Electric power energy system multi-dimensional evaluation method and related device

Abstract

The invention belongs to an electric power evaluation method, and provides an electric power energy system multi-dimensional evaluation method and a related device for solving the technical problems that a current electric power market evaluation method is numerous in evaluation indexes, easy to confuse and non-standard. And comprehensively evaluating multiple indexes of different power generation technologies in the electric power energy system. According to the method, comprehensive evaluation of the sustainable development of the multi-dimensional electrical energy system is carried out based on the gray analysis method, and the promotion effect of the development of renewable energy on the electrical energy system can be analyzed. The method can be used for pre-evaluation and post-evaluation of different-scale energy system planning. The technical problems that in an existing evaluation method, performance evaluation indexes are numerous, high in correlation, prone to being confused and not standard are solved.

Description

Technical Field

[0001] The present application relates to a method for evaluating electric power, and specifically to a method for evaluating a multi-dimensional electric power energy system and related devices. Background Art

[0002] Power market performance evaluation is a key link in the market-oriented reform of the power industry. Through economic analysis of the power market operation status, it provides decision-making basis for market participants and policy recommendations for market regulatory authorities, thereby promoting the development of the power market and the efficient allocation of power resources.

[0003] At present, the performance evaluation of the power market faces two difficulties: first, the particularity of the power market makes the performance evaluation involve multiple factors, such as power demand, supply, price, quality, environment, etc., and it is necessary to comprehensively consider various influencing factors; second, the diversity of the power market makes the performance evaluation different. Different market structures, rules, participants, etc. will lead to different market performance, so it is difficult to formulate a unified evaluation standard and method. Especially in the current context of the grid connection of new energy and traditional energy, the performance evaluation of the power market has encountered many new problems. The current new energy concept has fuzzy boundaries and is characterized by multi-subject game, heterogeneous energy flow coupling integration, and complex and diverse technical routes. Therefore, there are many performance evaluation indicators, which are easy to confuse and non-standard, making it difficult to ensure the accuracy and comprehensiveness of the evaluation. Summary of the invention

[0004] In order to solve the technical problems that current electricity market evaluation methods have too many evaluation indicators, which are easily confused and non-standard, this application provides a multi-dimensional evaluation method and related devices for an electric energy system.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In the first aspect, the present application proposes a multi-dimensional evaluation method for an electric energy system, including: Obtaining a graph structure of an electric energy system, a power generation evaluation index of each node in the graph structure, and a connection relationship between nodes in the graph structure; the graph structure of the electric energy system includes a plurality of nodes and edges connecting the plurality of nodes, and the nodes represent different power generation technologies; The graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure are input into the evaluation graph neural network to obtain a comprehensive evaluation result of the electric energy system; The evaluation graph neural network performs a comprehensive evaluation on multiple power generation evaluation indicators of different power generation technologies in the electric energy system based on the grey correlation coefficient; The grey correlation coefficient is determined according to the ideal scheme and the values ​​of each scheme on each power generation evaluation index; the ideal scheme is determined according to the optimal value of each power generation evaluation index, and each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies.

[0006] Furthermore, the training method of the evaluation graph neural network includes: Obtain power generation evaluation indicators for various power generation technologies; Conduct energy value analysis on various power generation technologies respectively and draw energy value flow charts corresponding to the power generation technologies; Standardize the power generation evaluation indicators to unify their dimensions; Determine the ideal solution based on the optimal values ​​of each power generation evaluation index; According to the grey correlation coefficient between the ideal scheme and the numerical values ​​of each scheme on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, the comprehensive evaluation result between each scheme and the ideal scheme is determined; each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies; The graph neural network is trained based on the comprehensive evaluation results between each scheme and the ideal scheme, as well as the corresponding graph structure of the power energy system.

[0007] Furthermore, the gray correlation coefficient between the ideal solution and the values ​​of each solution on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, determines the comprehensive evaluation result between each solution and the ideal solution, including:

[0008] in, It represents the value of the ideal solution on a certain power generation evaluation index. Indicates The value of a scheme on a certain power generation evaluation index, The ideal solution and The comprehensive evaluation result value of each scheme is The energy value flow chart reflects the The weight of each power generation evaluation index is The ideal solution is The value of the power generation evaluation index is It represents the standardized value of different schemes under each power generation evaluation index. express and Grey relational calculation formula.

[0009] Furthermore, the obtaining of power generation evaluation indicators of multiple power generation technologies includes: Obtain basic power generation related parameters for various power generation technologies; According to the basic power generation related parameters, the energy value sustainability index and the whole life cycle cost are calculated, and the energy value sustainability index, the whole life cycle cost and power generation efficiency are used as power generation evaluation indicators.

[0010] Further, the multiple power generation technologies include photovoltaic, wind power, hydropower, gas and coal; The basic power generation related parameters include: installed capacity and chip area of ​​photovoltaic power generation units; wind turbine composition, total installed capacity, annual average wind speed, and capacity factor of wind farms; installed capacity of hydropower stations; installed capacity and plant power consumption rate of gas-fired power generation units; installed capacity and coal consumption of coal-fired power generation units.

[0011] Furthermore, the standardization of the power generation evaluation index includes: The membership degree of the power generation evaluation index is calculated as the index after the power generation evaluation index is unified in dimension.

