Power grid investment benefit evaluation method and system based on multi-dimensional data

Abstract

The invention discloses a power grid investment benefit evaluation method and system based on multi-dimensional data, and belongs to the technical field of power system investment analysis, and the method comprises the steps: constructing a power grid investment benefit multi-source data pool; based on the data pool, constructing a dynamic benefit evaluation matrix containing economic, reliability, collaboration and robustness vectors; calculating a space-time comprehensive benefit index; generating a visual investment benefit optimization strategy map; and executing closed-loop feedback and model self-updating. According to the method, the real-time data flow is introduced, the power grid topological structure is fused, and the dynamic self-adaptive evaluation model is constructed, so that the problems of static state solidification, single dimension and untight association with the actual operation of the power grid in the existing evaluation method are solved, more accurate, comprehensive and dynamic evaluation on the investment benefit of the power grid can be realized, and the evaluation efficiency is improved. Powerful support is provided for scientific decision-making of a power grid.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system investment analysis, in particular to a power grid investment benefit evaluation method and system based on multi-dimensional data. BACKGROUND

[0002] The investment scale of power grid is huge, and its benefit evaluation is crucial for optimizing resource allocation and guiding scientific decision-making. Existing power grid investment benefit evaluation methods have tried to consider multiple dimensions, but still have some limitations.

[0003] For example, the prior art, such as the invention patent with publication number CN119106969A, provides a power distribution network investment benefit analysis method by constructing an evaluation system of economic return, technical performance, and environmental impact and performing comprehensive scoring, but this method focuses on static evaluation of the investment scheme itself, lacks dynamic tracking and feedback of the actual operation state of the power grid after investment, and its coefficient training relies on sampling verification, which needs to improve real-time performance and comprehensiveness.

[0004] For another example, another prior art, such as the invention patent with publication number CN119294865A, focuses on constructing a data model using the Lagrange multiplier method and convex optimization theory, which has advantages in theoretical optimization, but its model construction relies on pre-set objective functions and constraints, which may not be suitable for the non-convex, non-linear complex relationships widely existing in power grid investment and the adaptability of massive real-time operation data, has high computational complexity, and does not highlight the spatial distribution characteristics of investment benefits in the actual operation topology of the power grid.

[0005] In summary, the existing technologies generally have one or more of the following problems: 1) the evaluation dimension is relatively fixed and cannot fully integrate real-time massive data of power grid operation; 2) the evaluation model is static or pre-set and cannot adapt to the dynamically changing power grid environment; 3) the evaluation results are not closely related to the actual physical topology structure of the power grid, and the spatial benefit analysis is insufficient; 4) there is a lack of a closed-loop feedback and continuous optimization evaluation and decision support process. SUMMARY

[0006] To overcome the deficiencies of the prior art, the present application provides a power grid investment benefit evaluation method and system based on multi-dimensional data, which realizes more accurate, comprehensive, and dynamic evaluation of power grid investment benefits by introducing real-time data flow, integrating power grid topology structure, and constructing a dynamically adaptive evaluation model.

[0007] To achieve the above-mentioned purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides a power grid investment benefit evaluation method based on multi-dimensional data, comprising the following steps: S101: Construct a power grid investment benefit multi-source data pool. Obtain multi-dimensional data related to the investment project online from the power grid information model, dispatching automation system, asset management system, and environmental monitoring platform; the multi-dimensional data at least includes static topology data, real-time operation data, asset state data, and external environment data; the multi-dimensional data is preprocessed by cleaning, aligning, and normalizing to form a standardized multi-source data pool.

[0008] S102: Construct a dynamic benefit evaluation matrix. Based on the multi-source data pool, a dynamically updated benefit evaluation matrix M(t) is constructed: M(t)=[F,G,H,E].

