Interprovincial and interregional electric power medium and long term transaction continuous operation model analysis system

Abstract

The invention discloses a trans-provincial and trans-regional electric power medium and long term transaction continuous operation model analysis system, and belongs to the technical field of electric power. A data acquisition and preprocessing module acquires electric power transaction data, new energy power generation data, meteorological data and market rule change information in real time or regularly; the market dynamic monitoring and analysis module dynamically monitors and analyzes the market supply and demand relationship, the price trend and the transaction rule change based on real-time and historical data; the new energy adaptability evaluation module evaluates the influence of the fluctuation and uncertainty of the new energy power generation on the medium and long term transaction of the power by comparing the actual data and the prediction data of the new energy power generation; and the transaction strategy optimization module formulates an optimal transaction strategy and a quotation scheme for two transaction parties by constructing a multi-objective optimization model and synthesizing cost, risk and income. According to the invention, the accuracy of analysis and prediction of medium and long term transactions of trans-provincial and trans-regional electric power in which new energy participates is improved.

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology, and in particular relates to a continuous operation model analysis system for inter-provincial and inter-regional medium- and long-term electric power transactions. Background Art

[0002] Due to the imbalance between the distribution of energy resources and electricity demand, for example, coal, hydropower and other resources are mainly concentrated in the northwest and southwest regions, while economically developed and high-power consumption areas are mainly concentrated in the eastern coastal areas. Therefore, it is necessary to trade electricity across regions. Inter-provincial and inter-regional electricity medium- and long-term transactions can transmit electricity from resource-rich areas to areas with high demand, thereby achieving optimal allocation of resources. Through this system analysis, we can better understand the resource status and demand changes in different regions, provide support for the formulation of reasonable trading strategies and transmission plans, and improve energy efficiency.

[0003] The electricity market is a complex system that is constantly changing. With the rapid development of new energy, the advancement of power system reform, and the diversification of market players, the market's trading rules, supply and demand relationships, etc. are constantly changing. Existing analysis models may be based on past market conditions and data. For new market conditions and changes, the model is not adaptable enough and it is difficult to accurately analyze and predict. For example, in recent years, the proportion of new energy power generation has continued to increase, and its volatility and uncertainty have brought new challenges to medium- and long-term power transactions. However, existing models may not be able to adapt well to such changes, resulting in inaccurate analysis and prediction of medium- and long-term cross-provincial and cross-regional power transactions involving new energy. Summary of the invention

[0004] In response to the problems existing in the prior art, the present invention provides a continuous operation model analysis system for cross-provincial and cross-regional medium- and long-term electricity transactions, which has the advantage of improving the accuracy of analysis and prediction of cross-provincial and cross-regional medium- and long-term electricity transactions involving new energy, and solves the problems of the prior art.

[0005] The present invention is implemented as follows: a continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions, comprising a central processing module, wherein the central processing module is signal-connected with a data acquisition and preprocessing module, a market dynamic monitoring and analysis module, a new energy adaptability assessment module, a transaction strategy optimization module, and a model update and iteration module;

[0006] The data collection and preprocessing module collects power transaction data, new energy power generation data, meteorological data, and market rule change information in real time or regularly. After the data is cleaned, standardized, and integrated, it provides a data basis for subsequent analysis;

[0007] The market dynamic monitoring and analysis module dynamically monitors and analyzes market supply and demand relationships, price trends, and changes in trading rules based on real-time and historical data;

[0008] The new energy adaptability assessment module compares the actual data of new energy power generation with the forecast data to assess the impact of the volatility and uncertainty of new energy power generation on medium- and long-term power transactions;

[0009] The trading strategy optimization module builds a multi-objective optimization model to comprehensively consider costs, risks, and benefits to develop the best trading strategy and quotation plan for both parties.

[0010] The model update and iteration module presets several analysis models and sets the conditions for the use of each analysis model. When the conditions are met, the corresponding analysis model is automatically replaced.

[0011] Solutions to technical problems:

[0012] Improve model adaptability: Real-time acquisition of market change information through the data acquisition and preprocessing module, dynamic analysis of market trends through the market dynamics monitoring and analysis module, and special analysis of new energy power generation through the new energy adaptability assessment module, jointly improve the model's adaptability to market changes.

[0013] Coping with the volatility of renewable energy power generation: The new energy adaptability assessment module and the trading strategy optimization module jointly design flexible trading strategies to cope with the risks brought by the uncertainty of renewable energy power generation.

[0014] Continuously optimize model performance: preset several analysis models and set the conditions for using each analysis model. When the conditions are met, automatically replace the corresponding analysis model to ensure the accuracy and adaptability of the model.

[0015] Through the design and implementation of the above modules, the system can realize the continuous operation model analysis of cross-provincial and cross-regional medium- and long-term electricity transactions, improve the accuracy and adaptability of the analysis, and provide strong decision-making support for both parties of the electricity transaction.

[0016] As a preferred embodiment of the present invention, the central processing module includes the following units:

[0017] The data scheduling unit coordinates the data flow between various modules to ensure timely and accurate data transmission between the data acquisition and preprocessing module, the market dynamics monitoring and analysis module, the new energy adaptability assessment module, the trading strategy optimization module and the model update and iteration module;

[0018] The task allocation unit decomposes and allocates the tasks of each module according to system requirements to ensure that each module can work together efficiently and jointly complete the analysis task of the continuous operation model of medium- and long-term power transactions.