[0012] Furthermore, the graph neural network is a graph convolutional network; The loss function used by the graph convolutional network is a multi-task loss function: ; in, is the multi-task loss function, is the weight of the loss of different tasks, is the noise observation parameter of the first task, is the noise observation parameter of the second task, is the loss of the first task, For the loss of the second task.

[0013] In the second aspect, the present application proposes a multi-dimensional evaluation system for electric energy systems, including: An acquisition module, used to acquire a graph structure of an electric energy system, a power generation evaluation index of each node in the graph structure, and a connection relationship between nodes in the graph structure; the graph structure of the electric energy system includes a plurality of nodes and edges connecting the plurality of nodes, and the nodes represent different power generation technologies; An evaluation module is used to input the graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure into the evaluation graph neural network to obtain a comprehensive evaluation result of the electric energy system; The evaluation graph neural network performs a comprehensive evaluation on multiple power generation evaluation indicators of different power generation technologies in the electric energy system based on the grey correlation coefficient; The grey correlation coefficient is determined according to the ideal scheme and the values ​​of each scheme on each power generation evaluation index; the ideal scheme is determined according to the optimal value of each power generation evaluation index, and each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies.

[0014] Furthermore, the training method of the evaluation graph neural network includes: Obtain power generation evaluation indicators for various power generation technologies; Conduct energy value analysis on various power generation technologies respectively and draw energy value flow charts corresponding to the power generation technologies; Standardize the power generation evaluation indicators to unify their dimensions; Determine the ideal solution based on the optimal values ​​of each power generation evaluation index; According to the grey correlation coefficient between the ideal scheme and the numerical values ​​of each scheme on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, the comprehensive evaluation result between each scheme and the ideal scheme is determined; each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies; The graph neural network is trained based on the comprehensive evaluation results between each scheme and the ideal scheme, as well as the corresponding graph structure of the power energy system.

[0015] Furthermore, the gray correlation coefficient between the ideal solution and the values ​​of each solution on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, determines the comprehensive evaluation result between each solution and the ideal solution, including:

[0016] in, It represents the value of the ideal solution on a certain power generation evaluation index. Indicates The value of a scheme on a certain power generation evaluation index, The ideal solution and The comprehensive evaluation result value of each scheme is The energy value flow chart reflects the The weight of each power generation evaluation index is The ideal solution is The values ​​of the power generation evaluation indicators are It represents the standardized value of different schemes under each power generation evaluation index. express and Grey relational calculation formula: Furthermore, the obtaining of power generation evaluation indicators of multiple power generation technologies includes: Obtain basic power generation related parameters for various power generation technologies; According to the basic power generation related parameters, the energy value sustainability index and the whole life cycle cost are calculated, and the energy value sustainability index, the whole life cycle cost and power generation efficiency are used as power generation evaluation indicators.

[0017] Further, the multiple power generation technologies include photovoltaic, wind power, hydropower, gas and coal; The basic power generation related parameters include: installed capacity and chip area of ​​photovoltaic power generation units; wind turbine composition, total installed capacity, annual average wind speed, and capacity factor of wind farms; installed capacity of hydropower stations; installed capacity and plant power consumption rate of gas-fired power generation units; installed capacity and coal consumption of coal-fired power generation units.

[0018] Furthermore, the standardization of the power generation evaluation index includes: The membership degree of the power generation evaluation index is calculated as the index after the power generation evaluation index is unified in dimension.

[0019] Furthermore, the graph neural network is a graph convolutional network; The loss function used by the graph convolutional network is a multi-task loss function: .

[0020] in, is the multi-task loss function, is the weight of the loss of different tasks, is the noise observation parameter of the first task, is the noise observation parameter of the second task, is the loss of the first task, For the loss of the second task.

[0021] In a third aspect, the present application provides an electronic device, comprising: Memory for storing computer programs; A processor is used to implement the steps of the above-mentioned multi-dimensional evaluation method of the electric energy system when executing the computer program.

[0022] In a fourth aspect, the present application proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned multi-dimensional evaluation method of the electric power energy system are implemented.

[0023] Compared with the prior art, this application has the following beneficial effects: This application proposes a multi-dimensional evaluation method for electric energy systems, which uses graph neural networks and graph structures of electric energy systems, combined with gray correlation coefficients, to comprehensively evaluate multiple indicators of different power generation technologies in electric energy systems. This application conducts a comprehensive evaluation of the sustainable development of a multi-dimensional electric energy system based on the grayscale analysis method, and can analyze the effect of the development of renewable energy on the electric energy system. It can be used for pre-evaluation and post-evaluation of energy system planning at different scales. In addition, the evaluation of different power generation modes can be carried out under different technical and economic backgrounds. Even if the selection of the energy value benchmark has certain uncertainties, the overall conclusion of the horizontal comparison in the same time and space will not change, and appropriate sensitivity analysis can be performed when necessary. It solves the technical problems of the numerous performance evaluation indicators in the existing evaluation methods, which are highly correlated, easy to confuse, and non-standard.

