comprehensive evaluation of new power infrastructure projects, fully utilizing the information of multimodal data to improve the accuracy and comprehensiveness of the evaluation of new power infrastructure projects. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A schematic diagram of a flow chart of a method for evaluating new power infrastructure based on big data analysis according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a device for evaluating new power infrastructure based on big data analysis according to an embodiment of the present invention; Figure 3 The present invention is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0018] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.
[0019] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.
[0020] Glossary: ARIMA model, Autoregressive Integrated Moving Average Model; Geographic Information System (GIS) Global Positioning System (GPS); Moran's I index, Moran's index; The QQ plot (Quantile-Quantile Plot) is a graphical tool used to compare the similarity of two probability distributions; LB test, Ljung-Box test; Apriori algorithm is an association rule mining algorithm; CNN, Convolutional Neural Networks (CNN); RNN, (Recurrent Neural Network, RNN).
[0021] Example 1 like Figure 1 As shown, a method for evaluating new power infrastructure based on big data analysis includes the following steps: S10. Based on the electric power big data platform, obtain the geographic information data and project indicator data of each new electric power infrastructure project, as well as the time series data corresponding to the project indicators of each new electric power infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data.
[0022] Specifically, in step S10, based on the power big data platform, the geographic information data and project indicator data of each power new infrastructure project, as well as the time series data corresponding to the project indicators of each power new infrastructure project are obtained, including: S101, the data requesting party sends a data request to the electric power big data platform, and the electric power big data platform receives the data request and authenticates the data requesting party; S102, after identity authentication is passed, determining the required time series data in the data request; locating the data source in the power big data platform according to the required time series data, and extracting the required time series data from the data source; S103: Encrypt the extracted time series data and return it to the data requester.
[0023] Optionally, geographic information data and project indicator data of each new power infrastructure project, as well as time series data corresponding to the project indicators of each new power infrastructure project, can be obtained from multiple channels such as power companies, government departments, industry reports, and research institutions. Geographic information data of each new power infrastructure project can also be obtained from GIS data providers, for example, using open map data sources such as OpenStreetMap to obtain geographic information data, and can also be combined with GPS positioning and satellite remote sensing technology to obtain geographic information data.
[0024] S20. Determine the spatial distribution characteristics of new power infrastructure projects based on project indicator data and geographic information data.
[0025] Specifically, step S20 includes the following: S201. Integrate project indicator data and geographic information data so that each new power infrastructure project has a corresponding geographical location; S202, determining the spatial weight values between the new power infrastructure projects based on the geographical locations of the new power infrastructure projects; The specific calculation method is as follows:
[0026] in, is the spatial weight value between power new infrastructure project i and power new infrastructure project j, is the distance between new power infrastructure project i and new power infrastructure project j, and p is the power exponent.
[0027] S203, constructing a spatial weight matrix according to the spatial weight value; Specifically, the spatial weight matrix is expressed as follows:
[0028] S204. Calculate the Moran's I index of each new power infrastructure project based on the spatial weight matrix; Specifically, the Moran's I index is calculated as follows: Calculate the spatial lag value of the new power infrastructure project:
[0029] in, y i ∗ New power infrastructure projects i The spatial lag value of w ij is the spatial weight matrix W Elements in y j New power infrastructure projects j The project indicator value; n The total number of items.
[0030] Compute the mean of the spatially lagged values:
[0031] in, is the mean of the spatial lag values.
[0032] Calculate the Moran's I statistic:
[0033] in, I is the Moran's I index; n is the total number of new power infrastructure projects; w ij is the spatial weight matrix W Elements in y i and y j They are respectively the new power infrastructure projects i New power infrastructure projectsj The project indicator value; is the mean value of all project indicators, = .
[0034] The value range of Moran's I index is [−1,1]. I When it is close to 1, it means that the project index values are strongly positively correlated in space (i.e., spatial aggregation); when I When it is close to -1, it indicates a strong negative correlation (i.e., spatial dispersion); when I When it is close to 0, it means there is no obvious spatial autocorrelation.