[0019] As a preferred embodiment of the present invention, the data acquisition and preprocessing module includes the following units:

[0020] Real-time data collection unit collects power transaction data, new energy power generation data, meteorological data, etc. in real time to ensure the timeliness and accuracy of the data;

[0021] Historical data acquisition unit, which regularly acquires historical data for historical data analysis in the market dynamics monitoring and analysis module and the trading strategy optimization module;

[0022] The data cleaning and standardization unit cleans the collected data, removes duplicate, erroneous or invalid data, and performs standardization processing;

[0023] The new energy meteorological data correction unit collects wind speed data, wind power generation ratio, sunlight data, and photovoltaic power generation ratio to improve the accuracy of new energy power generation forecast data.

[0024] As a preferred embodiment of the present invention, the data acquisition and preprocessing module also includes the following units:

[0025] The first data calculation unit calculates data accuracy, data cleaning rate and new energy power generation ratio based on data from the real-time data acquisition unit, the historical data acquisition unit, the data cleaning and standardization unit and the new energy meteorological data correction unit; wherein,

[0026] Data accuracy = (correct data volume / total data volume) × 100%;

[0027] Data cleaning rate = (the amount of cleaned data / the original total amount of data) × 100%;

[0028] The proportion of power generation from a certain new energy source = (actual power generation from the new energy source / total power generation) × 100%.

[0029] As a preferred embodiment of the present invention, the market dynamic monitoring and analysis module includes the following units:

[0030] The market supply and demand relationship monitoring unit dynamically monitors and analyzes the market supply and demand relationship based on real-time and historical data, identifies supply and demand imbalances, and provides early warnings for decision makers;

[0031] The price trend analysis unit monitors and analyzes power transaction prices in real time, identifies price fluctuation trends, and provides price references for the trading strategy optimization module;

[0032] The trading rule change monitoring unit tracks changes in market rules and promptly identifies and analyzes the impact of rule changes on medium- and long-term power transactions;

[0033] The new energy power generation impact analysis unit conducts special analysis on the proportion and volatility of new energy power generation, evaluates its impact on medium- and long-term power transactions, and provides decision support for the trading strategy optimization module.

[0034] As a preferred embodiment of the present invention, the market dynamics monitoring and analysis module also includes the following units:

[0035] The second data calculation unit calculates the supply and demand imbalance, price volatility, rule change impact coefficient, new energy power generation impact rate and price trend prediction accuracy based on the data of the market supply and demand relationship monitoring unit, the price trend analysis unit, the transaction rule change monitoring unit and the new energy power generation impact analysis unit;

[0036] Among them, supply-demand imbalance = |total supply - total demand| / average demand × 100%;

[0037] Price volatility = (current price - average price) / average price × 100%;

[0038] Rule change impact coefficient = (total number of transactions after the change - total number of transactions before the change) / total number of transactions before the change × 100%;

[0039] Impact rate of new energy power generation = (total amount of transactions including new energy power generation - total amount of transactions without new energy power generation) / total amount of transactions without new energy power generation × 100%;

[0040] Price trend prediction accuracy = number of correctly predicted price trends / total number of predictions × 100%.

[0041] As a preferred embodiment of the present invention, the new energy power generation impact analysis unit includes:

[0042] Renewable energy power generation ratio analysis subunit: By comparing historical data with current data, evaluate the changing trend and speed of the proportion of renewable energy power generation;

[0043] New energy power generation volatility assessment subunit: By analyzing the historical volatility data of new energy power generation, a volatility assessment model is established to predict the volatility of future new energy power generation;

[0044] Sub-unit for analysis of the impact of renewable energy generation on medium- and long-term electricity transactions: Based on the analysis results of the proportion and volatility of renewable energy generation, the impact of renewable energy generation on medium- and long-term electricity transactions is deeply evaluated. The analysis includes the impact of renewable energy generation on the balance of electricity supply and demand, the impact on electricity price fluctuations, and the impact on the electricity market transaction structure;

[0045] Among them, the change rate of the proportion of new energy power generation = (the proportion of new energy power generation in this period - the proportion of new energy power generation in the previous period) / the proportion of new energy power generation in the previous period × 100%;

[0046] Contribution of renewable energy generation to electricity price fluctuations = (electricity price fluctuation rate when renewable energy generation is included - electricity price fluctuation rate when renewable energy generation is not included) / electricity price fluctuation rate when renewable energy generation is included × 100%;

[0047] Adjustment coefficient of supply and demand balance of new energy power generation = adjustable capacity of new energy power generation / difference between supply and demand in the electricity market;

[0048] New energy power generation market transaction structure impact index = change in the proportion of new energy power generation transaction amount / change in total electricity transaction amount.

[0049] As a preferred embodiment of the present invention, the new energy adaptability assessment module includes the following units:

[0050] The new energy power generation volatility analysis unit compares the actual data and forecast data of new energy power generation and evaluates the impact of the volatility of new energy power generation on medium- and long-term power transactions.

[0051] The uncertainty assessment unit evaluates the risks brought by the uncertainty of renewable energy power generation to medium- and long-term power transactions, and provides a risk assessment basis for the trading strategy optimization module.

[0052] The evaluation model dynamic adjustment unit dynamically adjusts the evaluation model according to the development trend of new energy power generation and changes in market rules to ensure the accuracy and adaptability of the evaluation results.