[0024] This application also proposes a multi-dimensional evaluation system for electric power energy systems, electronic equipment and computer storage media, which have all the advantages of the above-mentioned multi-dimensional evaluation method for electric power energy systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 This is a schematic diagram of the first process of the multi-dimensional evaluation method of the electric energy system in this application; Figure 2 This is a second flow chart of the multi-dimensional evaluation method of the electric energy system in this application; Figure 3 This is a schematic diagram of the structure of the multi-dimensional evaluation method of the electric energy system in this application; Figure 4 It is a schematic diagram of the model of multi-dimensional evaluation method of power energy system; Figure 5 An energy value flow chart drawn based on the energy structure of China's power system; Figure 6 Emergy flow chart for five power generation technologies; Figure 7 This is a schematic diagram of a multi-dimensional evaluation system for an electric energy system proposed in this application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0028] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0029] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0030] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invented product is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0031] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0032] In the description of the embodiments of the present application, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0033] Power market performance evaluation is a process of comprehensively evaluating the efficiency and performance level of the power market. It aims to reflect the power market's operating conditions, degree of competition, supply and demand matching, technological innovation, and sustainable development capabilities through a series of indicators. It not only helps market participants and stakeholders understand the market's operating conditions, existing problems, and changing trends, but also serves as a necessary tool for market analysis and management decision-making. Through performance evaluation, problems in the market can be discovered in a timely manner to promote the healthy operation and effective development of the market.

[0034] In the current context of the connection of new energy and traditional energy to the grid, the performance evaluation of the electricity market has indeed encountered many new problems. The evaluation process is faced with a large number of performance evaluation indicators that are easy to confuse and non-standard, making it difficult to ensure the accuracy and comprehensiveness of the evaluation.

[0035] Based on the above situation, the present application proposes a multi-dimensional evaluation method and related devices for an electric power energy system. The present application is described in detail below in conjunction with embodiments and drawings.

[0036] like Figure 1 As shown, it is a first flow chart of the multi-dimensional evaluation method of the electric energy system of the present application, which may include: S101, obtaining a graph structure of an electric energy system, a power generation evaluation index of each node in the graph structure, and a connection relationship between nodes in the graph structure; the graph structure of the electric energy system includes a plurality of nodes and edges connecting the plurality of nodes, and the nodes represent different power generation technologies.

[0037] It should be noted that in the electric power energy system, the graph structure is an effective representation method that can clearly display the various power generation technologies (nodes) in the system and the connection relationships (edges) between them. Among them, in the graph structure, each node represents a specific power generation technology, such as thermal power generation, hydropower generation, wind power generation, solar power generation, etc. These nodes are the basic components of the electric power energy system. The edge represents the connection relationship between the nodes, that is, the power transmission or interaction between different power generation technologies. For example, a thermal power station and a hydropower station may be connected by a transmission line to form an edge in the graph. The power generation evaluation index can be set according to the specific evaluation purpose, and this application does not make specific restrictions.

[0038] S102, inputting the graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure into the evaluation graph neural network to obtain a comprehensive evaluation result of the electric energy system.

[0039] It should be noted that in a graph neural network, each node can have its own feature vector, and the edge can represent the strength or type of connection between nodes. The goal of a graph neural network is to learn useful representations from graph structured data and use these representations to perform corresponding tasks. The comprehensive evaluation result of the power energy system is a comprehensive evaluation based on multiple power generation evaluation indicators, and the evaluation result is more comprehensive and accurate.

[0040] The evaluation graph neural network comprehensively evaluates multiple power generation evaluation indicators of different power generation technologies in the electric energy system based on the grey correlation coefficient; the grey correlation coefficient is determined according to the ideal scheme and the values ​​of each scheme on each power generation evaluation indicator; the ideal scheme is determined according to the optimal value of each power generation evaluation indicator, and each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies.

[0041] In some embodiments of the present application, the training method of the evaluation graph neural network may include: (1) Obtain power generation evaluation indicators for various power generation technologies; (2) Conduct energy value analysis on various power generation technologies and draw energy value flow charts corresponding to the power generation technologies; It should be noted that the specific methods of energy value analysis may be different for different power generation technologies. For example: thermal power generation mainly generates heat energy by burning fossil fuels such as coal, oil or natural gas, and then converts it into electrical energy. Energy value analysis can focus on the energy value of fuel input (including its energy value conversion efficiency), thermal energy conversion efficiency, mechanical energy conversion efficiency and final electrical energy output, and can also consider the negative energy value impact of environmental pollution (such as CO2, SO2, NOx, etc. emissions). Hydropower generation uses the gravitational potential energy or kinetic energy of water flow to convert into mechanical energy, and then further converts it into electrical energy. Energy value analysis can focus on the energy value input of water resources, turbine conversion efficiency, generator conversion efficiency and electrical energy output. At the same time, the impact of reservoir construction on the ecological environment can also be considered.

[0042] It should be noted that the drawing of the energy value flow chart also makes it convenient to make corresponding adjustments quickly and accurately with the help of visualization methods when the comprehensive evaluation results are obtained.

[0043] (3) Standardize the power generation evaluation indicators to unify their dimensions; (4) Determine the ideal solution based on the optimal values ​​of each power generation evaluation index; It should be noted that the optimal value is determined according to the specific situation of the power generation evaluation index, for example, the maximum value or minimum value of the power generation evaluation index is selected.