[0035] S205. Based on Moran's I index, determine the spatial correlation between the indicators of various projects in the current power new infrastructure projects; Step S205 is specifically as follows: The data obtained in step S10 is used as the original data set, and the project index values in the original data set are randomly permuted multiple times to destroy the original spatial autocorrelation; in each permutation, the spatial weight matrix is maintained W The project index values are randomly redistributed to each new power infrastructure project. For each permuted data set, the Moran's I index is calculated using the same Moran's I calculation formula as the original data set to generate a distribution of Moran's I index; Using the original dataset and a known spatial weights matrix W , calculate the Moran's I index; compare the Moran's I index calculated from the original data set with the Moran's I distribution generated by the Monte Carlo simulation, and calculate the position of the original Moran's I index in the simulated distribution; Based on the comparison results, determine whether the spatial autocorrelation in the original data set is significant. If the original Moran's I index is at the extreme of the simulated distribution (for example, much higher or much lower than most simulated values), the spatial autocorrelation is considered significant; According to the value of Moran's I index and the results of significance test, the spatial correlation between various indicators of power new infrastructure projects is analyzed. If the Moran's I index is positive and significant, it indicates that there is spatial aggregation between project indicators; if it is negative and significant, it indicates that there is spatial dispersion; if it is not significant, it may indicate that the spatial autocorrelation is weak or does not exist.
[0036] S206. Based on spatial correlation, determine spatially concentrated areas and spatially dispersed areas as the spatial distribution characteristics of new power infrastructure projects.
[0037] Specifically, based on the results of Moran's I index, the spatially concentrated areas and spatially dispersed areas of new power infrastructure projects are identified, thereby obtaining the spatial distribution characteristics of new power infrastructure projects.
[0038] S30. Determine the predicted change trend of each project indicator based on the time series data.
[0039] Specifically, step S30 includes the following: The time series data is analyzed using the ARIMA model to obtain the trend of each project indicator changing over time; based on the trend of each project indicator changing over time, the predicted change trend of each project indicator is obtained.
[0040] Specifically, the ARIMA model training method is as follows: Preprocess the time series data, including processing missing values, stationarity tests, and difference operations, to ensure that the data meets the requirements of the ARIMA model; use the ARIMA model to fit the time series data to determine the order of the ARIMA model ( p、 d, q ), the ARIMA model is expressed as: ; in, ϕ p (B) is an autoregressive polynomial, θ q (B) is the moving average polynomial, X t For time series data, Z t is a white noise sequence; p represents the order of the autoregressive term, d represents the difference order, q represents the order of the moving average term; B is the backshift operator.
[0041] In an optional embodiment, the fitted ARIMA model is also diagnosed to check whether the residual sequence meets the characteristics of the white noise sequence to ensure the effectiveness of the model, as follows: Analyze the residual sequence of the ARIMA model, including using autocorrelation plots and partial autocorrelation plots to check the autocorrelation of the residual sequence; use QQ plots to check whether the residual sequence conforms to the normal distribution; use the mean and variance plots of the residual sequence to check whether the mean and variance of the residual sequence remain stable; then determine the lag order in the LB test, usually selecting a lag order within a certain range for the test, calculate the LB test statistic Q, and compare it with the critical value to determine whether the residual sequence conforms to the characteristics of the white noise sequence;
[0042] Where m is the sample size, h is the lag order, is the autocorrelation coefficient of the kth sample residual sequence; According to the test results of the residual sequence, the fitting effect of the ARIMA model is evaluated. If the residual sequence shows autocorrelation or does not conform to the normal distribution, it means that the fitting effect of the ARIMA model is poor and further adjustment is needed. Adjustments include increasing the order of the ARIMA model, trying different seasonal adjustments, considering the introduction of external factors, etc. The purpose of adjusting the model is to make the residual sequence closer to the white noise sequence and improve the accuracy and reliability of the model.
