New energy station full life cycle dynamic evaluation method based on electric power spot market

Abstract

The invention relates to a new energy station full life cycle dynamic evaluation method based on an electric power spot market. The method comprises the steps of obtaining electric power spot market information; constructing a plurality of quantification factors based on the electric power spot market information; based on the quantitative factor, performing dynamic analysis on the power generation amount and the electricity price of the new energy station in the full life cycle to obtain a power generation amount analysis result and an electricity price analysis result; and based on the generating capacity analysis result and the electricity price analysis result, carrying out full-life-cycle dynamic technical and economic evaluation on the new energy station according to a preset technical and economic evaluation process. A series of targeted factors are constructed through electric power spot market information, the factors are fused into a dynamic analysis model of electric quantity and electricity price, and accurate calculation and deep analysis are performed by using a neural network, an artificial intelligence algorithm and a related professional model. Therefore, the technical effect of carrying out dynamic technical economic evaluation on the full life cycle of the power generation project is achieved, and the electric quantity and electricity price fluctuation conditions at different stages can be accurately predicted.

Description

Technical Field

[0001] The present invention belongs to the technical field of renewable energy power generation, and in particular, relates to a method, system, computer equipment and storage medium for dynamic evaluation of the entire life cycle of a renewable energy station based on a power spot market. Background Art

[0002] One of the core technical and economic evaluation methods of existing power generation projects is to evaluate the electricity cost benefits of power stations. The electricity cost can be evaluated in two dimensions: electricity quantity and electricity price.

[0003] However, there are some problems with the existing technical and economic evaluation methods for new energy projects. Taking wind power projects as an example, the analysis and calculation of electricity is limited to the analysis and calculation of meteorological data of wind speed and light, and does not consider the impact of more latitude meteorological data such as temperature, cloud cover, rainfall, etc., nor does it consider the impact of power generation station distribution, power grid transmission capacity, and power load distribution on power generation. It also lacks the impact of new energy stations participating in the power spot market on power generation restrictions.

[0004] In the existing technical and economic evaluation, the electricity price data is calculated using static benchmark electricity price data. However, in the electricity spot market, electricity prices fluctuate in real time. Using this calculation method will result in a significant deviation between the obtained electricity price and the price during the actual operation of the station throughout its life cycle.

[0005] In the existing technical and economic evaluation, the policies for the development of new energy stations can only be evaluated at a certain stage, and dynamic adjustments cannot be made according to policy changes, and the evaluation lacks flexibility.

[0006] In view of this, there is an urgent need for an innovative, comprehensive and dynamic technical and economic evaluation method to adapt to the development needs of renewable energy power generation in the electricity spot market environment, accurately evaluate the benefits and risks of power generation projects, and provide a scientific basis for investment decisions, operation management, etc. Summary of the invention

[0007] Based on this, it is necessary to provide a dynamic evaluation method, system, computer equipment and storage medium for the entire life cycle of new energy stations based on the electricity spot market, which can comprehensively and dynamically conduct technical and economic evaluations to address the above technical problems.

[0008] In the first aspect, the present application provides a dynamic evaluation method for the entire life cycle of a new energy station based on the electricity spot market, including:

[0009] S1: Obtain electricity spot market information, including: policy documents, information disclosed by market operating institutions, electricity market historical data, primary energy price data, power grid data and new energy station data;

[0010] S2: Based on the electricity spot market information, multiple quantitative factors are constructed, including:

[0011] S21: Construct policy factors based on policy documents;

[0012] S22: Construct market maturity factors based on information disclosed by market operating institutions;

[0013] S23: Based on the power grid data and new energy station data, construct the power station transmission risk factor and power load distance factor;

[0014] S24: Based on the historical data of the electricity market and combined with historical meteorological data, meteorological factors are constructed;

[0015] S25: Construct primary energy price factors based on primary energy price data;

[0016] Among them, the policy factor is used to quantify the impact of policies on new energy projects; the market maturity factor is used to quantify the degree of marketization at different stages of the development of the electricity spot market; the power plant transmission risk factor is used to quantify the difficulty of new energy sites in transmitting electricity to the connected power grid; the power load distance factor is used to quantify the closeness of the supply and demand relationship between new energy sites and power loads; the meteorological factor is used to quantify the impact of meteorology on power generation, transmission capacity and power load; the primary energy price factor is used to quantify the comprehensive impact of primary energy price fluctuations on power generation and electricity prices;

[0017] S3: Based on the quantitative factors, the power generation and electricity price of the new energy station in the whole life cycle are dynamically analyzed to obtain the power generation analysis results and electricity price analysis results;

[0018] S4: Based on the power generation analysis results and electricity price analysis results, a dynamic technical and economic evaluation of the new energy station throughout its life cycle is conducted according to the preset technical and economic evaluation process.

[0019] In the second aspect, the present application also provides a dynamic evaluation system for the entire life cycle of a new energy station based on the electricity spot market, including:

[0020] The data acquisition module is used to obtain electricity spot market information, including: policy documents, information disclosed by market operating institutions, electricity market historical data, primary energy price data, power grid data and new energy station data;

[0021] The factor construction module is used to construct multiple quantitative factors based on the electricity spot market information, including: constructing policy factors based on policy documents; constructing market maturity factors based on information disclosed by market operating institutions; constructing power plant transmission risk factors and power load distance factors based on power grid data and new energy station data; constructing meteorological factors based on historical electricity market data combined with historical meteorological data; and constructing primary energy price factors based on primary energy price data.

[0022] The electricity quantity and electricity price analysis module is used to dynamically analyze the power generation and electricity price of the new energy station throughout its life cycle based on quantitative factors, and obtain the power generation analysis results and electricity price analysis results;

[0023] Dynamic technical and economic evaluation module, which is used to conduct dynamic technical and economic evaluation of the new energy station throughout its life cycle based on the power generation analysis results and the electricity price analysis results according to the preset technical and economic evaluation process;

[0024] Among them, the policy factor is used to quantify the impact of policies on new energy projects; the market maturity factor is used to quantify the degree of marketization at different stages of development of the electricity spot market; the power plant transmission risk factor is used to quantify the difficulty of new energy sites in transmitting electricity to the connected power grid; the power load distance factor is used to quantify the closeness of the supply and demand relationship between new energy sites and power loads; the meteorological factor is used to quantify the impact of meteorology on power generation, transmission capacity and power load; the primary energy price factor is used to quantify the comprehensive impact of primary energy price fluctuations on power generation and electricity prices.

[0025] In a third aspect, the present application also provides a computer device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a dynamic evaluation method for the entire life cycle of a new energy station based on the electricity spot market as described in the first aspect is implemented.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for dynamic evaluation of the entire life cycle of a new energy station based on the electricity spot market as described in the first aspect.