[0044] (5) Determine the comprehensive evaluation results between each scheme and the ideal scheme based on the grey correlation coefficient between the values ​​of the ideal scheme and each scheme on each power generation evaluation index, combined with the weights of each power generation evaluation index reflected in the energy value flow chart; each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies; It should be noted that the grey correlation coefficient is an important concept in grey system theory, which is used to describe the degree of correlation between two sequences. In grey correlation analysis, there is usually a reference sequence (also called the parent sequence) and several comparison sequences (also called subsequences). By calculating the correlation coefficient between the comparison sequence and the reference sequence, the similarity or correlation between them can be evaluated, and then the degree of correlation between each scheme and the ideal scheme can be determined.

[0045] (6) The graph neural network is trained based on the comprehensive evaluation results between each scheme and the ideal scheme, as well as the corresponding graph structure of the power energy system.

[0046] like Figure 2 As shown, it is a second flow chart of the multi-dimensional evaluation method of the electric energy system of this application, such as Figure 3 The figure is a schematic diagram of the structure of the multi-dimensional evaluation method of the electric energy system of the present application. It may include: S201, select five power generation technologies as research objects, and obtain basic power generation related parameters of different power generation technologies.

[0047] In actual applications, the basic power generation-related parameters obtained may be different according to different power generation technologies. Taking photovoltaic, wind power, hydropower, gas and coal as five representative power generation technologies, the specific basic power generation-related parameters can be the installed capacity and chip area of ​​photovoltaic power generation units; the wind turbine composition, total installed capacity, annual average wind speed, and capacity factor of the wind farm; the installed capacity of the hydropower station; the installed capacity and plant power consumption rate of the gas-fired power generation units; the installed capacity and coal consumption of the coal-fired power generation units. The corresponding basic power generation-related parameters can be derived from public data. As an example, the wind farm consists of 1.5MW wind turbines with a total installed capacity of 48 MW, the annual average wind speed at the hub height of the wind farm is 5.59 m / s, and the capacity factor of the wind farm is 19.69%; the installed capacity of the photovoltaic power generation unit is 5 MW, and the chip area is 77.36 cm 2 ; The installed capacity of coal-fired power generation units is 600 MW, using supercritical pressure technology, and the coal consumption is 200.15 t / h; the installed capacity of gas-fired power generation units is 600 MW, and the power consumption rate is 5.05%; the installed capacity of hydropower stations is 85 MW. Because this type of data has the characteristics of large spatial span, diversified technology, prominent differences, and complex environment, the specific data acquisition method can be confirmed according to the specific data situation.

[0048] S202, calculating three power generation evaluation indicators of five power generation technologies based on basic power generation related parameters.

[0049] like Figure 4 As shown, this is a schematic diagram of the model of the multi-dimensional evaluation method of the power energy system.

[0050] In this embodiment, the energy value sustainability index, power generation efficiency and life cycle cost are selected as three power generation evaluation indicators. In practical applications, in addition to power generation efficiency, the energy value sustainability index and life cycle cost need to be calculated based on power generation related parameters.

[0051] It should be noted that power generation efficiency refers to the ratio of effectively utilized energy to total input energy in the process of converting fuel or other energy into electrical energy. Power generation efficiency is one of the important indicators to measure the efficiency of power plants or power systems, and is directly related to the economy and environmental protection of energy utilization. The energy value sustainability index is an indicator used to evaluate the degree of environmental sustainability of the research object. It is usually calculated through energy value analysis theory, reflecting the ratio of the energy value output rate to the environmental load rate of the research object during the complete operation cycle. The higher the energy value sustainability index, the less pressure the research object has on the environment while efficiently utilizing energy. The life cycle cost refers to the sum of all costs related to procurement, maintenance, operation, disposal, etc. incurred throughout the life cycle. For power generation projects, the life cycle cost is one of the important indicators for evaluating economic efficiency.

[0052] S203, based on the energy value analysis theory, draw an energy value flow chart.

[0053] It should be noted that the basic concepts of energy value analysis theory mainly include: (1) Energy value: refers to the amount of another energy directly or indirectly consumed by a certain energy or substance during its production process. Energy value is a relative concept that depends on the source and quality of energy. Generally, the energy value of various energies is measured based on solar energy, which is called solar energy value. (2) Energy value conversion rate: refers to the amount of solar energy value required to produce a unit of energy or substance. The energy value conversion rate reflects the quality and scarcity of energy or substance. The higher the energy value conversion rate means higher quality and lower renewability. (3) Energy value input-output ratio: refers to the ratio of the energy value output of the system to the energy value input of the system. The energy value input-output ratio reflects the energy value efficiency of the system. The higher the energy value input-output ratio means the higher energy value return. (4) Energy value self-support rate: refers to the ratio of the energy value generated within the system to the energy value input from the outside of the system.

[0054] The input energy value of the energy system can include the energy value R of local renewable energy, the energy value F of social and economic input (including operation and maintenance, manpower, and assets), and the energy value N of input non-renewable energy.

[0055] The energy value Y of the energy product produced by the energy system satisfies:

[0056] The energy conversion rate is calculated by dividing the solar energy value of a unit substance by the energy it contains, with the unit of solar joules / joule, recorded as sej / J. In fact, the energy flow of the ecological and economic system is the flow and transformation of energy from large quantity to small quantity and from low quality to high quality, and the corresponding conversion rate also increases accordingly.