[0053] As a preferred embodiment of the present invention, the trading strategy optimization module includes the following units:

[0054] Cost-benefit analysis unit, which conducts comprehensive analysis of the costs and benefits of trading strategies to provide data support for formulating optimal trading strategies;

[0055] The Risk Assessment and Response Unit assesses the risks posed by the volatility of renewable energy generation and designs flexible trading strategies to address these risks;

[0056] The quotation proposal formulation unit formulates quotation proposals for both parties to the transaction based on the results of cost-benefit analysis and risk assessment.

[0057] As a preferred embodiment of the present invention, the model updating and iteration module includes the following units:

[0058] An analysis model presetting unit is used to preset several analysis models for analyzing the continuous operation model of medium- and long-term power transactions;

[0059] Model usage condition setting unit, which sets the usage conditions for each analysis model to ensure that the corresponding analysis model can be automatically replaced under specific circumstances;

[0060] The model update and iteration execution unit automatically executes the model update and iteration operations when the conditions are met to ensure the accuracy and applicability of the analysis model.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] The system can significantly improve the efficiency and accuracy of medium- and long-term cross-provincial and cross-regional electricity transactions. By collecting and processing large amounts of data in real time, the system provides comprehensive and accurate market information and analysis results to both parties to the transaction, helping decision makers to respond quickly. At the same time, the introduction of the new energy adaptability assessment module and the trading strategy optimization module enables the system to better cope with the volatility and uncertainty of new energy power generation and reduce trading risks. In addition, the setting of the model update and iteration module ensures that the system can be continuously updated and optimized as the market environment and rules change, thereby continuously providing high-quality services to both parties to the transaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a structural block diagram of a continuous operation model analysis system for inter-provincial and inter-regional medium- and long-term power transactions provided by an embodiment of the present invention;

[0064] Figure 2 is a structural block diagram of a data acquisition and preprocessing module provided in an embodiment of the present invention;

[0065] Figure 3 is a structural block diagram of a market dynamics monitoring and analysis module provided by an embodiment of the present invention;

[0066] Figure 4 is a structural block diagram of a new energy adaptability assessment module provided by an embodiment of the present invention;

[0067] Figure 5 is a structural block diagram of a trading strategy optimization module provided by an embodiment of the present invention;

[0068] Figure 6 It is a structural block diagram of the model updating and iteration module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to further understand the content, features and effects of the present invention, the following embodiments are given as examples and described in detail with reference to the accompanying drawings.

[0070] The structure of the present invention is described in detail below in conjunction with the accompanying drawings.

[0071] like Figures 1 to 6 As shown, an embodiment of the present invention provides an inter-provincial and inter-regional medium- and long-term electricity transaction continuous operation model analysis system, including a central processing module, wherein the central processing module is signal-connected to a data acquisition and preprocessing module, a market dynamic monitoring and analysis module, a new energy adaptability evaluation module, a transaction strategy optimization module, and a model update and iteration module;

[0072] The data collection and preprocessing module collects power transaction data, renewable energy power generation data, meteorological data, and market rule change information from various power markets, power generation companies, power grid companies, and other channels in real time or regularly. After data cleaning, standardization, and integration, it provides a data basis for subsequent analysis. In particular, in view of the volatility and uncertainty of renewable energy power generation, this module will focus on collecting and preprocessing key meteorological data such as wind speed and light intensity, as well as renewable energy power generation forecast data, to improve the accuracy of analysis.

[0073] The market dynamic monitoring and analysis module dynamically monitors and analyzes market supply and demand relationships, price trends, and changes in trading rules based on real-time and historical data. Through machine learning algorithms and statistical analysis methods, it automatically identifies abnormal situations and trend changes in the market, providing timely warnings and insights for decision makers. In addition, the module will also conduct special analysis on the proportion and volatility of new energy power generation, and evaluate its impact on medium- and long-term power transactions.

[0074] The new energy adaptability assessment module compares the actual data of new energy power generation with the forecast data to assess the impact of the volatility and uncertainty of new energy power generation on medium- and long-term power transactions. At the same time, the module will dynamically adjust the assessment model according to the development trend of new energy power generation and changes in market rules to ensure the accuracy and adaptability of the assessment results.

[0075] The trading strategy optimization module builds a multi-objective optimization model, comprehensively considers costs, risks, and benefits, and formulates the best trading strategy and quotation plan for both parties. In particular, in view of the volatility of renewable energy power generation, the module will design flexible trading strategies to cope with the risks brought by the uncertainty of renewable energy power generation.

[0076] The model update and iteration module presets several analysis models and sets the conditions for the use of each analysis model. When the conditions are met, the corresponding analysis model is automatically replaced.

[0077] Solutions to technical problems:

[0078] Improve model adaptability: Real-time acquisition of market change information through the data acquisition and preprocessing module, dynamic analysis of market trends through the market dynamics monitoring and analysis module, and special analysis of new energy power generation through the new energy adaptability assessment module, jointly improve the model's adaptability to market changes.

[0079] Coping with the volatility of renewable energy power generation: The new energy adaptability assessment module and the trading strategy optimization module jointly design flexible trading strategies to cope with the risks brought by the uncertainty of renewable energy power generation.

[0080] Continuously optimize model performance: preset several analysis models and set the conditions for using each analysis model. When the conditions are met, automatically replace the corresponding analysis model to ensure the accuracy and adaptability of the model.

[0081] Through the design and implementation of the above modules, the system can realize the continuous operation model analysis of cross-provincial and cross-regional medium- and long-term electricity transactions, improve the accuracy and adaptability of the analysis, and provide strong decision-making support for both parties of the electricity transaction.