[0027] The above-mentioned method, system, computer equipment and storage medium for dynamic evaluation of the whole life cycle of a new energy station based on the electricity spot market, by obtaining policy documents, market operation information, electricity market data, meteorological data, primary energy price data and power grid data from the electricity spot market, constructs a series of targeted factors, such as policy factors, market maturity factors, power station transmission risk factors, etc., integrates these factors into the dynamic analysis model of electricity quantity and electricity price, and uses neural networks, artificial intelligence algorithms and related professional models (such as TGARCH-Vi neCopula model, etc.) for precise calculation and in-depth analysis, so as to achieve the technical effect of dynamic technical and economic evaluation of the whole life cycle of power generation projects, accurately predict the fluctuations of electricity quantity and electricity price at different stages, comprehensively evaluate the impact of multiple factors such as policies, markets, natural environment, and power grid conditions on the economic benefits of power generation stations, and provide scientific, accurate and dynamic basis for project investment decisions, operation management, market transactions, etc., and effectively improve the adaptability and competitiveness of power generation projects in the complex and changeable electricity spot market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A schematic diagram of a flow chart of a method for dynamic evaluation of the entire life cycle of a new energy station based on the electricity spot market provided by the present invention;

[0030] Figure 2 A structural schematic diagram of a full life cycle dynamic evaluation method system for a new energy station based on the electricity spot market provided by the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] refer to Figure 1 , which presents a flow chart of a method for dynamic evaluation of the entire life cycle of a new energy station based on the electricity spot market provided by the present application, the method comprising the following steps:

[0033] S1: Obtain electricity spot market information, which includes: policy documents, information disclosed by market operating institutions, electricity market historical data, primary energy price data, power grid data and new energy station data.

[0034] Specifically, in order to obtain policy documents, detailed collection of policies and regulations related to the electricity spot market and new energy development issued by the national, local governments and relevant energy management departments can be used. These policies can cover adjustments to new energy subsidy policies, market access rules, restrictions on power production due to environmental protection requirements, and other aspects. For example, the new energy subsidy reduction policy will directly affect the expected revenue of new energy sites, and it is necessary to accurately interpret key information such as the time nodes for changes in subsidy standards and the extent of subsidy reduction in the policy.

[0035] In order to obtain information disclosed by market operators, we can obtain information such as market trading rules details, market entity registration status, statistical data on trading volume and trading prices, market trading products and trading schedules from power market operators. This information helps us understand the current trading activity, competition situation and liquidity of various trading products in the spot power market.

[0036] To obtain historical data on the electricity market, we can collect transaction data on the electricity spot market in the past few years, including electricity price fluctuations in different periods, transaction volume trends of different power types, historical data on electricity supply and demand balance in various regions, etc. Through in-depth analysis of these historical data, we can find the seasonal and cyclical fluctuation patterns of the electricity market.

[0037] For obtaining primary energy price data, we can collect market price data of primary energy such as coal, natural gas, and oil, including the trend of international and domestic market prices, price differences in different regions, and the relationship between price fluctuations and the macroeconomic environment and geopolitical factors. This is because changes in primary energy prices will indirectly affect the cost of electricity production, and thus affect the competitiveness of new energy sites in the power market and the electricity price formation mechanism.

[0038] In terms of obtaining grid data, we can obtain grid topology information, including substation location, transmission line length, transmission line capacity, etc.; grid operation data, such as grid load rate, grid congestion, grid loss data, etc. at different time periods; and grid planning information to understand future grid expansion and upgrade plans. These data are crucial for evaluating the feasibility and stability of power transmission after new energy stations are connected to the grid.

[0039] For obtaining data on new energy stations, we can obtain the installed capacity, equipment parameters (such as wind turbine model, conversion efficiency of photovoltaic modules, etc.), geographic location information (latitude and longitude, altitude, etc.), and historical operation data of the stations (power generation time series data, equipment failure rate data, operation and maintenance cost data, etc.). These data are the basis for analyzing the power generation characteristics and operation status of new energy stations themselves.

[0040] S2: Based on the electricity spot market information, multiple quantitative factors are constructed, including:

[0041] S21: Construct policy factors based on policy documents.

[0042] Specifically, we can deeply analyze the direction and degree of influence of various clauses in policy documents on new energy sites. For example, if the policy encourages the development of new energy and grants land use concessions, then the corresponding positive weight should be given when constructing the policy factor; if the policy puts forward higher requirements for the grid connection standards of new energy sites and has strict punishment measures, it is necessary to consider giving a certain negative weight. Through comprehensive consideration of multiple influencing factors in the policy, the relative importance weight of each factor can be determined by using hierarchical analysis or expert scoring methods, so as to construct a quantitative policy factor that can accurately reflect the comprehensive impact of the policy.

[0043] S22: Construct a market maturity factor based on information disclosed by market operating institutions.

[0044] Specifically, the market maturity can be evaluated from multiple dimensions, such as the degree of perfection of market trading rules, the number and diversity of market participants, and the rationality of the market price formation mechanism. For example, the more detailed, transparent and fair the trading rules are, the more diverse the types of market participants are (including power generation companies, power sales companies, power users and other entities actively participating), and the price formation mechanism can fully reflect the power supply and demand relationship and cost factors, the higher the market maturity. A multi-indicator comprehensive evaluation method can be used to set corresponding evaluation indicators and weights for each dimension, and finally construct a market maturity factor.

[0045] S23: Based on the power grid data and new energy station data, construct the power station transmission risk factor and power load distance factor.

[0046] Specifically, the transmission risk factor of the power station can be constructed by considering factors such as the length of the transmission line between the new energy station and the grid connection point, the matching degree between the line capacity and the station installed capacity, the frequency and duration of grid congestion, etc. If the transmission line is long and the capacity is relatively small, or the grid congestion is more serious, then the power station transmission risk is higher, and a larger risk value should be reflected when constructing the factor. By establishing a transmission risk assessment model, these influencing factors can be used as input variables to output the power station transmission risk factor.

[0047] The power load distance factor can be constructed based on the geographical distance between the new energy site and the main power load center, the regional power supply and demand balance and other factors. Generally speaking, the closer the distance to the power load center is and the greater the power demand in the region is and the relatively insufficient supply is, the closer the supply and demand relationship between the new energy site and the power load is, and the higher the value of the power load distance factor should be. The degree of correlation between the two is calculated by combining power supply and demand data through geographic information system (GIS) technology, thereby determining the quantitative value of this factor.

[0048] S24: Construct meteorological factors based on historical electricity market data and historical meteorological data.

[0049] Specifically, the correlation between historical meteorological data (such as light intensity, wind speed, temperature, precipitation, etc.) and historical data of the electricity market (power generation, electricity price) can be analyzed. For example, light intensity and wind speed directly affect photovoltaic power generation and wind power generation, while too high or too low temperature may affect the efficiency of power generation equipment, and precipitation may cause equipment failure or damage to transmission lines. By establishing a meteorological-power generation-electricity price correlation model, the influence coefficient of meteorological factors on power generation and electricity prices is determined, and then meteorological factors are constructed. For example, in a season with abundant wind resources, an increase in wind power generation may lead to a decrease in market electricity prices, so this negative correlation should be considered when constructing meteorological factors.

[0050] S25: Construct a primary energy price factor based on primary energy price data.