[0057] Emergy Sustainability Index It is the ratio of the system's energy output rate to the environmental load rate. As shown below:

[0058] in It is the environmental load rate of the system, which is the ratio of the energy value of non-renewable energy input to the energy value of renewable energy input. It is an indicator to measure the impact of production activities on the environment. The larger the value of this indicator, the greater the environmental pressure. It is the energy output rate of the system, which is the ratio of the system's output energy value to the economic input energy value. The economic input energy value includes fuel, various means of production and services. The higher the energy output rate, the more output energy value can be produced with the same economic input energy value, that is, the higher the production efficiency.

[0059]

[0060] Emergy analysis is based on energy value, which converts different types of incomparable energy in an ecological system or economic ecosystem into energy values ​​of the same standard for analysis, so as to evaluate its status and role in the system.

[0061] Emergy analysis theory measures and compares the value of different energies or materials through the energy conversion rate (the solar energy value consumed per unit of energy or material). According to the characteristics of various power generation methods, the corresponding energy flow charts can be drawn using the energy analysis theory.

[0062] In practical applications, the following methods can be used to draw an energy flow chart: (1) Determine system boundaries and scope Define the scope of the system to be analyzed, i.e. what parts need to be included in the analysis diagram. For example, it could be a factory, a building, an ecosystem, etc.

[0063] (2) Identify energy sources and energy flows Identify the major energy sources (e.g., electricity, fuel, solar, etc.) and energy flow paths in the system.

[0064] (3) Identify energy conversion and storage nodes Find the nodes in the system where energy is converted and stored, such as devices, machines, processes, etc. These nodes can be used as key parts in the diagram.

[0065] (4) Draw nodes Draw the identified energy conversion and storage nodes on the graph. In practical applications, nodes can be represented by shapes such as boxes and circles, and the node names are labeled.

[0066] (5) Drawing energy flow Arrows are used to represent the flow of energy between different nodes, and the direction of the arrows indicates the direction of energy flow. The thickness of the arrows can be adjusted according to the size of the energy flow.

[0067] (6) Mark the energy type and size Label the type of energy (e.g., electrical energy, thermal energy) and the magnitude (e.g., kilowatt-hours, joules, etc.) next to the arrow.

[0068] (7) Indicates energy loss Energy losses are identified in the diagram by special symbols or colors.

[0069] By drawing an energy flow chart, the energy flow and conversion in the system can be clearly displayed, and possible energy loss points can be identified and optimized.

[0070] As an example, Figure 5 As shown in the figure, it is an energy value flow chart drawn based on the energy structure of China's power system. Figure 6 The figure shows the energy value flow chart of five power generation technologies. Through energy value analysis and energy value flow chart drawing, the basic energy value data of each power generation method is provided, which provides the necessary basis for subsequent standardization processing and comprehensive evaluation.

[0071] S204, standardizing the power generation evaluation indicators of the five power generation technologies.

[0072] In order to compare power generation evaluation indicators of different dimensions, such as energy value sustainability index, power generation efficiency and life cycle cost, different power generation evaluation indicators can be dimensionlessly processed.

[0073] In practical applications, the membership degrees of different power generation evaluation indicators can be calculated and the dimensions can be unified through the membership degrees.

[0074] For incremental indicators, that is, indicators with larger values, the better, such as energy sustainability index and power generation efficiency, the membership degree can be calculated according to the following formula:

[0075] For decreasing indicators, that is, indicators with smaller values, the better, such as life cycle cost, the membership degree can be calculated as follows:

[0076] in, represents the power generation evaluation index, Indicates the maximum value of the same power generation evaluation index, Indicates the minimum value of the same power generation evaluation index, represents the degree of membership; Indicates the scheme number, i.e. the sequence number of the power generation technology. and Indicates the serial number of the same power generation evaluation index, K is the sequence number in the calculation process, k It is the sequence number in the calculation result.

[0077] S205, determining an ideal solution based on the optimal values ​​of the three power generation evaluation indicators.

[0078] For the five power generation technologies, the optimal values ​​of the three power generation evaluation indicators are selected respectively. For the increasing indicators, the maximum value is selected, and for the decreasing indicators, the minimum value is selected. For each power generation technology, the combination of the three power generation evaluation indicators forms the corresponding ideal solution.

[0079] S206, calculating the grey correlation coefficient.

[0080] The grey correlation coefficient of each scheme under each power generation evaluation index can be calculated according to the following two formulas. The grey correlation coefficient can reflect the similarity between each scheme and the ideal scheme. The larger the grey correlation coefficient, the closer it is to the optimal index:

[0081]

[0082] in, Indicated in The grey correlation coefficient of the scheme under each indicator reflects the closeness between the performance of the scheme on the indicator and the ideal scheme. Indicates the minimum difference between the given reference sequence and the comparison sequence. Indicates the maximum difference between the given reference sequence and the comparison sequence. Represents the resolution coefficient.

[0083] S207, conduct a comprehensive evaluation of multiple plans.

[0084] It should be noted that in this application, for any power generation technology, each indicator combination corresponds to a solution. Specifically, for each power generation technology (such as photovoltaic, wind power, hydropower, gas and coal, etc.), multiple indicators (such as energy value sustainability index, power generation efficiency and life cycle cost) can be evaluated. Each power generation technology will have a specific value for each indicator, and the combination of these values ​​will form a comprehensive evaluation of the power generation technology.

