Comprehensive evaluation method for comprehensive energy system

Abstract

The invention discloses a comprehensive evaluation method for a comprehensive energy system, and the method specifically comprises the following steps: 1, constructing a multi-dimensional index system: employing a hierarchical structure to construct four types of indexes including technology, economy, environment and reliability, and refining each type of indexes into at least three secondary indexes; and 2, dynamic weight adaptive distribution: adopting an improved entropy weight and game theory combined weighting method based on real-time data, such as electricity price fluctuation, weather change and load demand, and preset scenes, such as extreme climate and policy adjustment, and relates to the technical field of comprehensive energy system evaluation. According to the comprehensive evaluation method for the comprehensive energy system, correlation interference among indexes is effectively eliminated through an improved entropy weight and game theory combined weighting method, and the entropy value is dynamically updated by introducing multiple data information, so that weight calculation can adapt to the time sequence change characteristic of the energy system, and the comprehensive evaluation accuracy is improved. And meanwhile, the subjective and objective weight collaborative equalization is realized by constructing a Nash equilibrium game model.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated energy system evaluation, and in particular to a comprehensive evaluation method for an integrated energy system. Background Art

[0002] An integrated energy system refers to a new type of integrated energy system that uses advanced physical information technology and innovative management models to integrate various energy sources such as coal, oil, natural gas, electricity, and thermal energy in a certain area, and realize coordinated planning, optimized operation, collaborative management, interactive response, and mutual complementarity among various heterogeneous energy subsystems. While meeting the diversified energy needs within the system, it must effectively improve energy utilization efficiency and promote sustainable energy development.

[0003] Reference patent announcement number "CN117649138A" discloses a comprehensive evaluation method for the operation strategy of an integrated energy system, which is carried out in accordance with the following steps: according to the construction principles of the integrated energy system indicator system, a comprehensive evaluation indicator system for the integrated energy system is established, the indicator groups are stratified and classified, and a specific quantification method for each indicator is given; the indicator groups are divided into 4 first-level indicators and 7 second-level indicators, the 4 first-level indicators are: economy, energy efficiency, flexibility and environmental protection, and the 7 second-level indicators are: equipment maintenance cost, energy purchase cost, comprehensive energy utilization rate, reserve equipment utilization rate, grid interaction power fluctuation rate, gas grid interaction power fluctuation rate, and pollutant emissions.

[0004] As shown in the aforementioned technology, existing evaluation systems generally use manual weight adjustment, with an update cycle of up to quarterly or even annual periods. For example, the adjustment of the weights of the economic indicators of a provincial power grid company requires multiple rounds of expert review, which is time-consuming. As a result, the system cannot respond to intraday electricity price fluctuations and lacks predictive capabilities. Traditional methods lack prediction modules for key parameters and rely solely on weighted averages of historical data. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a comprehensive evaluation method for an integrated energy system, which solves the problems of time-consuming weight adjustment and slow response in the existing comprehensive evaluation method for an integrated energy system.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A comprehensive evaluation method for an integrated energy system specifically comprises the following steps:

[0007] Step 1: Construct a multi-dimensional indicator system: Use a hierarchical structure to construct four major categories of indicators covering technology, economy, environment, and reliability, and refine each major category into at least three secondary indicators;

[0008] Step 2: Dynamic weight adaptive allocation: Based on real-time data such as electricity price fluctuations, weather changes, load demand, and preset scenarios such as extreme climate and policy adjustments, an improved entropy weight and game theory combined weighting method is used;

[0009] Entropy weight method: calculate the objective weight of each indicator to reflect the degree of data dispersion;

[0010] Game theory: Introducing the subjective weight preferences of stakeholders such as governments, enterprises, and users, and optimizing conflicts between subjective and objective weights through Nash equilibrium;

[0011] Dynamic adjustment: Combined with the LSTM neural network to predict the weight change trend in the future period and realize adaptive weight update;

[0012] Step 3: Establish an intelligent comprehensive evaluation model;

[0013] Step 4: Visualize decision support.

[0014] Preferably, the secondary indicators of the technical indicators include:

[0015] Multi-energy complementary efficiency: measures the coupling efficiency of the electricity, heat and cooling multi-energy supply system;

[0016] Energy conversion efficiency: through Analyze and calculate the energy quality coefficient of each energy conversion equipment;

[0017] Renewable energy penetration rate: the proportion of clean energy such as photovoltaics and wind power in the total energy supply.

[0018] Preferably, the secondary indicators of the economic indicators include:

[0019] Full life cycle cost: covering equipment investment, operation and maintenance costs, and residual value recovery;

[0020] Dynamic electricity price benefits: Calculate the energy trading benefit maximization objective based on the time-of-use electricity price model;

[0021] Investment return cycle: dual evaluation using net present value method and internal rate of return.