[0051] Specifically, we can study the transmission mechanism between primary energy price fluctuations and electricity production costs, power generation companies' bidding strategies, and electricity prices in the power market. When primary energy prices rise, the power generation costs of traditional thermal power companies increase, which may increase quotations, thereby affecting the electricity price level in the power market, and also changing the relative competitiveness of new energy sites in the market. By establishing a primary energy price-electricity cost-electricity price correlation model, we analyze the comprehensive impact of primary energy price changes on the power generation of new energy sites (such as changes in market share caused by changes in electricity prices, which in turn affects power generation) and electricity prices (the impact of market electricity price linkage), and construct a primary energy price factor.

[0052] S3: Based on quantitative factors, a dynamic analysis is conducted on the power generation and electricity price of the new energy station throughout its life cycle to obtain power generation analysis results and electricity price analysis results.

[0053] Specifically, for power generation analysis: the constructed policy factors, market maturity factors, power plant transmission risk factors, power load distance factors, meteorological factors, etc. can be incorporated into the power generation prediction model. The model can be constructed based on historical data using time series analysis and machine learning algorithms (such as neural networks, support vector machines, etc.). For example, the light intensity and wind speed data in the meteorological factors are used as input variables, combined with the impact of other factors on the operating efficiency of power generation equipment, transmission stability, etc., to predict the power generation trend of new energy stations in different future time periods (short-term, medium-term, and long-term), and obtain the power generation analysis results, including the power generation value range and power generation fluctuations under different scenarios.

[0054] For electricity price analysis: the constructed quantitative factors can also be used to dynamically analyze the electricity prices of new energy sites throughout their life cycle in combination with the electricity market supply and demand model, power generation cost model, etc. Consider the impact of policy factors on subsidy policies, the impact of market maturity factors on the degree of market competition and price formation mechanism, and the transmission effect of primary energy price factors on electricity costs and market electricity prices. For example, in the stage of low market maturity, new energy sites may obtain higher subsidized electricity prices due to policy support; as the market maturity increases, subsidies decrease, and electricity prices are more affected by market supply and demand and cost factors. The model simulates the changes in electricity prices under different market environments and policy scenarios, and obtains electricity price analysis results, such as the average electricity price level and electricity price fluctuation range in different periods.

[0055] S4: Based on the results of power generation analysis and electricity price analysis, a dynamic technical and economic evaluation of the new energy station over its entire life cycle is conducted according to the preset technical and economic evaluation process.

[0056] Specifically, based on the market transaction volume in the power generation analysis results, the site power generation forecast data, and the market power price and site node power price forecast data in the power price analysis results, combined with the basic data of the power generation project, such as installed capacity, total project investment plan and fund raising plan. According to the standardized technical and economic evaluation index system, calculate the key financial indicators such as the internal rate of return of capital, the total investment rate of return ROI, the net profit rate of project capital ROE, the investment profit and tax rate, the kilowatt-hour cost LOC, the break-even point, and the annual equivalent utilization hours. By establishing a financial cash flow model, combining the power generation, power price data and cost data of different time periods, simulate the capital inflow and outflow of power generation projects throughout their life cycle, and evaluate the profitability, debt repayment ability and risk resistance of the project. Based on the evaluation results, a basis is provided for investment decisions of new energy stations in the early stages of the project, and the feasibility and return on investment of the project are judged; in the planning, design and construction stages, the station layout, equipment selection and capacity configuration are optimized; in the operation period, guidance is provided on the formulation of power production plans, adjustment of power market trading strategies, station technical transformation decisions, and mergers, acquisitions or sales of power stations, so as to achieve refined management and maximize benefits over the entire life cycle of new energy stations.

[0057] The above-mentioned dynamic evaluation method for the whole life cycle of new energy stations based on the electricity spot market obtains various information such as policy documents, information disclosed by operating institutions, historical data, energy price data, power grid and new energy station data covered by the electricity spot market, and then constructs multiple quantitative factors such as policy factors, market maturity factors, transmission risks and power load distance factors, meteorological factors, and primary energy price factors. Based on these quantitative factors, the power generation and electricity price of the whole life cycle of the new energy station are dynamically analyzed, and finally a dynamic technical and economic evaluation of the whole life cycle is carried out according to the preset technical and economic evaluation process. The technical effect achieved is that it can comprehensively and dynamically consider various influencing factors, accurately analyze the power generation and electricity price of new energy stations at different stages, so as to scientifically and accurately evaluate the economic benefits and technical feasibility of new energy stations throughout the whole life cycle, and provide a scientific basis for relevant project decisions.

[0058] In an optional embodiment, constructing a policy factor based on a policy document includes the following steps:

[0059] Assign different policy levels to each policy document, and set corresponding level coefficients for policy documents of different policy levels;

[0060] Using the lag effect panel model, based on the historical data of the electricity market, we quantitatively analyzed the time lag patterns and degrees of different policies from their introduction to their actual impact on new energy projects, and obtained the lag factors corresponding to policy documents of different policy levels.

[0061] Use text mining technology to extract keywords from policy documents and convert them into quantitative data; use system dynamics models to analyze the relationship between quantitative data and market installed capacity, market power generation, and market electricity prices, and use these relationships to establish policy-based prediction models for installed capacity, power generation, and electricity prices;

[0062] The policy factors are constructed based on the grade coefficient, lag factor, the policy prediction model for installed capacity, the policy prediction model for power generation and the policy prediction model for electricity price.

[0063] Specifically, the policy documents cover various laws, regulations, plans, subsidy policies and other text materials related to renewable energy power generation and the electricity market issued by the national, provincial and municipal levels.

[0064] In-depth analysis of the various clauses in the policy documents, extracting key information such as the average cost of power generation projects in the corresponding provinces and regions, unified pricing data, capacity electricity price data, installed capacity data, industrial distribution, national economic development data, electricity market reform measures, time-of-use electricity price policy, transmission and distribution price policy, capacity electricity price policy, energy storage policy, etc. The level coefficient is set according to the policy release level (national, provincial, and municipal), which can be 1, 0.5, and 0.25 respectively, and the lag factor is determined according to the nature of the policy (encouragement or constraint). The lag factor can be a numerical value, for example, the national level is set to 0.25, the provincial level is set to 0.5, and the municipal level is set to 1. The general equilibrium CGE model is used to simulate the comprehensive impact of economic policy changes on the supply and demand, price, industrial structure and other aspects of the electricity market, and the lag effect panel model is used to quantify the lag time and impact change curve of different policies based on historical data. The PMC index is constructed through system dynamics, and text mining technology is used to extract policy keywords and assign weights (the weight of keywords about encouragement is +1, and the weight of keywords about constraints is -1). A quantitative relationship model between energy policy and electricity market installed capacity, power generation, and electricity prices is established, and finally integrated to form policy factors.

[0065] In an optional embodiment, constructing a market maturity factor based on information disclosed by a market operation agency includes the following steps:

[0066] Obtain market operation information from information disclosed by market operation institutions, determine the market operation stage through market operation information, and set corresponding stage factors for different operation stages according to preset rules;

[0067] Calculate the ratio of installed capacity of power plants participating in the electricity spot market to the installed capacity of all power plants r 1 , calculate the ratio of the power generation of power stations participating in the power spot market to the power generation of all power stations r 2 , based on the ratio r 1and ratio r 2 Construct the marketization degree factor of power plants;

[0068] Calculate the ratio of the electricity load participating in the electricity spot market to the total electricity load capacity r 3 , calculate the ratio of the number of electricity loads participating in electricity spot trading to the total number of electricity loads r 4 , based on the ratio r 3 and ratio r 4 Construct the marketization degree factor of electricity load;

[0069] The market maturity factor is constructed based on the stage factor, the power station marketization degree factor and the electricity load marketization degree factor.