[0082] Specifically, the central processing module includes the following units:

[0083] The data scheduling unit coordinates the data flow between various modules to ensure timely and accurate data transmission between the data collection and preprocessing module, market dynamics monitoring and analysis module, new energy adaptability assessment module, trading strategy optimization module and model update and iteration module.

[0084] The task allocation unit decomposes and allocates the tasks of each module according to system requirements to ensure that each module can work together efficiently and jointly complete the analysis task of the continuous operation model of medium- and long-term power transactions.

[0085] Specifically, the data acquisition and preprocessing module includes the following units:

[0086] Real-time data collection unit collects power transaction data, new energy power generation data, meteorological data, etc. in real time to ensure the timeliness and accuracy of the data;

[0087] Historical data acquisition unit, which regularly acquires historical data for historical data analysis in the market dynamics monitoring and analysis module and the trading strategy optimization module;

[0088] The data cleaning and standardization unit cleans the collected data, removes duplicate, erroneous or invalid data, and performs standardization to provide a data basis for subsequent analysis.

[0089] The new energy meteorological data correction unit collects wind speed data, wind power generation ratio, sunlight data, and photovoltaic power generation ratio to improve the accuracy of new energy power generation forecast data.

[0090] Specifically, the data acquisition and preprocessing module also includes the following units:

[0091] The first data calculation unit calculates data accuracy, data cleaning rate and new energy power generation ratio based on data from the real-time data collection unit, the historical data acquisition unit, the data cleaning and standardization unit and the new energy meteorological data correction unit.

[0092] Data Accuracy

[0093] Formula: Data accuracy = (correct data volume / total data volume) × 100%;

[0094] For example, the real-time data collection unit collected 1,000 pieces of power transaction data in a certain hour. After manual sampling inspection and system logic verification, it was found that 980 pieces of data were correct. Then the data accuracy = (980 / 1,000) × 100% = 98%.

[0095] Data cleaning rate

[0096] Formula: Data cleaning rate = (amount of cleaned data / total original data) × 100%;

[0097] For example, the data cleaning and standardization unit obtains 5,000 pieces of original data. After deduplication, error and invalid data removal, 4,500 pieces of valid data remain. The amount of cleaned data is 5,000-4,500=500. Data cleaning rate=(500 / 5,000)×100%=10%.

[0098] Proportion of renewable energy power generation

[0099] Formula: The proportion of electricity generation from a certain new energy source = (actual electricity generation from the new energy source / total electricity generation) × 100%;

[0100] For example: assuming that the total power generation in a certain area is 1000 MWh, of which the actual wind power generation is 300 MWh, the wind power generation ratio = (300 / 1000) × 100% = 30%.

[0101] Specifically, the market dynamics monitoring and analysis module includes the following units:

[0102] The market supply and demand relationship monitoring unit dynamically monitors and analyzes the market supply and demand relationship based on real-time and historical data, identifies supply and demand imbalances, and provides early warnings for decision makers;

[0103] The price trend analysis unit monitors and analyzes power transaction prices in real time, identifies price fluctuation trends, and provides price references for the trading strategy optimization module;

[0104] The trading rule change monitoring unit tracks changes in market rules and promptly identifies and analyzes the impact of rule changes on medium- and long-term power transactions;

[0105] The new energy power generation impact analysis unit conducts special analysis on the proportion and volatility of new energy power generation, evaluates its impact on medium- and long-term power transactions, and provides decision support for the trading strategy optimization module.

[0106] Specifically, the market dynamics monitoring and analysis module also includes the following units:

[0107] The second data calculation unit calculates the supply and demand imbalance, price volatility, rule change impact coefficient, new energy power generation impact rate and price trend prediction accuracy based on the data from the market supply and demand relationship monitoring unit, the price trend analysis unit, the transaction rule change monitoring unit and the new energy power generation impact analysis unit.

[0108] The specific calculation is as follows:

[0109] Supply and demand imbalance

[0110] Formula: Supply-demand imbalance = |Total supply - total demand| / average demand × 100%;

[0111] For example: In a certain period of time, the total market supply is 8000 MWh, the total demand is 7500 MWh, and the average demand in the past period is 7000 MWh. Then the supply-demand imbalance = |8000-7500| / 7000×100%≈7.14%.

[0112] Price volatility

[0113] Formula: Price volatility = (current price - average price) / average price × 100%;

[0114] For example, in a period of time, the average price of electricity trading is 50 yuan / MWh, and the current price is 53 yuan / MWh. Then the price volatility = (53-50) / 50×100% = 6%.

[0115] Rule change impact coefficient

[0116] Formula: Rule change impact coefficient = (total number of transactions after the change - total number of transactions before the change) / total number of transactions before the change × 100%;

[0117] For example, before the market rules change, the total volume of medium- and long-term electricity transactions is 10,000 MWh, and after the rules change, the total volume is 11,000 MWh. Then the impact coefficient of the rule change = (11,000-10,000) / 10,000×100%=10%.

[0118] Impact rate of new energy power generation

[0119] Formula: New energy power generation impact rate = (total amount of transactions including new energy power generation - total amount of transactions without new energy power generation) / total amount of transactions without new energy power generation × 100%;

[0120] For example, when there is no participation of renewable energy generation, the total transaction volume is 8,000 MWh, and when there is participation of renewable energy generation, the total transaction volume is 8,500 MWh. Then the impact rate of renewable energy generation = (8,500-8,000) / 8,000×100% = 6.25%.