[0043] S40, mining the indicator data of each project to obtain significant association rules between the indicator data of each project.
[0044] Specifically, step S40 includes: using the Apriori algorithm to mine the project indicator data of the new power infrastructure project, obtaining the association rules between the project indicator data, and screening out significant association rules through a preset threshold standard.
[0045] Specifically, the project indicator data of the new power infrastructure projects are converted into a transaction data set format suitable for the Apriori algorithm, and the Apriori algorithm is used to mine the association rules between different project indicator data. The support and confidence thresholds are set to screen out significant association rules, such as the association rules between construction cost and electricity consumption.
[0046] S50, inputting the spatial distribution characteristics, the predicted change trend and the significant association rules into a pre-trained comprehensive evaluation model for new electric power infrastructure, and the comprehensive evaluation model for new electric power infrastructure outputs the evaluation results of the new electric power infrastructure projects.
[0047] Specifically, in step S50, the comprehensive evaluation model for new power infrastructure is constructed and trained in the following manner: S501, obtaining GIS spatial data corresponding to the new power infrastructure project, as well as time series data of indicators of each project of the new power infrastructure project, and the results of mining association rules between the indicators of each project, and constructing a training data set for the comprehensive evaluation model of the new power infrastructure; S502. Constructing a basic model for comprehensive evaluation of new power infrastructure based on deep neural network; Wherein, the basic model includes a multimodal input layer, a processing layer, a fusion layer, an evaluation layer and an output layer; The multimodal input layer includes multiple input layers, which are respectively used to receive geographic information data, time series data Xtime and association rule mining results X rules ; Geographic information data can be GIS spatial data X gis ; The processing layer includes a convolutional neural network (CNN), a recurrent neural network (RNN) and a fully connected layer (FullyConnected Layer), wherein the convolutional neural network is used to process GIS spatial data, the recurrent neural network is used to process time series data, and the fully connected layer is used to process association rule mining results; the details are as follows: H gis = σ CNN ( W 1* X gis + b 1) H time = σ RNN ( W 2* X time + U 2* H time−1 + b 2) H rules = σ rules ( W 3* X rules + b 3) in, X gis It is the input of GIS spatial data; H gis It is the feature representation of GIS spatial data after CNN processing; σ CNN is the activation function of CNN; W 1 is the input weight of CNN, b 1 is the bias term of CNN. X time is the current input of the time series data; W 2 is the input weight of RNN, U 2 is the recurrent weight of RNN, b 2 is the bias term of RNN, * represents matrix multiplication, σ RNN is the activation function of RNN; H time−1is the output state of RNN at the previous moment; H time It is the feature representation of time series data after RNN processing. W 3 is the input weight of the fully connected layer, b 3 is the bias term of the fully connected layer; σ rules is the activation function of the fully connected layer; X rules It is the input of association rule mining results; H rules It is the feature representation of association rules after being processed by the fully connected layer.
[0048] The fusion layer is used to fuse the outputs of the convolutional neural network, the recurrent neural network and the fully connected layer by splicing to obtain fusion features; specifically, it is expressed as follows: H fusion = σ fusion ( W 4*[ H GIS ; H time ; H rules ]+ b 4) in, W 4 is the weight of the fusion layer, σ fusion is the activation function of the fusion layer; b 4 is the bias term of the fusion layer; H fusio It is the feature representation after fusion layer processing.
[0049] The evaluation layer is used to learn from the fusion features to obtain evaluation results. The specific representation is as follows: Y = σ output ( W output * H fusion + b output ) in, W output is the weight of the evaluation layer, σ output is the activation function of the evaluation layer, b output is the bias term of the evaluation layer; Y is the final output of the network.
[0050] S503: Use a training data set to train the basic model to obtain a trained comprehensive evaluation model for new power infrastructure.