[0070] Specifically, the information disclosed by market operating institutions includes real-time or periodic summary information such as the trading rules of the electricity market, operating hours, trading data of each participant, and market capacity.

[0071] The current operation stage of the market is accurately determined from the information disclosed by the market operation institutions, such as not yet in trial operation, simulated trial operation, power adjustment trial operation, settlement trial operation, formal operation, etc., and the stage factor is set accordingly. The stage factor can be expressed as a numerical value. For example, the stage factor of the stage of not yet in trial operation is 0, the stage factor of the stage of simulated trial operation is 0.01, the stage factor of the stage of power adjustment trial operation is 0.015, and the stage factor of the stage of settlement trial operation is The stage factor of the formal operation stage is 1. Calculate the marketization degree factor of the power station, that is, the ratio of the installed capacity of the power station participating in the electricity spot market to the installed capacity of all power stations in a province, and the ratio of the power generation of the power station participating in the electricity spot market to the power generation of all power stations in a province. For the marketization degree factor of the electricity load, calculate a1 = the ratio of the power load participating in the electricity spot market to the total power load capacity of a province (or a region) and a2 = the ratio of the number of power loads participating in the electricity spot transaction to the total number of power loads in a province, and combine the two to determine the marketization degree of the power load. Considering the key position of the power load side in the market maturity assessment, give it a greater weight. The marketization degree data of different provinces are normalized, and the development trend of the future marketization degree of the same power market is derived based on historical electricity price data through data mining and similarity analysis technology to construct a market maturity factor.

[0072] In an optional embodiment, based on the power grid data and the new energy station data, a power station transmission risk factor is constructed, including:

[0073] Based on the power grid data, the flow of the existing power grid is analyzed to obtain the blocking probability distribution of the power station nodes; based on the blocking probability distribution, the site selection of the power station is evaluated to obtain the evaluation result of the site selection of the power station;

[0074] Based on the data of new energy stations, calculate the ratio of the transmission capacity of the grid node line connected to the power station to the installed capacity of the power station. 5 , based on the ratio r 5 Construct node transmission risk factors;

[0075] Based on the data of new energy stations, the historical power generation time series data of all new energy stations in the power grid nodes connected to the new energy stations are collected, and after normalization, the total power generation time series data within the power grid node range is used as the benchmark to perform similarity analysis on the power generation curves of each power station to obtain the power generation homogeneity factor;

[0076] Based on the power grid data, the structural types of the power grid nodes where the new energy stations are located are classified; for different classified structural types, the corresponding initial average system availability index is configured according to the preset rules, and the initial average system availability index is corrected according to the new energy station data to obtain the actual average system availability index; based on the new energy station data, the historical fault data is obtained, and the ratio of the number of faults to the total number of faults of the power grid nodes where the new energy stations are located is calculated according to the historical fault data. 6 ; Actual average system availability index and ratio r based on different structural types of grid nodes 6 , construct the transmission fault factor;

[0077] The power plant transmission risk factor is constructed based on the site selection assessment results of the power station, the node transmission risk factor, the generation homogeneity factor and the transmission failure factor.

[0078] Specifically, the grid data includes the grid topology, transmission capacity of each node, historical flow data, fault records, etc., which are extracted by the grid company through interfaces or internal data systems. The new energy station data covers the station's installed capacity, geographical location, equipment parameters, historical power generation efficiency, operation and maintenance records, etc., which are summarized from the station's own operation management system and early construction materials.

[0079] First, the flow calculation is carried out, and the flow distribution of the existing power grid is simulated and analyzed using professional power system analysis software to obtain the blocking probability distribution data of each power station node, which is used to evaluate the rationality of the station selection. The node transmission risk factor is calculated, that is, the ratio of the transmission capacity of the power grid node line connected to the power station to the installed capacity of the power station. According to the voltage level of the power plant station, the voltage level of the provincial backbone network is investigated upward, and a maximum of three levels are investigated. The proportional relationship of the associated upper-level nodes is evaluated in a proportional manner. Based on the historical power generation time series data of all power stations in the power grid node connected to the power station, normalization is first performed to make the data in the same dimension, and then cluster analysis or curve fitting algorithm is used to perform similarity analysis on the power generation curve. The total power generation time series data within the node range is used as a benchmark to determine the power generation homogeneity factor of each station. The types of power grid nodes where the power station is located are classified (radial, ring, tree, mesh, hybrid, bus, star, etc.), and the corresponding average system availability index is configured according to the reliability theoretical model of different structural types. The ASAI is calculated based on historical data, and the historical data of relevant power generation stations and power grid failures in the power grid nodes connected to the power station are collected. The ratio of the number of failures to the number of node failures is calculated by time period, and the probability distribution function of the transmission failure factor is constructed. The transmission risk factor of the power station is obtained by combining the above results.

[0080] In an optional embodiment, based on the power grid data and the new energy station data, constructing the distance factor of the power load includes the following steps:

[0081] Based on the data of new energy stations, the HHI is used to evaluate the concentration of power loads in the grid node area to obtain the concentration evaluation results; and the impedance of the transmission line between each independent power load and the new energy station is weighted to obtain the load impedance weighted value; based on the concentration evaluation results and the load impedance weighted value, the load concentration factor is constructed;

[0082] Based on the ratio of the total electric load of the area directly connected to the grid node connected to the new energy station to the installed capacity of the new energy station connected to the grid node 7 , construct the electricity intensity factor;

[0083] Based on the load concentration factor and the power intensity factor, the distance factor of the power load is constructed.

[0084] Specifically, the grid data includes the grid topology, transmission capacity of each node, historical flow data, fault records, etc., which are extracted by the grid company through interfaces or internal data systems. The new energy station data covers the station's installed capacity, geographical location, equipment parameters, historical power generation efficiency, operation and maintenance records, etc., which are summarized from the station's own operation management system and early construction materials.

[0085] Calculate the power intensity, that is, the ratio of the total power load of the area directly connected to the grid node connected to the power station to be investigated to the installed capacity of the power station connected to the node (the power generation time series data is used for dynamic evaluation). According to the voltage level of the power plant, the voltage level of the provincial backbone network is investigated upward, and a maximum of three levels are investigated. Different weights are set for the associated nodes and the upper nodes, and the more directly connected, the higher the weight. Use the HHI index to evaluate the concentration of power load in the node area, obtain the impedance data of the transmission line between the power load and the power plant through the geographic information system, and perform weighted calculation to comprehensively obtain the power load distance factor.

[0086] In an optional embodiment, based on the historical data of the electricity market and in combination with the historical meteorological data, a meteorological factor is constructed, including:

[0087] Based on the historical data of the power market, the time series data of power generation in the power market is obtained, and the correlation analysis between the time series data of power generation in the power market and the historical meteorological data is carried out to obtain the factors affecting power generation;

[0088] Based on the historical data of the power market, the time series data of the power grid transmission capacity is obtained, and the correlation analysis of the time series data of the power grid transmission capacity and the historical meteorological data is carried out to obtain the influencing factors of the transmission capacity;

[0089] Based on the historical data of the power market, the time series data of power load is obtained, and the correlation analysis of the time series data of power load and the historical meteorological data is carried out to obtain the influencing factors of power load;

[0090] Meteorological factors are constructed based on the factors affecting power generation, transmission capacity and power load.