[0121] Price trend prediction accuracy

[0122] Formula: Price trend prediction accuracy = number of correctly predicted price trends / total number of predictions × 100%;

[0123] For example, 30 price trend forecasts were conducted within a month, and 24 of them were correct. The price trend forecast accuracy rate = 24 / 30 × 100% = 80%.

[0124] Specifically, the new energy power generation impact analysis unit includes:

[0125] Renewable energy power generation ratio analysis subunit: By comparing historical data with current data, evaluate the changing trend and speed of the proportion of renewable energy power generation;

[0126] New energy power generation volatility assessment subunit: By analyzing the historical volatility data of new energy power generation, a volatility assessment model is established to predict the volatility of future new energy power generation. The assessment results help the trading strategy optimization module to formulate measures to deal with volatility risks. Volatility refers to the instability of power generation caused by weather, seasons and other factors.

[0127] Sub-unit for analysis of the impact of renewable energy generation on medium- and long-term electricity trading: Based on the analysis results of the proportion and volatility of renewable energy generation, the impact of renewable energy generation on medium- and long-term electricity trading is deeply evaluated. The analysis includes the impact of renewable energy generation on the balance of electricity supply and demand, the impact on electricity price fluctuations, and the impact on the electricity market trading structure. Through comprehensive analysis, it provides decision support for the trading strategy optimization module and helps to formulate more reasonable and effective medium- and long-term electricity trading strategies.

[0128] Among them, the change rate of renewable energy power generation

[0129] Formula: Change rate of new energy power generation ratio = (new energy power generation ratio in this period - new energy power generation ratio in the previous period) / new energy power generation ratio in the previous period × 100%;

[0130] For example, the proportion of renewable energy generation in a certain region in the previous period was 20% of the total power generation, and it is 25% in this period. Then the change rate of renewable energy generation = (25%-20%) / 20%×100%=25%. This indicates that the proportion of renewable energy generation has increased significantly, which may have an impact on the power market structure and trading strategies, prompting the trading strategy optimization module to consider adjusting the trading portfolio to adapt to the growth of renewable energy generation.

[0131] Contribution of renewable energy generation to electricity price fluctuations

[0132] Formula: Contribution of renewable energy generation to electricity price fluctuation = (electricity price fluctuation rate when renewable energy generation is included - electricity price fluctuation rate when renewable energy generation is not included) / electricity price fluctuation rate when renewable energy generation is included × 100%;

[0133] For example, in a certain area, if the impact of renewable energy generation is not considered, the electricity price volatility is 5% over a period of time, and after considering renewable energy generation, the electricity price volatility becomes 8%. Then the contribution of renewable energy generation to electricity price fluctuation = (8%-5%) / 8%×100%=37.5%. This shows that renewable energy generation has a significant impact on electricity price fluctuation during this period. The trading strategy optimization module can adjust the quotation strategy accordingly, such as appropriately reducing the quotation when the supply of renewable energy generation is expected to be sufficient, and increasing the risk premium when renewable energy generation is unstable.

[0134] Adjustment coefficient of supply and demand balance of new energy power generation

[0135] Formula: New energy power generation supply and demand balance adjustment coefficient = New energy power generation adjustable capacity / power market supply and demand difference;

[0136] For example, the difference between supply and demand in a certain power market is 500 MWh, and the adjustable capacity of renewable energy generation (such as through energy storage facilities or dispatchable renewable energy generation equipment) is 100 MWh. Then the renewable energy generation supply and demand balance adjustment coefficient = 100 / 500 = 0.2. This coefficient reflects the role of renewable energy generation in balancing power supply and demand, and can assist the trading strategy optimization module in determining the utilization strategy of renewable energy generation resources under different supply and demand conditions, such as giving priority to renewable energy generation resources when supply is insufficient to meet demand, and adjusting the transaction price to encourage the generator to increase supply.

[0137] New energy power generation market transaction structure impact index

[0138] Formula: New energy power generation market transaction structure impact index = change in the proportion of new energy power generation transaction amount / change in the total power transaction amount;

[0139] For example, the total electricity transaction amount increased by 10 million yuan in a certain quarter, of which the proportion of new energy power generation transaction amount increased from 10% to 15%, and the proportion change was 5%. Then the new energy power generation market transaction structure impact index = 5% / (the proportion change corresponding to 10 million yuan). Assuming that the total electricity transaction amount base is 100 million yuan, and the proportion change corresponding to 10 million yuan is 10%, then the index = 5% / 10% = 0.5. This index can measure the influence of new energy power generation on the changes in the electricity market transaction structure, help the transaction strategy optimization module grasp the market dynamics, and adjust the allocation strategy of transaction objects and transaction scale.

[0140] Specifically, the new energy adaptability assessment module includes the following units:

[0141] The new energy power generation volatility analysis unit compares the actual data and forecast data of new energy power generation and evaluates the impact of the volatility of new energy power generation on medium- and long-term power transactions.

[0142] The uncertainty assessment unit evaluates the risks brought by the uncertainty of renewable energy power generation to medium- and long-term power transactions, and provides a risk assessment basis for the trading strategy optimization module.

[0143] The evaluation model dynamic adjustment unit dynamically adjusts the evaluation model according to the development trend of new energy power generation and changes in market rules to ensure the accuracy and adaptability of the evaluation results.