[0051] Specifically, the training method is as follows: (1) Initialize the model’s weights and biases; (2) Calculate the model’s predicted output via forward propagation; (3) Use the loss function to measure the gap between the model prediction output and the true label;
[0052] Where N is the number of samples, is the true label, is the model prediction output; (4) Calculate the gradient of the loss function with respect to the model parameters through back propagation;
[0053] in, are model parameters; (5) Use the gradient descent algorithm to update the model parameters to reduce the loss function;
[0054] in, is the learning rate; To update the model parameters.
[0055] (6) Repeat steps (2)-(5): repeatedly perform forward propagation, calculate loss, backpropagation, and parameter update until the model converges or reaches the stopping condition.
[0056] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiment, the present invention also provides a new power infrastructure evaluation device based on big data analysis, comprising the following steps: The data acquisition module is used to obtain the geographic information data and project indicator data of each new power infrastructure project based on the power big data platform, as well as the time series data corresponding to the project indicators of each new power infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data; The first determination module is used to determine the spatial distribution characteristics of the new power infrastructure project based on the project indicator data and geographic information data; The second determination module is used to determine the predicted change trend of each project indicator based on the time series data; The data mining module is used to mine the indicator data of each project and obtain the significant association rules between the indicator data of each project; An evaluation module is used to input the spatial distribution characteristics, the predicted change trend and the significant association rules into a pre-trained comprehensive evaluation model for new power infrastructure, and the comprehensive evaluation model for new power infrastructure outputs the evaluation results of the new power infrastructure project.
[0057] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing the above-mentioned embodiment 1, a method for evaluating new power infrastructure based on big data analysis; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .
[0058] The memory 101 can be used to store a computer program 103. The processor 102 implements the steps of a method for evaluating new power infrastructure based on big data analysis in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.
[0059] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
[0060] At least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.
[0061] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for evaluating new power infrastructure based on big data analysis, and the processor 102 can execute the plurality of instructions to implement: Based on the power big data platform, obtain the geographic information data and project indicator data of each power new infrastructure project, as well as the time series data corresponding to the project indicators of each power new infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data; Determine the spatial distribution characteristics of new power infrastructure projects based on project indicator data and geographic information data; Determine the predicted change trend of each project indicator based on time series data; Mining the indicator data of each project to obtain the significant association rules between the indicator data of each project; The spatial distribution characteristics, the predicted change trend and the significant association rules are input into a pre-trained comprehensive evaluation model for new electric power infrastructure, and the comprehensive evaluation model for new electric power infrastructure outputs evaluation results of new electric power infrastructure projects.
[0062] Example 4 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).
[0063] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take 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.) containing computer-usable program code.
[0064] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.
[0065] 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.
[0066] 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.
[0067] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. 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 can be combined in any one or more embodiments or examples in a suitable manner.
[0068] Finally, 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A method for evaluating new power infrastructure based on big data analysis, characterized in that: The steps include: Based on the power big data platform, obtain the geographic information data and project indicator data of each power new infrastructure project, as well as the time series data corresponding to the project indicators of each power new infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data; Determine the spatial distribution characteristics of new power infrastructure projects based on project indicator data and geographic information data; Determine the predicted change trend of each project indicator based on time series data; Mining the indicator data of each project to obtain the significant association rules between the indicator data of each project; The spatial distribution characteristics, the predicted change trend and the significant association rules are input into a pre-trained comprehensive evaluation model for new electric power infrastructure, and the comprehensive evaluation model for new electric power infrastructure outputs evaluation results of new electric power infrastructure projects.
2. The method for evaluating new power infrastructure based on big data analysis according to claim 1 is characterized in that: Based on project indicator data and geographic information data, the spatial distribution characteristics of new power infrastructure projects are determined, including: Integrate project indicator data and geographic information data so that each new power infrastructure project has a corresponding geographical location; Based on the geographical location of each new power infrastructure project, determine the spatial weight value between each new power infrastructure project; The spatial weight matrix is constructed according to the spatial weight value; The Moran's I index of each new power infrastructure project is calculated based on the spatial weight matrix; Based on Moran's I index, the spatial correlation between the indicators of various projects in the current power new infrastructure projects is determined; Based on spatial correlation, spatially concentrated areas and spatially dispersed areas are determined as the spatial distribution characteristics of new power infrastructure projects.