[0009] Wherein, F is an economic vector, the elements of which include unit investment loss reduction benefit, asset life cycle cost change rate, and investment recovery period dynamic prediction value; G is a reliability vector, the elements of which include node power supply reliability improvement degree based on real-time topology and system average power outage frequency change rate; H is a synergy vector, the elements of which include investment contribution to regional power flow balance and improvement to new energy consumption capacity; E is a robustness vector, the elements of which include change of N-1 passing rate of key lines of power grid after investment and quantitative index of system disturbance resistance.

[0010] S103: Calculate the spatio-temporal comprehensive benefit index. The spatio-temporal comprehensive benefit index S(t) of the dynamic benefit evaluation matrix M(t) is calculated by using a weighted aggregation model: S(t)=α·Norm(F)+β·Norm(G)+γ·Norm(H)+δ·Norm(E).

[0011] Wherein, α, β, γ, δ are dynamic weight coefficients determined by analytic hierarchy process and entropy weight method, and α+β+γ+δ=1; Norm() represents normalizing the module of the vector.

[0012] S104: Generate investment benefit optimization strategy atlas. The spatio-temporal comprehensive benefit index S(t) and its dimensional vector results are mapped to the power grid geographical wiring diagram and topology structure diagram to form a visual investment benefit optimization strategy atlas; the atlas is used to identify weak benefit areas, recommend additional investment directions, and show benefit comparison of different investment schemes.

[0013] S105: Perform closed-loop feedback and model self-update. Compare actual operation data with evaluation prediction results to generate feedback deviation; use the feedback deviation to periodically adaptively optimize the dynamic weight coefficients (α, β, γ, δ) and the weighted aggregation model by machine learning algorithm, and update the evaluation model.

[0014] Secondly, the present invention provides a power grid investment benefit assessment system based on multidimensional data for implementing the above method, comprising: The data aggregation and processing module is used to execute step S1, and to build and manage the multi-source data pool of power grid investment benefits.

[0015] The dynamic matrix construction module is used to perform step S2, which constructs and updates the dynamic benefit evaluation matrix M(t) based on the multi-source data pool.

[0016] The comprehensive evaluation and calculation module is used to perform step S3 and calculate the spatiotemporal comprehensive benefit index S(t).

[0017] The visualization decision support module is used to execute step S4, generating and displaying the investment benefit optimization strategy map.

[0018] The adaptive learning optimization module is used to execute step S5, which uses feedback data to self-update the evaluation model.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention introduces real-time operational data streams to construct a dynamically updated evaluation matrix, enabling benefit evaluation to reflect the latest state of the power grid and overcoming the lag of traditional static evaluation. The addition of "synergy" and "robustness" dimensions better aligns with the development needs of modern power grids. All evaluation indicators are closely linked to the actual physical topology and operating mode of the power grid, providing clear spatial orientation for the evaluation results. Through closed-loop feedback mechanisms and machine learning, the assessment model can continuously optimize itself as the power grid develops and data accumulates, thereby improving the accuracy and robustness of the assessment. By generating visualized strategy maps, abstract evaluation data is transformed into intuitive spatial decision-making suggestions, greatly improving the usability of the results and the efficiency of decision-making. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1This is a flowchart of a power grid investment benefit evaluation method based on multidimensional data provided in an embodiment of the present invention.

[0023] Figure 2 This is a schematic diagram illustrating the construction of the dynamic benefit evaluation matrix provided in an embodiment of the present invention.

[0024] Figure 3 This is an example diagram of the investment benefit optimization strategy map provided in the embodiments of the present invention.