[0022] Preferably, the secondary indicators of the environmental performance index include:

[0023] Carbon intensity index: CO2 emissions per unit of energy supplied, dynamically adjusted based on the carbon quota trading mechanism;

[0024] Pollutant emission equivalent: converting pollutants such as SO2 and NOx into equivalent environmental costs;

[0025] Green certificate coverage: measures the completion of renewable energy quotas.

[0026] Preferably, the secondary indicators of the reliability index include:

[0027] Energy availability: Calculate the system's annual failure-free probability based on the Markov chain model;

[0028] Energy storage reserve margin: quantifies the ability of the energy storage system to cope with sudden load fluctuations;

[0029] Fault recovery time: Simulate the recovery efficiency in extreme scenarios through digital twin simulation.

[0030] Preferably, the data-driven entropy weight method inputs real-time data, such as energy prices, meteorological data, and load curves, and calculates the information entropy value of each indicator. The calculation formula is as follows:

[0031]

[0032]

[0033] The objective weights are:

[0034] where x ij : The original observation value of the i-th sample on the j-th indicator;

[0035] P ij : The proportion of the i-th sample under the j-th indicator;

[0036] E j : The information entropy of the jth indicator, measuring the dispersion of data

[0037] The game theory empowerment optimization integrates the subjective weights of the government, enterprises, and users to construct a game model:

[0038] min||W sub w sub -W obj w obj ||;

[0039] Where W sub : subjective weight set, a matrix consisting of weight vectors set by stakeholders;

[0040] W obj : objective weight matrix, weight vector calculated by entropy weight method;

[0041] Then, the Nash equilibrium point is solved by the Lagrange multiplier method, and the comprehensive weight is output;

[0042] The LSTM weight prediction is to train the LSTM network to predict the weight adjustment trend in the future period by inputting the historical weight sequence and external variables. The update formula is:

[0043] w t =αwt-1 +(1-α)w t ;

[0044] Where α∈[0,1] is the smoothing coefficient.

[0045] Preferably, the step 3 of establishing an intelligent comprehensive evaluation model includes:

[0046] Establish a fuzzy comprehensive evaluation model based on improved TOPSIS;

[0047] Data normalization: Use range method to process heterogeneous data;

[0048] Fuzzy membership: combining triangular fuzzy numbers to represent uncertainty and expert experience;

[0049] Dynamic ideal solution: Update positive and negative ideal solutions based on real-time data to improve the timeliness of evaluation.

[0050] Preferably, the visual decision support generates a three-dimensional visual report through the digital twin platform, displays the evaluation results, short board indicators and optimization paths, and supports users to interactively adjust parameters.

[0051] Beneficial effects

[0052] The present invention provides a comprehensive evaluation method for an integrated energy system. Compared with the existing technology, it has the following advantages:

[0053] 1. This comprehensive evaluation method for the integrated energy system effectively eliminates the correlation interference between indicators through the improved entropy weight and game theory combined weighting method. Combined with the introduction of multiple data information to dynamically update the entropy value, the weight calculation can adapt to the temporal change characteristics of the energy system and improve stability. At the same time, the subjective and objective weights are coordinated and balanced by constructing a Nash equilibrium game model, combining the improved entropy weight method with the subjective weighting method for optimization, solving the bias problem of a single weighting method. The coordination of the combined weights is effectively improved, which is better than the traditional linear combination method.

[0054] 2. This comprehensive evaluation method for the integrated energy system constructs multiple evaluation matrices for technology, economy, environment, and reliability, and combines the coefficient of variation method to optimize the indicator screening mechanism, thereby avoiding the dilution effect of redundant indicators on the evaluation results, improving the consistency between the evaluation results and the actual operation data, and reducing the error compared with traditional methods.

[0055] 3. This comprehensive energy system evaluation method, through a dynamic evaluation framework integrating an LSTM neural network prediction module, can predict system performance trends 3-6 hours in advance, support real-time control decisions, and effectively improve short-term prediction accuracy, significantly outperforming the static evaluation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] See also Figure 1 The present invention discloses a comprehensive evaluation method for an integrated energy system, which specifically includes the following steps:

[0059] Step 1: Construct a multi-dimensional indicator system: Use a hierarchical structure to construct four major categories of indicators covering technology, economy, environment, and reliability, and refine each major category into at least three secondary indicators;

[0060] The secondary indicators of technical indicators include:

[0061] Multi-energy complementary efficiency: measures the coupling efficiency of the electricity / heat / cooling multi-energy combined supply system;

[0062] Energy conversion efficiency: through Analyze and calculate the energy quality coefficient of each energy conversion equipment;

[0063] Renewable energy penetration rate: the proportion of clean energy such as photovoltaics and wind power in the total energy supply.