[0091] Specifically, the historical data of the electricity market involves the power generation, electricity consumption, electricity price change curves, electricity load data in different time periods, etc. in the past years.

[0092] Comprehensively collect time series data such as temperature, wind speed, precipitation, etc. in historical meteorological data, and classify precipitation data into three types: rainfall, snowfall, and others. In-depth analysis of temperature data, including characteristics such as average temperature, temperature drop amplitude, and temperature time change rate, while considering the probability distribution function of extreme weather, combined with the distribution characteristics of wind and solar resources in different provinces and regions, and the differential impact of different time periods (high wind month, low wind month, flood season, dry season, heating season, summer supply period, etc.). Using the data association analysis algorithm, the historical meteorological data is correlated with the existing power market power generation time series data to determine the impact coefficient of meteorological data on power generation; the correlation mining is carried out with the power grid transmission capacity time series data to obtain the impact weight of meteorological data on transmission capacity; the fitting analysis is carried out with the power load time series data to obtain the impact relationship of meteorological data on power load, and a meteorological factor model is constructed to predict the trend of power generation, transmission capacity, and power load changes under future meteorological conditions.

[0093] In an optional embodiment, constructing a primary energy price factor based on primary energy price data includes the following steps:

[0094] Based on the primary energy price data, obtain the changing pattern of the proportion of primary energy to energy consumption over time, and set the time series factor of the primary energy consumption proportion based on the changing pattern;

[0095] Based on the primary energy price data, the degree of dependence of different types of new energy stations on primary energy is obtained, and the weight time series factor of the power station type is set based on the degree of dependence;

[0096] Based on the time series factor of primary energy consumption proportion and the time series factor of power station type weight, the primary energy price factor is constructed.

[0097] Specifically, we will collect data on the price of primary energy such as coal, natural gas, and oil from different provinces and regions, and build a database of the correlation between primary energy and the electricity market that is suitable for the energy structure of the region. Set the time series factor of the proportion of primary energy consumption, and dynamically adjust it according to the changes in the consumption proportion of each primary energy in different periods; determine the time series factor of the weight of the power station type, taking into account the different degrees of dependence on primary energy by different types of stations such as thermal power, wind power, and photovoltaic power. Use multiple linear regression or neural network algorithms to conduct in-depth correlation analysis between these factors and the historical time series data of electricity market electricity and prices, determine the transmission coefficient matrix of primary energy prices and electricity market electricity load and electricity prices, and construct a primary energy price factor to predict the comprehensive impact of primary energy price fluctuations on electricity and prices during the life cycle of the power station.

[0098] In an optional embodiment, based on the quantitative factors, the power generation and electricity price of the new energy station throughout its life cycle are dynamically analyzed to obtain power generation analysis results and electricity price analysis results, including:

[0099] S31: Multi-factor integration step:

[0100] Aggregate policy factors, market maturity factors, power plant transmission risk factors, power load distance factors, meteorological factors, and primary energy price factors to obtain a historical comprehensive factor data set;

[0101] S32: Dynamic analysis steps of power generation:

[0102] Obtaining historical power generation time series data based on new energy station data, and using the historical power generation time series data to build a first quantitative analysis model integrating a neural network and an artificial intelligence algorithm; wherein the neural network and artificial intelligence algorithm in this step include LSTM and Transformer models;

[0103] Inputting the historical comprehensive factor data set into the first quantitative analysis model, training the quantitative analysis model, and obtaining a trained power generation prediction model;

[0104] According to different time periods, the real-time comprehensive factor data set is input into the trained power generation prediction model to calculate the power generation prediction values ​​of different time periods in the whole life cycle of the new energy station, forming the dynamic analysis results of power generation;

[0105] S33: Steps for dynamic analysis of electricity prices:

[0106] Obtain historical electricity price time series data based on new energy station data, and use the historical electricity price time series data to build a second quantitative analysis model that integrates a neural network and an artificial intelligence algorithm; wherein the neural network and artificial intelligence algorithm in this step include a CNN-LSTM model, a Transformer model, or an ARI MA-SSA-LSTM combination model;

[0107] Inputting the historical comprehensive factor data set into the second quantitative analysis model, training the quantitative analysis model, and obtaining a trained electricity price prediction model;

[0108] According to different time periods, the real-time comprehensive factor data set is input into the trained electricity price prediction model to calculate the electricity price forecast values ​​for different time periods in the entire life cycle of the new energy station, forming a dynamic analysis result of power generation.

[0109] Specifically, based on the analysis of new energy resources (such as wind energy resource assessment for wind power and light resource assessment for photovoltaic power, including the geographical location, topography, climate profile, meteorological station data, selection of representative meteorological stations, analysis of basic meteorological elements, theoretical annual power generation calculation and other data obtained in the early stage), policy factors, market maturity factors, power station transmission risk factors, power load distance factors, meteorological factors, primary energy price factors, etc. are fully integrated into the analysis model. Using the existing historical data (including historical time series data such as power generation of power stations, power grid transmission capacity, power load, etc.), according to different time periods (year, quarter, month, ten days, week, day, etc.), a dynamic analysis model of electricity consumption is constructed by integrating neural networks and artificial intelligence algorithms (such as LSTM or Transformer models). The LSTM model can effectively capture the long-term dependencies in time series data through its memory unit, and the Transformer model uses the multi-head attention mechanism to better handle the complex interactive relationship between multiple factors, and dynamically calculates the market transaction electricity and station power generation during the entire life cycle of the station, and obtains the power generation forecast curve and fluctuation range under different time periods, forming the power generation analysis results.

[0110] Based on the above multi-factor fusion, the existing historical electricity price time series data of the electricity market is used to build an electricity price dynamic analysis model that integrates neural networks and artificial intelligence algorithms (such as CNN-LSTM, Transformer model or ARI MA-SSA-LSTM combination model), and the TGARCH-Vi neCopula model is used to predict electricity market risks. In the CNN-LSTM model, the CNN part extracts the local features of the electricity price data, and the LSTM part processes the long-term dependencies on the time series; the Transformer model processes the complex relationship between multiple factors and electricity prices; the ARI MA-SSA-LSTM combination model combines the processing ability of the autoregressive moving average model (ARIMA) for linear relationships, the advantages of singular spectrum analysis (SSA) for data denoising and trend extraction, and the modeling ability of LSTM for nonlinear relationships. Through the multi-factor electricity price dynamic calculation model to process time series data, the market electricity price and station node electricity price in the entire life cycle of the station are dynamically analyzed, and the electricity price forecast values ​​and risk assessment indicators under different time periods are obtained to form the electricity price analysis results.