[0025] Figure 4 This is a structural block diagram of the power grid investment benefit evaluation system based on multidimensional data provided in the embodiments of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0027] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0028] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0029] Example 1 like Figure 1 As shown, the power grid investment benefit assessment method based on multidimensional data in this embodiment includes the following steps: S101: Construct a multi-source data pool for power grid investment benefits. The specific implementation process includes: 1) Data Source Access and Acquisition: Data is collected in real time from multiple core business systems of the power grid company through standardized data interfaces. Among them: Static topology data, including network structure parameters, equipment technical specifications, and geographic coordinate information, is obtained from the power grid information model (GIM) system. Real-time operational data, including power flow distribution, node voltage, load curves, and generation output, are obtained from the Supervisory Control and Data Acquisition (SCADA) system. Obtain asset status data from the Product Management System (PMS), including equipment health index, service life, maintenance records, and decommissioning plans; External environmental data, including meteorological conditions, temperature and humidity, wind speed and direction, and policy guidance, are obtained from environmental monitoring platforms.

[0030] 2) Data Preprocessing and Quality Control: ETL processing is performed on the collected raw data, specifically including: Data cleaning: Identifying and handling outliers, duplicate data, and inconsistent formatting issues; Missing value imputation: Missing data are imputed using multiple imputation combined with a time series prediction model; Data standardization: Converting data of different dimensions to the [0,1] interval; Spatiotemporal alignment: Ensure that all data has a consistent timestamp and spatial reference system.

[0031] 3) Data fusion and storage: Construct a unified data model to fuse and store multi-source data in a distributed database, supporting efficient querying and real-time updates.

[0032] S102: Construct a dynamic benefit evaluation matrix. For example... Figure 2 As shown, the specific implementation process includes: 1) Calculation of the economic vector F: Unit investment loss reduction benefit: Based on the change in line loss rate before and after investment, combined with electricity price, the economic benefits are calculated; Asset life cycle cost change rate: Considers the impact of investment on equipment maintenance costs and replacement cycles; Dynamic payback period forecast: The dynamic payback period is calculated using the discounted cash flow method combined with risk adjustment.

[0033] 2) Calculation of the reliability vector G: Improvement in node power supply reliability: Based on real-time topology and component reliability parameters, the degree of improvement in system average outage frequency (SAIFI) and system average outage duration (SAIDI) is calculated through Monte Carlo simulation. System average power outage frequency change rate: statistical trend of the number of failures before and after investment.

[0034] 3) Calculation of the synergy vector H: Contribution of inter-regional power flow balance: Analyzing the effect of investment on alleviating transmission congestion and optimizing power distribution; Improvement in renewable energy absorption capacity: Assessing the ability of investment to support the grid connection and absorption of renewable energy sources such as wind power and photovoltaics.

[0035] 4) Calculation of the robustness vector E: Critical path N-1 throughput change: Verify the system stability when critical equipment fails through power flow calculation; Quantitative indicators of system disturbance resistance: The ability of a system to withstand large disturbances is evaluated based on transient stability analysis.

[0036] 5) Matrix dynamic update mechanism: Establish a dual update mechanism based on event triggering and time driving. When a change in the power grid structure or an abnormal operating status is detected, the matrix is ​​immediately recalculated. At the same time, a regular update cycle (such as every 15 minutes) is set to ensure the timeliness of the evaluation results.

[0037] S103: Calculate the spatiotemporal comprehensive benefit index. The specific implementation process includes: 1) Determination of weighting coefficients: Dynamic weighting coefficients are determined using a modified Analytic Hierarchy Process (AHP) combined with the entropy weighting method. Subjective weighting: A judgment matrix is ​​constructed through expert surveys to calculate the subjective importance weight of each indicator; Objective weights: Objective weights are calculated based on the degree of variation in indicator data using the principle of information entropy. Comprehensive weighting: The subjective and objective weights are weighted and combined in a ratio of 6:4 to obtain the final dynamic weighting coefficients α, β, γ, δ.

[0038] 2) Vector normalization: The range normalization method is used to transform each vector element to a uniform dimension. Norm(X)=(X - X_min) / (X_max - X_min) Where X is the original vector value, and X_min and X_max are the historical minimum and maximum values ​​of the vector, respectively.