[0144] The calculation is as follows:

[0145] 1. Fluctuation deviation of new energy power generation

[0146] formula: (where pi represents the difference between the actual power generation and the predicted power generation in the i-th time period, represents the average difference, and n represents the number of time periods)

[0147] For example: the difference between the actual power generation and the predicted power generation of a new energy power station within a week (7 time periods) is 10, -5, 8, -3, 12, -7, and 9 MWh respectively, then the fluctuation deviation is ≈7.5.

[0148] 2. Uncertainty risk value of new energy power generation

[0149] Formula: New energy power generation uncertainty risk value = (maximum forecast error / average forecast power generation) × 100%

[0150] For example, the average predicted power generation of a new energy power station in a month is 500 MWh, and the maximum prediction error is 50 MWh. Then the uncertainty risk value of new energy power generation = (50 / 500) × 100% = 10%.

[0151] 3. Evaluation model adjustment weights (simple linear weighting)

[0152] Formula: Adjusted weight (in represents the original weight of the jth indicator, k represents the learning rate, ΔF j represents the change of the jth indicator);

[0153] For example: Assume that the original reliability index weight in a certain evaluation model Learning rate k = 0.1, according to the development trend of new energy power generation and changes in market rules, the reliability index change ΔF j =0.2. Then the adjusted weight

[0154] IV. Stability indicators of new energy power generation

[0155] Formula: New energy power generation stability index = 1-(actual power generation standard deviation / average actual power generation)

[0156] For example, the actual power generation of a new energy power station in one month (30 days) is 480, 520, 490, 510, 500... (hypothetical data), the average actual power generation MWh (calculation process omitted), the standard deviation of actual power generation is assumed to be 15 MWh. Then the stability index of new energy power generation = 1-(15 / 500) = 0.97.

[0157] 5. New Energy Power Generation Forecast Deviation Rate

[0158] Formula: New energy power generation forecast deviation rate = (forecasted power generation - actual power generation) / actual power generation × 100%;

[0159] For example, a new energy power station predicts that the power generation on a certain day is 450 MWh, and the actual power generation is 430 MWh. Then the new energy power generation prediction deviation rate = (450-430) / 430×100%≈4.65%.

[0160] Specifically, the trading strategy optimization module includes the following units:

[0161] Cost-benefit analysis unit, which conducts comprehensive analysis of the costs and benefits of trading strategies to provide data support for formulating optimal trading strategies;

[0162] The Risk Assessment and Response Unit assesses the risks posed by the volatility of renewable energy generation and designs flexible trading strategies to address these risks;

[0163] The quotation proposal formulation unit formulates quotation proposals for both parties to the transaction based on the results of cost-benefit analysis and risk assessment.

[0164] 1. Cost-benefit ratio

[0165] Formula: Cost-benefit ratio = benefit / cost × 100%;

[0166] For example: In a certain transaction, the cost is 8 million yuan and the profit is 10 million yuan. Then the cost-benefit ratio = 1000 / 800 × 100% = 125%.

[0167] 2. Risk Factor

[0168] Formula: Risk coefficient = risk value / total transaction amount;

[0169] For example, in a transaction, the risk value is assessed as 2 million yuan, and the total transaction amount is 20 million yuan. Then the risk factor = 200 / 2000 = 0.1.

[0170] 3. Adjustment range of the best offer

[0171] Formula: Adjustment range of the best offer = (new cost-benefit ratio - original cost-benefit ratio) / original cost-benefit ratio × 100%;

[0172] For example: the original cost-benefit ratio is 1.2, and after analysis the new cost-benefit ratio is 1.3. Then the adjustment range of the best offer = (1.3-1.2) / 1.2×100%≈8.33%.

[0173] 4. Risk Response Costs

[0174] Formula: Risk response cost = risk factor × expected loss;

[0175] For example: the risk factor is 0.05, and the expected loss is 5 million yuan. Then the risk response cost = 0.05 × 500 = 250,000 yuan.

[0176] 5. Quotation Scheme Optimization

[0177] Formula: Quotation optimization degree = (benefit after optimization - benefit before optimization) / benefit before optimization × 100%;

[0178] For example, the profit before optimization is 8 million yuan, and the profit after optimization is 8.8 million yuan. Then the optimization degree of the quotation plan = (880-800) / 800×100% = 10%.

[0179] Specifically, the model update and iteration module includes the following units:

[0180] An analysis model presetting unit is used to preset several analysis models for analyzing the continuous operation model of medium- and long-term power transactions;

[0181] Model usage condition setting unit, which sets the usage conditions for each analysis model to ensure that the corresponding analysis model can be automatically replaced under specific circumstances;

[0182] The model update and iteration execution unit automatically executes the model update and iteration operations when the conditions are met to ensure the accuracy and applicability of the analysis model.

[0183] The conditions used in each analysis model can be based on the data calculated by the above formula.

[0184] Analysis models can include the following:

[0185] 1. Time Series Analysis Model - ARIMA Model

[0186] This is applicable when the power transaction data and new energy power generation data acquired by the data acquisition and preprocessing module show obvious time series characteristics, and the data is relatively stable, without large-scale structural mutations or outlier interference. For example, over a long period of time, the power demand in a certain region shows periodic fluctuations in different seasons and time periods, and the fluctuation range is relatively stable, without sudden policy adjustments or large-scale new energy access. By analyzing historical data, the parameters of the ARIMA model (such as autoregressive order p, moving average order q, etc.) can be determined, and then the power transaction data in the future can be predicted, providing basic data support for the trading strategy optimization module, helping trading parties to plan trading strategies in advance and reduce costs and risks.