[0111] In an embodiment of the present application, a dynamic evaluation method for the entire life cycle of a new energy station based on the electricity spot market is provided. The method constructs multi-dimensional quantitative factors such as policies, market maturity, power plant transmission risks, power load distance, meteorology, and primary energy prices by comprehensively acquiring policy documents of the electricity spot market, information disclosed by operating agencies, various historical data, and power grid and station-related data. With the help of neural networks and artificial intelligence algorithms, these factors are integrated into a dynamic analysis model of power generation and electricity prices, and in-depth calculation and analysis are performed according to different time periods, thereby achieving an accurate and dynamic technical and economic evaluation effect for the entire life cycle of new energy stations. It can accurately predict the trends of power generation and electricity prices, comprehensively consider the influence of multiple factors, and provide a scientific basis for investment decisions, planning and construction, operation and management, and market trading strategy formulation of stations, effectively improving the comprehensive benefits and competitiveness of new energy stations in the complex and changeable electricity spot market environment, enabling them to better adapt to market changes and policy orientations, and achieve sustainable development and optimal resource allocation.

[0112] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0113] Based on the same inventive concept, the embodiment of the present application also provides a system for implementing the above-mentioned method for dynamic evaluation of the whole life cycle of a new energy station based on the electricity spot market. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the system for dynamic evaluation of the whole life cycle of a new energy station based on the electricity spot market provided below can be found in the above definition of a method for dynamic evaluation of the whole life cycle of a new energy station based on the electricity spot market, which will not be repeated here.

[0114] In an exemplary embodiment, Figure 2 As shown, a dynamic evaluation system for the whole life cycle of new energy stations based on the electricity spot market is provided, including:

[0115] The data acquisition module 201 is used to acquire the electricity spot market information, which includes: policy documents, information disclosed by market operating institutions, electricity market historical data, primary energy price data, power grid data and new energy station data.

[0116] The factor construction module 202 is used to construct multiple quantitative factors based on the electricity spot market information, including: constructing policy factors based on policy documents; constructing market maturity factors based on information disclosed by market operating institutions; constructing power station transmission risk factors and power load distance factors based on power grid data and new energy station data; constructing meteorological factors based on historical electricity market data combined with historical meteorological data; and constructing primary energy price factors based on primary energy price data.

[0117] The electricity quantity and electricity price analysis module 203 is used to dynamically analyze the power generation and electricity price of the new energy station throughout its life cycle based on quantitative factors, and obtain power generation analysis results and electricity price analysis results.

[0118] The dynamic technical and economic evaluation module 204 is used to conduct a dynamic technical and economic evaluation of the new energy station throughout its life cycle based on the power generation analysis results and the electricity price analysis results according to a preset technical and economic evaluation process.

[0119] Among them, the policy factor is used to quantify the impact of policies on new energy projects; the market maturity factor is used to quantify the degree of marketization at different stages of development of the electricity spot market; the power plant transmission risk factor is used to quantify the difficulty of new energy sites in transmitting electricity to the connected power grid; the power load distance factor is used to quantify the closeness of the supply and demand relationship between new energy sites and power loads; the meteorological factor is used to quantify the impact of meteorology on power generation, transmission capacity and power load; the primary energy price factor is used to quantify the comprehensive impact of primary energy price fluctuations on power generation and electricity prices.

[0120] Optionally, the factor construction module 202 includes a policy factor construction unit 2021, which is used to perform the following operations:

[0121] Assign different policy levels to each policy document, and set corresponding level coefficients for policy documents of different policy levels;

[0122] Using the lag effect panel model, based on the historical data of the electricity market, we quantitatively analyzed the time lag patterns and degrees of different policies from their introduction to their actual impact on new energy projects, and obtained the lag factors corresponding to policy documents of different policy levels.

[0123] Use text mining technology to extract keywords from policy documents and convert them into quantitative data; use system dynamics models to analyze the relationship between quantitative data and market installed capacity, market power generation, and market electricity prices, and use these relationships to establish policy-based prediction models for installed capacity, power generation, and electricity prices;

[0124] The policy factors are constructed based on the grade coefficient, lag factor, the policy prediction model for installed capacity, the policy prediction model for power generation and the policy prediction model for electricity price.

[0125] Optionally, the factor construction module 202 further includes a market maturity factor construction unit 2022, which is used to perform the following operations:

[0126] Obtain market operation information from information disclosed by market operation institutions, determine the market operation stage through market operation information, and set corresponding stage factors for different operation stages according to preset rules;

[0127] Calculate the ratio of installed capacity of power plants participating in the electricity spot market to the installed capacity of all power plants r 1 , calculate the ratio of the power generation of power stations participating in the power spot market to the power generation of all power stations r 2 , based on the ratio r 1 and ratio r 2 Construct the marketization degree factor of power plants;

[0128] Calculate the ratio of the electricity load participating in the electricity spot market to the total electricity load capacity r 3 , calculate the ratio of the number of electricity loads participating in electricity spot trading to the total number of electricity loads r 4 , based on the ratio r 3 and ratio r 4 Construct the marketization degree factor of electricity load;

[0129] The market maturity factor is constructed based on the stage factor, the power station marketization degree factor and the electricity load marketization degree factor.

[0130] Optionally, the factor construction module 202 further includes a power plant transmission risk factor construction unit 2023, which is used to perform the following operations:

[0131] Based on the power grid data, the flow of the existing power grid is analyzed to obtain the blocking probability distribution of the power station nodes; based on the blocking probability distribution, the site selection of the power station is evaluated to obtain the evaluation result of the site selection of the power station;

[0132] Based on the data of new energy stations, calculate the ratio of the transmission capacity of the grid node line connected to the power station to the installed capacity of the power station. 5 , based on the ratio r5 Construct node transmission risk factors;

[0133] Based on the data of new energy stations, the historical power generation time series data of all new energy stations in the power grid nodes connected to the new energy stations are collected, and after normalization, the total power generation time series data within the power grid node range is used as the benchmark to perform similarity analysis on the power generation curves of each power station to obtain the power generation homogeneity factor;

[0134] Based on the power grid data, the structural types of the power grid nodes where the new energy stations are located are classified; for different classified structural types, the corresponding initial average system availability index is configured according to the preset rules, and the initial average system availability index is corrected according to the new energy station data to obtain the actual average system availability index; based on the new energy station data, the historical fault data is obtained, and the ratio of the number of faults to the total number of faults of the power grid nodes where the new energy stations are located is calculated according to the historical fault data. 6 ; Actual average system availability index and ratio r based on different structural types of grid nodes 6 , construct the transmission fault factor;

[0135] The power plant transmission risk factor is constructed based on the site selection assessment results of the power station, the node transmission risk factor, the generation homogeneity factor and the transmission failure factor.

[0136] Optionally, the factor construction module 202 further includes a distance factor construction unit 2024 of the power load, which is used to perform the following operations:

[0137] Based on the data of new energy stations, the HHI is used to evaluate the concentration of power loads in the grid node area to obtain the concentration evaluation results; and the impedance of the transmission line between each independent power load and the new energy station is weighted to obtain the load impedance weighted value; based on the concentration evaluation results and the load impedance weighted value, the load concentration factor is constructed;

[0138] Based on the ratio of the total electric load of the area directly connected to the grid node connected to the new energy station to the installed capacity of the new energy station connected to the grid node 7 , construct the electricity intensity factor;

[0139] Based on the load concentration factor and the power intensity factor, the distance factor of the power load is constructed.