[0064] The secondary indicators of economic indicators include:

[0065] Full life cycle cost: covering equipment investment, operation and maintenance costs, and residual value recovery;

[0066] Dynamic electricity price benefits: Calculate the energy trading benefit maximization objective based on the time-of-use electricity price model;

[0067] Investment return cycle: dual evaluation using net present value method and internal rate of return.

[0068] The secondary indicators of environmental protection indicators include:

[0069] Carbon intensity index: CO2 emissions per unit of energy supplied, dynamically adjusted based on the carbon quota trading mechanism;

[0070] Pollutant emission equivalent: converting pollutants such as SO2 and NOx into equivalent environmental costs;

[0071] Green certificate coverage: measures the completion of renewable energy quotas.

[0072] The secondary indicators of reliability index include:

[0073] Energy availability: Calculate the system's annual failure-free probability based on the Markov chain model;

[0074] Energy storage reserve margin: quantifies the ability of the energy storage system to cope with sudden load fluctuations;

[0075] Fault recovery time: Simulate the recovery efficiency in extreme scenarios through digital twin simulation.

[0076] By constructing multiple evaluation matrices for technology, economy, environment, and reliability, and combining them with the coefficient of variation method to optimize the indicator screening mechanism, the dilution effect of redundant indicators on the evaluation results is avoided, the consistency between the evaluation results and the actual operation data is improved, and the error is reduced compared with traditional methods.

[0077] Step 2: Dynamic weight adaptive allocation: Based on real-time data such as electricity price fluctuations, weather changes, load demand, and preset scenarios such as extreme climate and policy adjustments, an improved entropy weight and game theory combined weighting method is used;

[0078] Entropy weight method: Calculate the objective weight of each indicator to reflect the degree of data dispersion. When performing the data-driven entropy weight method, real-time data such as energy prices, meteorological data, and load curves are input to calculate the information entropy value of each indicator. The calculation formula is as follows:

[0079]

[0080]

[0081] The objective weights are:

[0082] where x ij : The original observation value of the i-th sample on the j-th indicator;

[0083] P ij : The proportion of the i-th sample under the j-th indicator;

[0084] E j : The information entropy of the jth indicator, measuring the data dispersion;

[0085] Game theory: Introducing the subjective weight preferences of stakeholders including government, enterprises, and users, optimizing the conflict between subjective and objective weights through Nash equilibrium, and empowering game theory to optimize and integrate the subjective weights of the three parties to build a game model:

[0086] min||W sub w sub -W obj w obj ||;

[0087] Where W sub: subjective weight set, a matrix consisting of weight vectors set by stakeholders;

[0088] W obj : objective weight matrix, weight vector calculated by entropy weight method;

[0089] Then, the Nash equilibrium point is solved by the Lagrange multiplier method, and the comprehensive weight is output;

[0090] Dynamic adjustment: Combined with the LSTM neural network to predict the weight change trend in the future period, the weight adaptive update is achieved. The LSTM weight prediction is trained by inputting the historical weight sequence and external variables to predict the weight adjustment trend in the future period. The update formula is:

[0091] w t =αw t-1 +(1-α)w t ;

[0092] Where α∈[0,1] is the smoothing coefficient.

[0093] Through the improved entropy weight and game theory combined weighting method, the correlation interference between indicators is effectively eliminated. Combined with the introduction of multiple data information to dynamically update the entropy value, the weight calculation can adapt to the temporal change characteristics of the energy system and improve stability. At the same time, the subjective and objective weights are coordinated and balanced by constructing a Nash equilibrium game model, combining the improved entropy weight method with the subjective weighting method for optimization, solving the bias problem of a single weighting method. The coordination of the combined weights is effectively improved, which is better than the traditional linear combination method.

[0094] Step 3: Establish an intelligent comprehensive evaluation model and a fuzzy comprehensive evaluation model based on the improved TOPSIS; data normalization: use the range method to process heterogeneous data; fuzzy membership: combine triangular fuzzy numbers to represent uncertainty and expert experience; dynamic ideal solution: update positive and negative ideal solutions based on real-time data to improve the timeliness of evaluation;

[0095] Step 4: Visual decision support. Visual decision support generates a three-dimensional visual report through the digital twin platform, showing the evaluation results, short board indicators and optimization paths, and supporting users to interactively adjust parameters.