[0085] Comprehensively evaluate each plan by weighted summing up each The comprehensive evaluation value obtained is used to get the grey correlation coefficient ranking of the comprehensive performance of each solution. The calculation formula is as follows:

[0086]

[0087] in, It represents the value of the ideal solution on a certain power generation evaluation index. Indicates The value of a scheme on a certain power generation evaluation index, The ideal solution and The comprehensive evaluation result value of each scheme is Indicates The weight of each power generation evaluation index, that is, the importance of each power generation evaluation index to the comprehensive performance of the scheme, can be given by the decision maker based on his / her willingness and experience. The ideal solution is The value of the power generation evaluation index is It represents the standardized value of different schemes under each power generation evaluation index. express and The calculation formula of grey relational degree is: Characterization The right side of the equation.

[0088] In addition, in the traditional grey correlation analysis method, it is usually assumed that the weights of various power generation evaluation indicators are equal.

[0089] S208, using a graph neural network to learn the comprehensive evaluation result values ​​of the various power generation technologies obtained after processing by the grey correlation analysis method, to obtain a trained graph neural network for multi-dimensional evaluation of the electric power energy system.

[0090] Graph Neural Network (GNN) is a neural network specially designed to process graph data. In the power system, due to its non-Euclidean structure, the power system can be naturally represented as a graph. It consists of vertices and edges. The vertex represents the object of study, and the edge represents the relationship between two objects.

[0091] In practical applications, when using graph neural networks for evaluation, the input and output can be defined as follows: 1. Input (1) Graph structure: The structure of the graph mainly involves vertices (nodes) and edges, where vertices represent evaluation objects, such as different power generation technologies or energy systems, and edges represent the relationship or connection between vertices, such as the mutual influence between different technologies or the association between data.

[0092] (2) Node feature vector: The input features are multi-dimensional indicators of each node, such as energy sustainability index, power generation efficiency, life cycle cost, etc. Specifically, these feature vectors can include standardized values ​​of each power generation technology on different indicators.

[0093] (3) Adjacency matrix: The adjacency matrix is ​​used to represent the connection relationship between nodes in a graph. The elements in the adjacency matrix can represent whether there is an edge between two nodes and its weight.

[0094] 2. Output (1) Node embedding vector: Graph neural networks generate embedded representations of each node through convolution operations. These embedded representations contain the feature information of the node and its neighboring nodes.

[0095] (2) Comprehensive evaluation results: The comprehensive evaluation result is used as the output value, and the node embedding vector is further processed, such as a fully connected layer or a regression layer, to obtain the final comprehensive evaluation result. The output comprehensive result can be a comprehensive score or ranking of each power generation technology to evaluate its overall performance.

[0096] In practical applications, a graph can be represented by G=(V,E,A), where each vertex is associated with a size The eigenvector of , V, E, and A represent the vertex set, edge set, and adjacency matrix, respectively. According to the directionality of the edges in the graph, the graph can be divided into directed graphs and undirected graphs. According to whether each edge has a weight, it can be divided into weighted graphs and unweighted graphs. According to whether there are isolated vertices in the graph, it can also be divided into connected graphs and disconnected graphs.

[0097] GCN (Graph Convolutional Network) is a specific type of GNN (Graph Neural Network). Compared with traditional GNN networks, it has the advantages of simple and effective structure, explainable information propagation, and stronger robustness. The main idea is to obtain feature information from all neighbors of each node, and use the aggregation function to aggregate its own feature information with the neighbor feature information to update its own feature information. This operation is performed on all nodes, and finally the average value is input into a neural network. The propagation rule of each layer of GCN is:

[0098] in, is a nonlinear activation function, is the degree matrix, is the trainable parameter matrix is an adjacency matrix with self-loops, where the degree matrix is ​​a diagonal matrix that can describe the degree of association between different nodes; The node itself is added to the adjacency matrix, so that in the message aggregation The characteristics of the node itself can also be considered.

[0099] During the model training process, a weighted loss function with the same variance uncertainty can be used. Multi-task learning is common in many deep learning tasks, mainly for optimization problems with multiple objectives. In order to solve the problem that the traditional multi-objective optimization method simply weights the loss of each individual task, the loss of the model is measured by the difference between the predicted value and the true value, and the uncertainty of the difference is weighted according to the model. The multi-task loss function is as follows:

[0100] in, Represents the noise observation parameter, and the model will assign corresponding weights to each task based on this parameter. represents the weights of different task losses, Indicates The noisy observation parameters of each task, Indicates Loss of a mission.

[0101] The energy sustainability evaluation of the electric energy system proposed in this application is a simplified model. In the future, it can also be based on specific time and space boundaries to conduct detailed research on the coupling and complementary relationship of different electric energy systems, that is, the energy sharing relationship in multi-input and multi-output energy systems. In general, this application can provide a comprehensive evaluation of energy, economic and environmental sustainability taking into account energy value for the future energy structure.

[0102] like Figure 7 FIG. 1 is a schematic diagram of a multi-dimensional evaluation system for an electric energy system proposed in this application, which may include: An acquisition module, used to acquire a graph structure of an electric energy system, a power generation evaluation index of each node in the graph structure, and a connection relationship between nodes in the graph structure; the graph structure of the electric energy system includes a plurality of nodes and edges connecting the plurality of nodes, and the nodes represent different power generation technologies; An evaluation module is used to input the graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure into the evaluation graph neural network to obtain a comprehensive evaluation result of the electric energy system; The evaluation graph neural network comprehensively evaluates multiple power generation evaluation indicators of different power generation technologies in the electric energy system based on the grey correlation coefficient; the grey correlation coefficient is determined according to the ideal scheme and the values ​​of each scheme on each power generation evaluation indicator; the ideal scheme is determined according to the optimal value of each power generation evaluation indicator, and each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies.