[0187] 2. Multiple Linear Regression Model

[0188] Applicable situations: Used when the market dynamic monitoring and analysis module finds that there is a relatively obvious linear correlation between electricity trading data and multiple factors (such as market supply and demand, proportion of new energy power generation, meteorological factors, etc.). For example, after analyzing a large amount of historical data, it is found that there is a linear relationship between electricity prices and total supply, total demand, proportion of new energy power generation, and average temperature (affecting electricity demand for cooling and heating). By establishing a multivariate linear regression model, the impact of various factors on electricity prices can be quantitatively analyzed, so that in the trading strategy optimization module, the trading parties can adjust the quotation plan according to the predicted changes in these factors. For example, if it is predicted that the proportion of new energy power generation will increase significantly, which may lead to a drop in electricity prices, the trading parties can reduce their quotations accordingly to improve their competitiveness, and at the same time better estimate the benefits in the cost-benefit analysis.

[0189] 3. Decision Tree Model in Machine Learning

[0190] Applicable situations: Applicable when facing complex changes in market rules, uncertainties in renewable energy generation, and situations where multiple factors interweave and affect medium- and long-term electricity transactions. For example, market rules may formulate different trading rules and price mechanisms based on different sources of power generation (thermal power, hydropower, renewable energy, etc.), power consumption periods (peak, valley, and flat), regional supply and demand differences, etc.; renewable energy generation is also affected by the high uncertainty of meteorological factors such as wind speed and light intensity. The decision tree model can be classified and predicted based on these multi-dimensional features, such as judging whether a certain trading strategy is feasible under specific market rules, renewable energy generation conditions, and meteorological conditions, as well as the possible benefits and risk ranges. In the model update and iteration module, if it is found that the prediction accuracy of the decision tree model decreases under the new data environment (such as major adjustments to market rules or breakthroughs in new energy technology leading to changes in power generation characteristics), the model update and iteration operation can be started according to the preset conditions (such as the accuracy rate is lower than a certain threshold) to retrain the decision tree model to adapt to the new market situation.

[0191] Working principle of the present invention:

[0192] The working principle of the cross-provincial and cross-regional power medium- and long-term trading continuous operation model analysis system is based on the overall coordination of the central processing module. The system starts with the data acquisition and preprocessing module, which collects data from various power markets, power generation companies, power grid companies, etc. in real time or regularly, and cleans, standardizes and integrates them to ensure data quality. Then, the market dynamic monitoring and analysis module uses real-time and historical data to dynamically monitor and analyze the market to identify abnormal situations and trend changes. The new energy adaptability assessment module focuses on assessing the impact of the volatility and uncertainty of new energy power generation on transactions, and dynamically adjusts the assessment model according to new energy development trends and market rule changes. The transaction strategy optimization module is based on a multi-objective optimization model to formulate the optimal transaction strategy and quotation plan for both parties to the transaction. Finally, the model update and iteration module automatically replaces the analysis model according to the preset conditions to ensure the continuous and effective operation of the system.

[0193] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0194] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions, including a central processing module, characterized in that: The central processing module is signal-connected to a data acquisition and preprocessing module, a market dynamics monitoring and analysis module, a new energy adaptability assessment module, a trading strategy optimization module, and a model update and iteration module; The data collection and preprocessing module collects power transaction data, new energy power generation data, meteorological data, and market rule change information in real time or regularly. After the data is cleaned, standardized, and integrated, it provides a data basis for subsequent analysis; The market dynamic monitoring and analysis module dynamically monitors and analyzes market supply and demand relationships, price trends, and changes in trading rules based on real-time and historical data; The new energy adaptability assessment module compares the actual data of new energy power generation with the forecast data to assess the impact of the volatility and uncertainty of new energy power generation on medium- and long-term power transactions; The trading strategy optimization module builds a multi-objective optimization model to comprehensively consider costs, risks, and benefits to develop the best trading strategy and quotation plan for both parties. The model update and iteration module presets several analysis models and sets the conditions for the use of each analysis model. When the conditions are met, the corresponding analysis model is automatically replaced.

2. The continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions according to claim 1 is characterized by: The central processing module includes the following units: The data scheduling unit coordinates the data flow between various modules to ensure timely and accurate data transmission between the data acquisition and preprocessing module, the market dynamics monitoring and analysis module, the new energy adaptability assessment module, the trading strategy optimization module and the model update and iteration module; The task allocation unit decomposes and allocates the tasks of each module according to system requirements to ensure that each module can work together efficiently and jointly complete the analysis task of the continuous operation model of medium- and long-term power transactions.

3. The continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions according to claim 1 is characterized by: The data acquisition and preprocessing module includes the following units: Real-time data collection unit, real-time collection of power transaction data, new energy power generation data, and meteorological data; Historical data acquisition unit, which regularly acquires historical data for historical data analysis in the market dynamics monitoring and analysis module and the trading strategy optimization module; The data cleaning and standardization unit cleans the collected data, removes duplicate, erroneous or invalid data, and performs standardization processing; The new energy meteorological data correction unit collects wind speed data, wind power generation ratio, sunlight data, and photovoltaic power generation ratio to improve the accuracy of new energy power generation forecast data.