[0039] 3) Comprehensive index calculation: The spatiotemporal comprehensive benefit index is calculated according to the formula S(t)=α· Norm(F)+β· Norm(G)+γ· Norm(H)+δ· Norm(E). This index comprehensively reflects the overall performance of the investment project in multiple dimensions.

[0040] S104: Generate an investment benefit optimization strategy map. For example... Figure 3 As shown, the specific implementation process includes: 1) Spatial visualization mapping: Mapping the calculated benefit index and scores of each dimension onto the power grid geographical wiring diagram, specifically including: A gray gradient is used to represent the overall benefit level of different regions, gradually changing from light gray (low benefit) to dark gray (high benefit); Use icons of different shapes and sizes to identify the status of key device nodes; Arrows and flow lines are used to illustrate the direction of power flow and the transmission path of investment benefits.

[0041] 2) Benefit Hotspot Analysis: Identifying benefit hotspot areas and weak links based on spatial clustering algorithms: High-efficiency clusters: Identify clusters with significantly higher efficiency indices than surrounding areas and analyze their success factors; Low-efficiency clusters: Identify problem areas with low efficiency and diagnose the root causes; Benefit transmission path: Analyze the propagation pattern and scope of impact of investment benefits in the power grid.

[0042] 3) Optimization Strategy Recommendation: Based on the graph analysis results, automatically generate targeted investment optimization suggestions: For high-efficiency areas, it is recommended to expand the scale of investment and replicate successful experiences; For medium-efficiency areas, it is recommended to optimize the operation mode and improve the utilization rate of existing equipment; For low-efficiency areas, it is recommended to upgrade equipment or restructure the network to eliminate bottlenecks.

[0043] S105: Implement closed-loop feedback and model self-update. The specific implementation process includes: 1) Feedback Data Acquisition: Continuously monitor actual power grid operating indicators, including: Economic feedback: the deviation between actual and projected returns; Reliability feedback: the difference between the actual number of power outages and the predicted number; Collaborative feedback: Comparison between actual and predicted rates of curtailment of renewable energy sources; Robustness feedback: Comparison between the system's actual disturbance rejection capability and the evaluation results.

[0044] 2) Model parameter optimization: Based on feedback bias, an adaptive learning algorithm is used to optimize the model parameters. Weight coefficient adjustment: The values ​​of α, β, γ, and δ are dynamically adjusted using the gradient descent method; Evaluation model correction: The evaluation model is retrained based on historical data to improve prediction accuracy; Threshold parameter update: Adjust various judgment thresholds based on actual operating experience.

[0045] 3) Periodic evaluation and improvement: Establish a quarterly evaluation mechanism to comprehensively review the performance of the evaluation system. At the end of each quarter, a comprehensive evaluation of the accuracy and usability of the assessment model is conducted. The decision on whether to initiate model reconstruction will be made based on the evaluation results; Update the expert knowledge base to ensure that the evaluation criteria are up-to-date.

[0046] Through the detailed implementation of the above five steps, this embodiment achieves a comprehensive, dynamic, and accurate assessment of the benefits of power grid investment, providing strong support for the scientific decision-making of power grid enterprises. This method not only considers traditional economic indicators but also innovatively introduces key dimensions required for modern power grid development, such as synergy and robustness, thus possessing significant practical value.

[0047] Example 2 like Figure 4 As shown, this embodiment provides a system for implementing the above method, including: The data aggregation and processing module 401 is responsible for communicating with external data sources, performing data collection, cleaning, and storage tasks, and maintaining a multi-source data pool.

[0048] The dynamic matrix construction module 402 calls the data in the data pool and calculates and generates the dynamic benefit evaluation matrix M(t) according to the built-in algorithm model.

[0049] The comprehensive evaluation calculation module 403 receives the dynamic matrix and performs weight calculation, normalization, and comprehensive index calculation.

[0050] The visualization decision support module 404 receives the evaluation results, combines them with power grid graphical data, generates an interactive strategy map, and provides it to the user.