[0096] By integrating the dynamic evaluation framework of the LSTM neural network prediction module, system performance trends can be predicted 3-6 hours in advance, supporting real-time control decisions, and effectively improving short-term prediction accuracy, which is significantly better than the static evaluation system.

[0097] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0098] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive evaluation method for an integrated energy system, characterized by: The specific steps include: Step 1: Construct a multi-dimensional indicator system: Use a hierarchical structure to construct four major categories of indicators covering technology, economy, environment, and reliability, and refine each major category into at least three secondary indicators; Step 2: Dynamic weight adaptive allocation: Based on real-time data such as electricity price fluctuations, weather changes, load demand, and preset scenarios such as extreme climate and policy adjustments, an improved entropy weight and game theory combined weighting method is used; Entropy weight method: calculate the objective weight of each indicator to reflect the degree of data dispersion; Game theory: Introducing the subjective weight preferences of stakeholders such as governments, enterprises, and users, and optimizing conflicts between subjective and objective weights through Nash equilibrium; Dynamic adjustment: Combined with the LSTM neural network to predict the weight change trend in the future period and realize adaptive weight update; Step 3: Establish an intelligent comprehensive evaluation model; Step 4: Visualize decision support.

2. A comprehensive evaluation method for an integrated energy system according to claim 1, characterized in that: The secondary indicators of the technical indicators include: Multi-energy complementary efficiency: measures the coupling efficiency of the electricity, heat and cooling multi-energy supply system; Energy conversion efficiency: through Analyze and calculate the energy quality coefficient of each energy conversion equipment; Renewable energy penetration rate: the proportion of clean energy such as photovoltaics and wind power in the total energy supply.

3. The comprehensive evaluation method for an integrated energy system according to claim 1, characterized in that: The secondary indicators of the economic indicators include: Full life cycle cost: covering equipment investment, operation and maintenance costs, and residual value recovery; Dynamic electricity price benefits: Calculate the energy trading benefit maximization objective based on the time-of-use electricity price model; Investment return cycle: dual evaluation using net present value method and internal rate of return.

4. The comprehensive evaluation method for an integrated energy system according to claim 1, characterized in that: The secondary indicators of the environmental protection index include: Carbon intensity index: CO2 emissions per unit of energy supplied, dynamically adjusted based on the carbon quota trading mechanism; Pollutant emission equivalent: converting pollutants such as SO2 and NOx into equivalent environmental costs; Green certificate coverage: measures the completion of renewable energy quotas.

5. The comprehensive evaluation method for an integrated energy system according to claim 1, characterized in that: The secondary indicators of the reliability index include: Energy availability: Calculate the system's annual failure-free probability based on the Markov chain model; Energy storage reserve margin: quantifies the ability of the energy storage system to cope with sudden load fluctuations; Fault recovery time: Simulate the recovery efficiency in extreme scenarios through digital twin simulation.

6. A comprehensive energy system comprehensive evaluation method according to claim 1, characterized in that: The data-driven entropy weight method inputs real-time data, such as energy prices, meteorological data, and load curves, to calculate the information entropy value of each indicator. The calculation formula is as follows: The objective weights are: where x ij : The original observation value of the i-th sample on the j-th indicator; P ij : The proportion of the i-th sample under the j-th indicator; E j : The information entropy of the jth indicator, measuring the data dispersion; The game theory empowerment optimization integrates the subjective weights of the government, enterprises, and users to construct a game model: min||In sub ·In sub -IN obj ·In obj ||; Where W sub : subjective weight set, a matrix consisting of weight vectors set by stakeholders; W obj : objective weight matrix, weight vector calculated by entropy weight method; Then, the Nash equilibrium point is solved by the Lagrange multiplier method, and the comprehensive weight is output; The LSTM weight prediction is to train the LSTM network to predict the weight adjustment trend in the future period by inputting the historical weight sequence and external variables. The update formula is: w t =αw t-1 +(1-a)w t ; Where α∈[0,1] is the smoothing coefficient.

7. The comprehensive evaluation method for an integrated energy system according to claim 1, characterized in that: The step 3 of establishing an intelligent comprehensive evaluation model includes: Establish a fuzzy comprehensive evaluation model based on improved TOPSIS; Data normalization: Use range method to process heterogeneous data; Fuzzy membership: combining triangular fuzzy numbers to represent uncertainty and expert experience; Dynamic ideal solution: Update positive and negative ideal solutions based on real-time data to improve the timeliness of evaluation.

8. The comprehensive evaluation method for an integrated energy system according to claim 1, characterized in that: The visual decision support generates a three-dimensional visual report through the digital twin platform, displays the evaluation results, short board indicators and optimization paths, and supports users to interactively adjust parameters.

Images