4. A continuous operation model analysis system for inter-provincial and inter-regional medium- and long-term power transactions as claimed in claim 3, characterized in that: The data acquisition and preprocessing module also includes the following units: The first data calculation unit calculates data accuracy, data cleaning rate and new energy power generation ratio based on data from the real-time data acquisition unit, the historical data acquisition unit, the data cleaning and standardization unit and the new energy meteorological data correction unit; wherein, Data accuracy = (correct data volume / total data volume) × 100%; Data cleaning rate = (the amount of cleaned data / the original total amount of data) × 100%; The proportion of power generation from a certain new energy source = (actual power generation from the new energy source / total power generation) × 100%.

5. The continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions according to claim 1 is characterized by: The market dynamics monitoring and analysis module includes the following units: The market supply and demand relationship monitoring unit dynamically monitors and analyzes the market supply and demand relationship based on real-time and historical data, identifies supply and demand imbalances, and provides early warnings for decision makers; The price trend analysis unit monitors and analyzes power transaction prices in real time, identifies price fluctuation trends, and provides price references for the trading strategy optimization module; The trading rule change monitoring unit tracks changes in market rules and promptly identifies and analyzes the impact of rule changes on medium- and long-term power transactions; The new energy power generation impact analysis unit conducts special analysis on the proportion and volatility of new energy power generation, evaluates its impact on medium- and long-term power transactions, and provides decision support for the trading strategy optimization module.

6. The continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions according to claim 1 is characterized by: The market dynamics monitoring and analysis module also includes the following units: The second data calculation unit calculates the supply and demand imbalance, price volatility, rule change impact coefficient, new energy power generation impact rate and price trend prediction accuracy based on the data of the market supply and demand relationship monitoring unit, the price trend analysis unit, the transaction rule change monitoring unit and the new energy power generation impact analysis unit; Among them, supply-demand imbalance = |total supply - total demand| / average demand × 100%; Price volatility = (current price - average price) / average price × 100%; Rule change impact coefficient = (total number of transactions after the change - total number of transactions before the change) / total number of transactions before the change × 100%; Impact rate of new energy power generation = (total amount of transactions including new energy power generation - total amount of transactions without new energy power generation) / total amount of transactions without new energy power generation × 100%; Price trend prediction accuracy = number of correctly predicted price trends / total number of predictions × 100%.

7. The continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions according to claim 5 is characterized by: The new energy power generation impact analysis unit includes: Renewable energy power generation ratio analysis subunit: By comparing historical data with current data, evaluate the changing trend and speed of the proportion of renewable energy power generation; New energy power generation volatility assessment subunit: By analyzing the historical volatility data of new energy power generation, a volatility assessment model is established to predict the volatility of future new energy power generation; Sub-unit for analysis of the impact of renewable energy generation on medium- and long-term electricity transactions: Based on the analysis results of the proportion and volatility of renewable energy generation, the impact of renewable energy generation on medium- and long-term electricity transactions is deeply evaluated. The analysis includes the impact of renewable energy generation on the balance of electricity supply and demand, the impact on electricity price fluctuations, and the impact on the electricity market transaction structure; Among them, the change rate of the proportion of new energy power generation = (the proportion of new energy power generation in this period - the proportion of new energy power generation in the previous period) / the proportion of new energy power generation in the previous period × 100%; Contribution of renewable energy generation to electricity price fluctuations = (electricity price fluctuation rate when renewable energy generation is included - electricity price fluctuation rate when renewable energy generation is not included) / electricity price fluctuation rate when renewable energy generation is included × 100%; Adjustment coefficient of supply and demand balance of new energy power generation = adjustable capacity of new energy power generation / difference between supply and demand in the electricity market; New energy power generation market transaction structure impact index = change in the proportion of new energy power generation transaction amount / change in total electricity transaction amount.

8. The continuous operation model analysis system for medium- and long-term inter-provincial and inter-regional power transactions according to claim 1 is characterized by: The new energy adaptability assessment module includes the following units: The new energy power generation volatility analysis unit compares the actual data of new energy power generation with the forecast data, and evaluates the impact of the volatility of new energy power generation on medium- and long-term power transactions; Uncertainty assessment unit, which assesses the risks brought by the uncertainty of renewable energy generation to medium- and long-term power transactions, and provides a risk assessment basis for the trading strategy optimization module; The evaluation model dynamic adjustment unit dynamically adjusts the evaluation model according to the development trend of new energy power generation and changes in market rules to ensure the accuracy and adaptability of the evaluation results.

9. The continuous operation model analysis system for inter-provincial and inter-regional medium- and long-term power transactions according to claim 1, characterized in that: The trading strategy optimization module includes the following units: Cost-benefit analysis unit, which conducts comprehensive analysis of the costs and benefits of trading strategies to provide data support for formulating optimal trading strategies; The Risk Assessment and Response Unit assesses the risks posed by the volatility of renewable energy generation and designs flexible trading strategies to address these risks; The quotation proposal formulation unit formulates quotation proposals for both parties to the transaction based on the results of cost-benefit analysis and risk assessment.

10. The inter-provincial and inter-regional medium- and long-term electricity transaction continuous operation model analysis system according to claim 1, characterized in that: The model update and iteration module includes the following units: An analysis model presetting unit is used to preset several analysis models for analyzing the continuous operation model of medium- and long-term power transactions; Model usage condition setting unit, which sets the usage conditions for each analysis model to ensure that the corresponding analysis model can be automatically replaced under specific circumstances; The model update and iteration execution unit automatically executes the model update and iteration operations when the conditions are met to ensure the accuracy and applicability of the analysis model.

Images