3. The method for evaluating new power infrastructure based on big data analysis according to claim 1 is characterized in that: Determine the forecast change trend of each project indicator based on time series data, including: The time series data is analyzed using the ARIMA model to obtain the trend of each project indicator over time; Based on the changing trend of each project indicator over time, the predicted changing trend of each project indicator is obtained.
4. The method for evaluating new power infrastructure based on big data analysis according to claim 1 is characterized in that: Mining the indicator data of each project, we can get the significant association rules between the indicator data of each project, including: The Apriori algorithm is used to mine the project indicator data of the new power infrastructure projects, obtain the association rules between the project indicator data, and screen out significant association rules through the preset threshold standards.
5. The method for evaluating new power infrastructure based on big data analysis according to claim 1 is characterized in that: The spatial distribution characteristics, the predicted change trend and the significant association rules are input into a pre-trained comprehensive evaluation model for new power infrastructure, and the comprehensive evaluation model for new power infrastructure outputs the evaluation results of the new power infrastructure project, wherein: The comprehensive evaluation model of new power infrastructure is constructed and trained as follows: Obtain geographic information data corresponding to new power infrastructure projects, as well as time series data of indicators of each project of new power infrastructure projects, as well as the results of mining association rules between indicators of each project, and construct a training data set for the comprehensive evaluation model of new power infrastructure; A basic model for building a comprehensive evaluation model for new power infrastructure based on deep neural networks; The basic model is trained using a training data set to obtain a trained comprehensive evaluation model for new power infrastructure.
6. The method for evaluating new power infrastructure based on big data analysis according to claim 5 is characterized in that: The basic model includes a multimodal input layer, a processing layer, a fusion layer, an evaluation layer and an output layer; The multimodal input layer includes multiple input layers, which are respectively used to receive geographic information data, time series data and association rule mining results; The processing layer includes a convolutional neural network, a recurrent neural network and a fully connected layer, wherein the convolutional neural network is used to process geographic information data, the recurrent neural network is used to process time series data, and the fully connected layer is used to process association rule mining results; The fusion layer is used to fuse the outputs of the convolutional neural network, the recurrent neural network and the fully connected layer by splicing to obtain fusion features; The evaluation layer is used to learn from the fusion features to obtain an evaluation result.
7. The method for evaluating new power infrastructure based on big data analysis according to claim 1 is characterized in that: Based on the power big data platform, the geographic information data and project indicator data of each power new infrastructure project are obtained, as well as the time series data corresponding to the project indicators of each power new infrastructure project, including: Receive data requests and authenticate; After the identity verification is passed, the required data in the data request is determined; the data source is located in the power big data platform according to the required data, and the required data is extracted from the data source; The extracted required data is encrypted and returned.
8. A new power infrastructure evaluation device based on big data analysis, characterized in that: The steps include: The data acquisition module is used to obtain the geographic information data and project indicator data of each new power infrastructure project based on the power big data platform, as well as the time series data corresponding to the project indicators of each new power infrastructure project; among which, the project indicators include construction cost, electricity consumption, and environmental protection data; The first determination module is used to determine the spatial distribution characteristics of the new power infrastructure project based on the project indicator data and geographic information data; The second determination module is used to determine the predicted change trend of each project indicator based on the time series data; The data mining module is used to mine the indicator data of each project and obtain the significant association rules between the indicator data of each project; An evaluation module is used to input the spatial distribution characteristics, the predicted change trend and the significant association rules into a pre-trained comprehensive evaluation model for new power infrastructure, and the comprehensive evaluation model for new power infrastructure outputs the evaluation results of the new power infrastructure project.
9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the new power infrastructure evaluation method based on big data analysis as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, it implements the new power infrastructure evaluation method based on big data analysis as described in any one of claims 1 to 7.