[0140] Optionally, the factor construction module 202 further includes a meteorological factor construction unit 2025, which is used to perform the following operations:

[0141] Based on the historical data of the power market, the time series data of power generation in the power market is obtained, and the correlation analysis between the time series data of power generation in the power market and the historical meteorological data is carried out to obtain the factors affecting power generation;

[0142] Based on the historical data of the power market, the time series data of the power grid transmission capacity is obtained, and the correlation analysis of the time series data of the power grid transmission capacity and the historical meteorological data is carried out to obtain the influencing factors of the transmission capacity;

[0143] Based on the historical data of the power market, the time series data of power load is obtained, and the correlation analysis of the time series data of power load and the historical meteorological data is carried out to obtain the influencing factors of power load;

[0144] Meteorological factors are constructed based on the factors affecting power generation, transmission capacity and power load.

[0145] Optionally, the factor construction module 202 further includes a primary energy price factor construction unit 2026, which is used to perform the following operations:

[0146] Based on the primary energy price data, obtain the changing pattern of the proportion of primary energy to energy consumption over time, and set the time series factor of the primary energy consumption proportion based on the changing pattern;

[0147] Based on the primary energy price data, the degree of dependence of different types of new energy stations on primary energy is obtained, and the weight time series factor of the power station type is set based on the degree of dependence;

[0148] Based on the time series factor of primary energy consumption proportion and the time series factor of power station type weight, the primary energy price factor is constructed.

[0149] Optionally, the electricity quantity and electricity price analysis module 203 includes:

[0150] The multi-factor integration unit 2031 is used to aggregate policy factors, market maturity factors, power plant transmission risk factors, power load distance factors, meteorological factors and primary energy price factors to obtain a historical comprehensive factor data set.

[0151] The power generation dynamic analysis unit 2032 is used to perform the following operations:

[0152] Obtaining historical power generation time series data based on new energy station data, and using the historical power generation time series data to build a first quantitative analysis model integrating a neural network and an artificial intelligence algorithm; wherein the neural network and artificial intelligence algorithm in this step include LSTM and Transformer models;

[0153] Inputting the historical comprehensive factor data set into the first quantitative analysis model, training the quantitative analysis model, and obtaining a trained power generation prediction model;

[0154] According to different time periods, the real-time comprehensive factor data set is input into the trained power generation prediction model to calculate the power generation prediction values ​​for different time periods in the entire life cycle of the new energy station, forming a dynamic analysis result of power generation.

[0155] The electricity price dynamic analysis unit 2033 is used to perform the following operations:

[0156] Obtain historical electricity price time series data based on new energy station data, and use the historical electricity price time series data to build a second quantitative analysis model that integrates a neural network and an artificial intelligence algorithm; wherein the neural network and artificial intelligence algorithm in this step include a CNN-LSTM model, a Transformer model, or an ARIMA-SSA-LSTM combination model;

[0157] Inputting the historical comprehensive factor data set into the second quantitative analysis model, training the quantitative analysis model, and obtaining a trained electricity price prediction model;

[0158] According to different time periods, the real-time comprehensive factor data set is input into the trained electricity price prediction model to calculate the electricity price forecast values ​​for different time periods in the entire life cycle of the new energy station, forming a dynamic analysis result of power generation.

[0159] An embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0160] The embodiments of the present application further provide a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0161] The above-mentioned method using CNN, LSTM, ARIMA, SSA, Transformer, TGARCH-Vi neCopula models and their combined models is only a method used in the field of artificial intelligence and big data. The present invention includes but is not limited to the mentioned method for data analysis, and is also applicable to other methods that can realize big data and artificial intelligence analysis.

[0162] The new energy sites mentioned in the present invention include thermal power plants, wind power plants, photovoltaic power plants, and combinations of different power plants.

[0163] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0164] The above-mentioned embodiments only express several implementation methods of the embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the embodiments of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the embodiments of the present application, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A dynamic evaluation method for the whole life cycle of a new energy station based on the electricity spot market, characterized in that: The method comprises: S1: Obtaining electricity spot market information, which includes: policy documents, information disclosed by market operating institutions, electricity market historical data, primary energy price data, power grid data and new energy station data; S2: Based on the electricity spot market information, construct multiple quantitative factors, including: S21: constructing policy factors based on the policy document; S22: constructing a market maturity factor based on the information disclosed by the market operating institution; S23: constructing a power transmission risk factor of a power station and a power load distance factor based on the power grid data and the new energy station data; S24: constructing meteorological factors based on the electricity market historical data and in combination with historical meteorological data; S25: constructing a primary energy price factor based on the primary energy price data; Among them, the policy factor is used to quantify the impact of policies on new energy projects; the market maturity factor is used to quantify the degree of marketization at different stages of development of the electricity spot market; the power station transmission risk factor is used to quantify the difficulty of new energy sites in transmitting electricity to the connected power grid; the power load distance factor is used to quantify the closeness of the supply and demand relationship between new energy sites and power loads; the meteorological factor is used to quantify the impact of meteorology on power generation, transmission capacity and power load; the primary energy price factor is used to quantify the comprehensive impact of primary energy price fluctuations on power generation and electricity prices; S3: Based on the quantitative factors, dynamically analyze the power generation and electricity price of the new energy station throughout its life cycle to obtain power generation analysis results and electricity price analysis results; S4: Based on the power generation analysis results and the electricity price analysis results, a dynamic technical and economic evaluation of the new energy station over its entire life cycle is performed according to a preset technical and economic evaluation process.

2. The method according to claim 1, characterized in that The step of constructing a policy factor based on the policy document includes: Assigning different policy levels to each of the policy documents, and setting corresponding level coefficients for the policy documents of different policy levels; Using the lag effect panel model, based on the historical data of the electricity market, the time lag law and degree of different policies from their introduction to their actual impact on new energy projects are quantitatively analyzed, and the lag factors corresponding to the policy documents of different policy levels are obtained; Extract keywords from the policy document using text mining technology and convert the keywords into quantitative data; analyze the relationship between the quantitative data and market installed capacity, market power generation, and market electricity price through a system dynamics model, and use the relationship to establish a prediction model of policy on installed capacity, a prediction model of policy on power generation, and a prediction model of policy on electricity price; The policy factor is constructed based on the grade coefficient, the hysteresis factor, the prediction model of the policy on installed capacity, the prediction model of the policy on power generation, and the prediction model of the policy on electricity price.

3. The method according to claim 2, characterized in that The market maturity factor is constructed based on the information disclosed by the market operating institution, including: Obtaining market operation information from information disclosed by the market operation institution, determining the market operation stage through the market operation information, and setting corresponding stage factors for different operation stages according to preset rules; Calculate the ratio r1 of the installed capacity of power stations participating in the electricity spot market to the installed capacity of all power stations, calculate the ratio r2 of the power generation of power stations participating in the electricity spot market to the power generation of all power stations, and construct the marketization degree factor of the power station based on the ratio r1 and the ratio r2; Calculate the ratio r3 of the power load participating in the power spot market to the total power load capacity, calculate the ratio r4 of the number of power loads participating in power spot transactions to the total power load quantity, and construct the power load marketization degree factor based on the ratio r3 and the ratio r4; The market maturity factor is constructed based on the stage factor, the power plant marketization degree factor and the electricity load marketization degree factor.