[0051] The adaptive learning optimization module 405 monitors feedback data, executes model training and parameter update algorithms, and completes the evaluation of the model's self-evolution.

[0052] Example 3 The present invention also provides an electronic device, including: a processor, a transmitting device, an input device, an output device, and a memory. The processor may be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory may be implemented using a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0053] Example 4 The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0054] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0055] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for evaluating the benefit of power grid investment based on multi-dimensional data, characterized in that, The method comprises the following steps: S101: Constructing a power grid investment benefit multi-source data pool, acquiring multi-dimensional data related to the investment project online, and preprocessing the data to form a standardized multi-source data pool; The multi-dimensional data at least includes static topology data, real-time operation data, asset state data and external environment data; S102: Based on the multi-source data pool, a dynamically updated benefit evaluation matrix M(t) is constructed, the matrix M(t) = [F, G, H, E], wherein F is an economic vector, G is a reliability vector, H is a synergy vector, and E is a robustness vector; S103: Using a weighted aggregation model, the time and space comprehensive benefit index S(t) of the dynamic benefit evaluation matrix M(t) is calculated; S104: The time and space comprehensive benefit index S(t) and its dimensional vector results are mapped to the power grid geographical connection diagram and topology structure diagram to form a visual investment benefit optimization strategy map; S105: Comparing the actual operation data with the evaluation prediction results to generate a feedback deviation, and periodically adapting the dynamic weight coefficient and the weighted aggregation model using the feedback deviation.

2. The method of claim 1, wherein, In the step of constructing the power grid investment benefit multi-source data pool, the data sources include a power grid information model, a dispatch automation system, an asset management system and an environment monitoring platform.

3. The method of claim 1, wherein, The elements of the economic vector F include unit investment loss reduction benefit, asset life cycle cost change rate and investment recovery period dynamic prediction value; the elements of the reliability vector G include node power supply reliability improvement degree based on real-time topology and system average power outage frequency change rate; the elements of the synergy vector H include investment contribution to regional power flow balance and improvement degree of new energy consumption capacity; the elements of the robustness vector E include change of N-1 passing rate of key lines of the power grid after investment and quantitative index of system disturbance resistance.

4. The method of claim 1, wherein, The investment benefit optimization strategy map is used to identify weak benefit areas, recommend additional investment directions, and show benefit comparisons of different investment schemes.

5. The method of claim 1, wherein, Periodically adapt the dynamic weight coefficient and the weighted aggregation model using a machine learning algorithm according to the feedback deviation.

6. The method of claim 5, wherein, The process of periodic adaptive optimization comprises the following steps: Set the model update period T and initialize the evaluation model parameters; At the end of each update period, collect the actual operation data and evaluation prediction results in the period to calculate the feedback deviation; Using the feedback deviation, the dynamic weight coefficient and the weighted aggregation model are optimized by gradient descent method or genetic algorithm; Update the optimized model parameters to the evaluation model for benefit evaluation in the next period.

7. The method of claim 6, wherein, The process of periodic adaptive optimization further comprises: Set a model performance threshold, when the feedback deviation of consecutive multiple periods exceeds the threshold, trigger an emergency model reconstruction; The emergency model reconstruction includes re-collecting historical data, re-training model parameters, and verifying model performance; During model reconstruction, a sliding window average method is temporarily used to replace the evaluation model output.

8. A multi-dimensional data based power grid investment benefit evaluation system for implementing the method of any one of claims 1-7, characterized in that, Comprise: a data aggregation and processing module configured to build and manage the power grid investment benefit multi-source data pool; a dynamic matrix construction module configured to build and update the dynamic benefit evaluation matrix M(t) based on the multi-source data pool; a comprehensive evaluation calculation module configured to calculate the spatio-temporal comprehensive benefit index S(t); a visual decision support module configured to generate and display the investment benefit optimization strategy map; an adaptive learning optimization module configured to update the evaluation model using feedback data.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-7.

Images