[0103] In some embodiments of the multi-dimensional evaluation system of the electric energy system of the present application, the training method of the evaluation graph neural network may include: Obtain power generation evaluation indicators for various power generation technologies; Conduct energy value analysis on various power generation technologies respectively and draw energy value flow charts corresponding to the power generation technologies; Standardize the power generation evaluation indicators to unify their dimensions; Determine the ideal solution based on the optimal values ​​of each power generation evaluation index; According to the grey correlation coefficient between the ideal scheme and the numerical values ​​of each scheme on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, the comprehensive evaluation result between each scheme and the ideal scheme is determined; each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies; The graph neural network is trained based on the comprehensive evaluation results between each scheme and the ideal scheme, as well as the corresponding graph structure of the power energy system.

[0104] It should be noted that in the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of each module is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another device, or some features can be ignored or not executed. The module described as a separate component may or may not be physically separated. The component displayed as a module may be a physical unit or multiple physical units, that is, it may be located in one place, or it may be distributed in multiple different places. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0105] In addition, each module in each embodiment of the present invention may be integrated into a processing unit, each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0106] An electronic device provided in an embodiment of the present application includes a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps of the multi-dimensional evaluation method of the electric energy system described in any of the above embodiments are implemented.

[0107] Another electronic device provided in the embodiment of the present application may also include: an input port connected to the processor, used to transmit multimodal data collected by an external acquisition device to the processor; and a display unit connected to the processor, used to display the processing results of the processor to the outside world; a communication module connected to the processor, used to realize the communication between the electronic device and the outside world. The display unit can be a display panel, a laser scanning display, etc.; the communication mode adopted by the communication module includes but is not limited to mobile high-definition link technology (HML), universal serial bus (USB), high-definition multimedia interface (HDMI), wireless connection (including wireless fidelity technology (WiFi), Bluetooth communication technology, low-power Bluetooth communication technology, and communication technology based on IEEE802.11s).

[0108] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-dimensional evaluation method of the electric energy system described in any of the above embodiments are implemented.

[0109] The computer-readable storage medium involved in the present application includes random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field.

[0110] For the description of the relevant parts of the multi-dimensional evaluation system for electric energy systems, electronic devices, and computer-readable storage media provided in the embodiments of the present application, please refer to the detailed description of the corresponding parts in the multi-dimensional evaluation method for electric energy systems provided in the embodiments of the present application, which will not be repeated here. In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0111] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-dimensional evaluation method for electric energy system, characterized in that: include: Obtain the graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure; The graph structure of the electric energy system includes a plurality of nodes and edges connecting the plurality of nodes, wherein the nodes represent different power generation technologies; The graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure are input into the evaluation graph neural network to obtain a comprehensive evaluation result of the electric energy system; The evaluation graph neural network performs a comprehensive evaluation on multiple power generation evaluation indicators of different power generation technologies in the electric energy system based on the grey correlation coefficient; The grey correlation coefficient is determined according to the ideal scheme and the values ​​of each scheme on each power generation evaluation index; the ideal scheme is determined according to the optimal value of each power generation evaluation index, and each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies.

2. According to claim 1, a multi-dimensional evaluation method for electric energy system is characterized in that: The training method of the evaluation graph neural network includes: Obtain power generation evaluation indicators for various power generation technologies; Conduct energy value analysis on various power generation technologies respectively and draw energy value flow charts corresponding to the power generation technologies; Standardize the power generation evaluation indicators to unify their dimensions; Determine the ideal solution based on the optimal values ​​of each power generation evaluation index; According to the grey correlation coefficient between the ideal scheme and the numerical values ​​of each scheme on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, the comprehensive evaluation result between each scheme and the ideal scheme is determined; each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies; The graph neural network is trained based on the comprehensive evaluation results between each scheme and the ideal scheme, as well as the corresponding graph structure of the power energy system.

3. According to claim 2, a multi-dimensional evaluation method for electric energy system is characterized in that: The method of determining the comprehensive evaluation results between each scheme and the ideal scheme based on the grey correlation coefficient between the values ​​of each scheme on each power generation evaluation index and the weight of each power generation evaluation index reflected in the energy value flow chart includes: in, It represents the value of the ideal solution on a certain power generation evaluation index. Indicates The value of a scheme on a certain power generation evaluation index, The ideal solution and The comprehensive evaluation result value of each scheme is The energy value flow chart reflects the The weight of each power generation evaluation index is The ideal solution is The value of the power generation evaluation index is It represents the standardized value of different schemes under each power generation evaluation index. express and Grey relational calculation formula.

4. According to claim 3, a multi-dimensional evaluation method for electric energy system is characterized in that: The obtaining of power generation evaluation indicators of multiple power generation technologies includes: Obtain basic power generation related parameters for various power generation technologies; According to the basic power generation related parameters, the energy value sustainability index and the whole life cycle cost are calculated, and the energy value sustainability index, the whole life cycle cost and power generation efficiency are used as power generation evaluation indicators.