4. The method according to claim 3, characterized in that The step of constructing a power station transmission risk factor based on the power grid data and the new energy station data includes: Based on the power grid data, the power flow of the existing power grid is analyzed to obtain the blocking probability distribution of the power station nodes; based on the blocking probability distribution, the site selection of the power station is evaluated to obtain the site selection evaluation result of the power station; Based on the new energy station data, the ratio r5 of the power transmission capacity of the power grid node line connected to the power station to the installed capacity of the power station is calculated, and the node transmission risk factor is constructed based on the ratio r5; Based on the new energy station data, the historical power generation time series data of all new energy stations in the power grid node to which the new energy station is connected are collected, and after normalization, the total power generation time series data within the power grid node range is used as a benchmark to perform similarity analysis on the power generation curves of each power station to obtain a power generation homogeneity factor; Based on the power grid data, the structural types of the power grid nodes where the new energy station is located are classified; for the structural types of different classifications, the corresponding initial average system availability index is configured for them according to preset rules, and the initial average system availability index is corrected according to the new energy station data to obtain the actual average system availability index; based on the new energy station data, historical fault data is obtained, and the ratio r6 of the number of faults to the total number of faults of the power grid node where the new energy station is located is calculated according to the historical fault data; based on the actual average system availability index of the power grid nodes of different structural types and the ratio r6, a transmission fault factor is constructed; The power station transmission risk factor is constructed based on the power station site selection assessment result, the node transmission risk factor, the power generation homogeneity factor and the transmission failure factor.

5. The method according to claim 4, characterized in that The step of constructing a distance factor of the power load based on the power grid data and the new energy station data includes: Based on the new energy station data, the HHI is used to evaluate the concentration of the power load in the grid node area to obtain a concentration evaluation result; and the transmission line impedance between each independent power load and the new energy station is weighted to obtain a load impedance weighted value; based on the concentration evaluation result and the load impedance weighted value, a load concentration factor is constructed; Constructing an electricity intensity factor based on a ratio r7 of the total electric load of the area directly connected to the grid node to which the new energy station is connected to and the installed capacity of the new energy station to which the grid node is connected; Based on the load concentration factor and the power intensity factor, a distance factor of the power load is constructed.

6. The method according to claim 5, characterized in that The meteorological factors are constructed based on the historical data of the power market and in combination with the historical meteorological data, including: Based on the power market historical data, the power market power generation time series data is acquired, and the power market power generation time series data and the meteorological historical data are correlated and analyzed to obtain the power generation influencing factor; Based on the electricity market historical data, the time series data of the power grid transmission capacity is obtained, and the correlation analysis is performed on the time series data of the power grid transmission capacity and the meteorological historical data to obtain the transmission capacity influencing factor; Acquire power load time series data based on the power market historical data, perform correlation analysis on the power load time series data and the meteorological historical data, and obtain a power load influencing factor; The meteorological factor is constructed based on the power generation influencing factor, the power transmission capacity influencing factor and the power load influencing factor.

7. The method according to claim 6, characterized in that The constructing of a primary energy price factor based on the primary energy price data includes: Based on the primary energy price data, obtain the changing pattern of the proportion of primary energy to energy consumption over time, and set the time series factor of the primary energy consumption proportion based on the changing pattern; Based on the primary energy price data, the degree of dependence of the different types of new energy stations on primary energy is obtained, and the weight time series factor of the power station type is set based on the degree of dependence; The primary energy price factor is constructed based on the primary energy consumption proportion time series factor and the power plant type weight time series factor.

8. The method according to claim 7, characterized in that Based on the quantitative factors, the power generation and electricity price of the new energy station throughout its life cycle are dynamically analyzed to obtain power generation analysis results and electricity price analysis results, including: S31: Multi-factor integration step: Summarizing the policy factor, the market maturity factor, the power plant transmission risk factor, the power load distance factor, the meteorological factor and the primary energy price factor to obtain a historical comprehensive factor data set; S32: Dynamic analysis steps of power generation: Based on the new energy station data, historical power generation time series data is obtained, and the historical power generation time series data is used to build a first quantitative analysis model integrating a neural network and an artificial intelligence algorithm; wherein the neural network and artificial intelligence algorithm in this step include LSTM and Transformer models; Inputting the historical comprehensive factor data set into the first quantitative analysis model, training the quantitative analysis model, and obtaining a trained power generation prediction model; According to different time periods, the real-time comprehensive factor data set is input into the trained power generation prediction model, and the power generation prediction values ​​of different time periods in the whole life cycle of the new energy site are calculated to form the power generation dynamic analysis results; S33: Steps for dynamic analysis of electricity prices: Based on the new energy station data, historical electricity price time series data is obtained, and the historical electricity price time series data is used to construct a second quantitative analysis model integrating a neural network and an artificial intelligence algorithm; wherein the neural network and artificial intelligence algorithm in this step include a CNN-LSTM model, a Transformer model or an ARIMA-SSA-LSTM combination model; Inputting the historical comprehensive factor data set into the second quantitative analysis model, training the quantitative analysis model, and obtaining a trained electricity price prediction model; According to different time periods, the real-time comprehensive factor data set is input into the trained electricity price prediction model, and the electricity price prediction values ​​for different time periods in the entire life cycle of the new energy site are calculated to form the dynamic analysis results of the power generation.

9. A dynamic evaluation system for the entire life cycle of new energy stations based on the electricity spot market, characterized in that: The system comprises: A data acquisition module is used to acquire electricity spot market information, which includes: policy documents, information disclosed by market operating institutions, electricity market historical data, primary energy price data, power grid data and new energy station data; A factor construction module is used to construct multiple quantitative factors based on the electricity spot market information, including: constructing a policy factor based on the policy document; constructing a market maturity factor based on the information disclosed by the market operation agency; constructing a power station transmission risk factor and a power load distance factor based on the power grid data and the new energy site data; constructing a meteorological factor based on the electricity market historical data and historical meteorological data; and constructing a primary energy price factor based on the primary energy price data. The power and electricity price analysis module is used to dynamically analyze the power generation and electricity price of the new energy station throughout its life cycle based on the quantitative factors to obtain power generation analysis results and electricity price analysis results; A dynamic technical and economic evaluation module, used to perform a dynamic technical and economic evaluation of the new energy station over its entire life cycle according to a preset technical and economic evaluation process based on the power generation analysis result and the electricity price analysis result; Among them, the policy factor is used to quantify the impact of policies on new energy projects; the market maturity factor is used to quantify the degree of marketization at different stages of development of the electricity spot market; the power station transmission risk factor is used to quantify the difficulty of new energy sites in transmitting electric energy to the connected power grid; the power load distance factor is used to quantify the closeness of the supply and demand relationship between new energy sites and power loads; the meteorological factor is used to quantify the impact of meteorology on power generation, transmission capacity and power load; the primary energy price factor is used to quantify the comprehensive impact of primary energy price fluctuations on power generation and electricity prices.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images