5. A multi-dimensional evaluation method for electric energy system according to claim 4, characterized in that: The multiple power generation technologies include photovoltaic, wind, hydro, gas and coal; The basic power generation related parameters include: installed capacity and chip area of ​​photovoltaic power generation units; wind turbine composition, total installed capacity, annual average wind speed, and capacity factor of wind farms; installed capacity of hydropower stations; installed capacity and plant power consumption rate of gas-fired power generation units; installed capacity and coal consumption of coal-fired power generation units.

6. A multi-dimensional evaluation method for electric energy system according to claim 5, characterized in that: The standardization of power generation evaluation indicators includes: The membership degree of the power generation evaluation index is calculated as the index after the power generation evaluation index is unified in dimension.

7. A multi-dimensional evaluation method for electric energy system according to claim 6, characterized in that: The graph neural network is a graph convolutional network; The loss function used by the graph convolutional network is a multi-task loss function: ； in, is the multi-task loss function, is the weight of the loss of different tasks, is the noise observation parameter of the first task, is the noise observation parameter of the second task, is the loss of the first task, For the loss of the second task.

8. A multi-dimensional evaluation system for electric energy system, characterized in that: include: An acquisition module, used to acquire the graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure; The graph structure of the electric energy system includes a plurality of nodes and edges connecting the plurality of nodes, wherein the nodes represent different power generation technologies; An evaluation module is used to input the graph structure of the electric energy system, the power generation evaluation index of each node in the graph structure, and the connection relationship between the nodes in the graph structure into the evaluation graph neural network to obtain a comprehensive evaluation result of the electric energy system; The evaluation graph neural network performs a comprehensive evaluation on multiple power generation evaluation indicators of different power generation technologies in the electric energy system based on the grey correlation coefficient; The grey correlation coefficient is determined according to the ideal scheme and the values ​​of each scheme on each power generation evaluation index; the ideal scheme is determined according to the optimal value of each power generation evaluation index, and each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies.

9. A multi-dimensional evaluation system for electric energy system according to claim 8, characterized in that: The training method of the evaluation graph neural network includes: Obtain power generation evaluation indicators for various power generation technologies; Conduct energy value analysis on various power generation technologies respectively and draw energy value flow charts corresponding to the power generation technologies; Standardize the power generation evaluation indicators to unify their dimensions; Determine the ideal solution based on the optimal values ​​of each power generation evaluation index; According to the grey correlation coefficient between the ideal scheme and the numerical values ​​of each scheme on each power generation evaluation index, combined with the weight of each power generation evaluation index reflected in the energy value flow chart, the comprehensive evaluation result between each scheme and the ideal scheme is determined; each scheme is a scheme obtained by combining the power generation evaluation indicators of multiple power generation technologies; The graph neural network is trained based on the comprehensive evaluation results between each scheme and the ideal scheme, as well as the corresponding graph structure of the power energy system.

10. A multi-dimensional evaluation system for electric energy system according to claim 9, characterized in that: The method of determining the comprehensive evaluation results between each scheme and the ideal scheme based on the grey correlation coefficient between the values ​​of each scheme on each power generation evaluation index and the weight of each power generation evaluation index reflected in the energy value flow chart includes: in, It represents the value of the ideal solution on a certain power generation evaluation index. Indicates The value of a scheme on a certain power generation evaluation index, The ideal solution and The comprehensive evaluation result value of each scheme is The energy value flow chart reflects the The weight of each power generation evaluation index is The ideal solution is The value of the power generation evaluation index is It represents the standardized value of different schemes under each power generation evaluation index. express and Grey relational calculation formula.

11. A multi-dimensional evaluation system for electric energy system according to claim 10, characterized in that: The obtaining of power generation evaluation indicators of multiple power generation technologies includes: Obtain basic power generation related parameters for various power generation technologies; According to the basic power generation related parameters, the energy value sustainability index and the whole life cycle cost are calculated, and the energy value sustainability index, the whole life cycle cost and power generation efficiency are used as power generation evaluation indicators.

12. A multi-dimensional evaluation system for electric energy system according to claim 11, characterized in that: The multiple power generation technologies include photovoltaic, wind, hydro, gas and coal; The basic power generation related parameters include: installed capacity and chip area of ​​photovoltaic power generation units; wind turbine composition, total installed capacity, annual average wind speed, and capacity factor of wind farms; installed capacity of hydropower stations; installed capacity and plant power consumption rate of gas-fired power generation units; installed capacity and coal consumption of coal-fired power generation units.

13. A multi-dimensional evaluation system for electric energy system according to claim 12, characterized in that: The standardization of power generation evaluation indicators includes: The membership degree of the power generation evaluation index is calculated as the index after the power generation evaluation index is unified in dimension.

14. A multi-dimensional evaluation system for electric energy system according to claim 13, characterized in that: The graph neural network is a graph convolutional network; The loss function used by the graph convolutional network is a multi-task loss function: ； in, is the multi-task loss function, is the weight of the loss of different tasks, is the noise observation parameter of the first task, is the noise observation parameter of the second task, is the loss of the first task, For the loss of the second task.

15. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, used to implement the steps of the multi-dimensional evaluation method of the electric energy system as claimed in any one of claims 1 to 7 when executing the computer program.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the multi-dimensional evaluation method for an electric energy system as claimed in any one of claims 1 to 7 are implemented.

Images