Electric power spot market clearing model optimization method, device, equipment and medium

Abstract

The invention discloses an electric power spot market clearing model optimization method and device, equipment and a medium, and the method comprises the steps: constructing a market clearing model with the minimum power generation total cost and the maximum social welfare as targets based on historical power generation data, load data and market transaction data, solving the market clearing model based on a set constraint condition to obtain a first market clearing result; target parameters in the market clearing model are adjusted to solve the market clearing model, and a second market clearing result is obtained; calculating the sensitivity corresponding to the target parameter according to the first and second market clearing results; and performing descending sorting on the sensitivities, selecting target parameters corresponding to the previous target number of sensitivities as key parameters, optimizing the key parameters by adopting a genetic algorithm to obtain an optimized market clearing model, and applying the optimized market clearing model to market clearing prediction. The key parameters of the market clearing model are optimized, and the accuracy of the model output result is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power market data processing, and in particular to a method, device, equipment and medium for optimizing a power spot market clearing model. Background Art

[0002] In the electricity spot market, achieving efficient market clearing is crucial for the rational allocation of power resources. Accurate market clearing can balance power generation and load demand, reduce power generation costs, and improve the safety and economy of grid operation. However, current electricity spot market clearing faces numerous challenges. First, power generation data, load data, and market transaction data in the electricity market are complex and volatile, subject to uncertainty and volatility. Traditional methods struggle to accurately capture these data characteristics and the interrelationships between parameters. Second, existing clearing optimization models often fail to fully account for factors such as the cost characteristics of generators, load uncertainty, and the physical and economic constraints of the grid, limiting their accuracy and practicality. Furthermore, there is a lack of scientific and effective methods for configuring key model parameters. Improper parameter settings can lead to significant deviations in model output, making them unable to meet the actual operational needs of the market. Summary of the Invention

[0003] The present application provides a method, device, equipment and medium for optimizing an electricity spot market clearing model, which is used to improve the technical problem that the key parameters of the existing electricity spot market clearing model are irrational, resulting in low accuracy of the model output results.

[0004] In view of this, the first aspect of this application provides a method for optimizing a power spot market clearing model, comprising:

[0005] Obtain historical power generation data, load data and market transaction data;

[0006] constructing a market clearing model with the objectives of minimizing total power generation cost and maximizing social welfare based on the historical power generation data, the load data, and the market transaction data, and solving the market clearing model based on set constraints to obtain a first market clearing result;

[0007] adjusting target parameters in the market-clearing model, solving the market-clearing model based on the adjusted target parameters, and obtaining a second market-clearing result;

[0008] The sensitivity corresponding to the target parameter is calculated based on the first market-clearing result and the second market-clearing result; the sensitivities are sorted in descending order, the target parameters corresponding to the first target number of sensitivities are selected as key parameters, and the key parameters are optimized using a genetic algorithm to obtain an optimized market-clearing model, and the optimized market-clearing model is used for market-clearing prediction.

[0009] Optionally, the constraints include generator set capacity constraints, generator set ramp rate constraints, generator start-up and shutdown cost constraints, load uncertainty constraints, transmission line capacity constraints, node voltage constraints and transmission cost constraints.

[0010] Optionally, calculating the sensitivity corresponding to the target parameter according to the first market clearing result and the second market clearing result includes:

[0011] calculating an adjustment amount between the target parameter and the adjusted target parameter, and calculating a ratio of the adjustment amount to the target parameter to obtain a first ratio;

[0012] calculating a deviation between the first market-clearing result and the second market-clearing result, and calculating a ratio of the deviation to the first market-clearing result to obtain a second ratio;

[0013] The ratio of the second ratio to the first ratio is calculated to obtain the sensitivity corresponding to the target parameter.

[0014] Optionally, the acquiring of historical power generation data, load data, and market transaction data further includes:

[0015] The Pearson correlation coefficient is used to calculate the correlation among the historical power generation data, the load data and the market transaction data, and data screening is performed on the historical power generation data, the load data and the market transaction data based on the correlation.

[0016] Optionally, the method further includes:

[0017] Acquiring historical market environment data to generate simulation data, inputting the simulation data into the optimized market clearing model, and obtaining a simulated market clearing result;

[0018] The effectiveness of the optimized market clearing model is evaluated based on the simulated market clearing results and the historical actual market clearing results. If the evaluation results do not meet the preset requirements, the key parameters are optimized again.

[0019] Optionally, the method further includes:

[0020] perturbing the simulated data, inputting the perturbed simulated data into the optimized market clearing model, and obtaining a perturbed simulated market clearing result;

[0021] The stability of the optimized market clearing model is evaluated based on the simulated market clearing results before and after the disturbance. If the evaluation results do not meet the preset requirements, the key parameters are optimized again.

[0022] Optionally, the method further includes:

[0023] Inputting the simulated data into the market clearing model before optimization to obtain the simulated market clearing result before optimization;

[0024] The total power generation cost and social welfare before and after optimization are calculated based on the simulated market clearing results before and after optimization. The economic evaluation of the optimized market clearing model is carried out based on the total power generation cost and social welfare before and after optimization. If the evaluation results do not meet the preset requirements, the key parameters are optimized again.

[0025] A second aspect of the present application provides an optimization device for a power spot market clearing model, comprising:

[0026] Data acquisition unit, used to obtain historical power generation data, load data and market transaction data;

[0027] a model building unit, configured to build a market clearing model with the objectives of minimizing total power generation cost and maximizing social welfare based on the historical power generation data, the load data, and the market transaction data, and solve the market clearing model based on set constraints to obtain a first market clearing result;

[0028] a parameter adjustment unit, configured to adjust target parameters in the market-clearing model, and solve the market-clearing model based on the adjusted target parameters to obtain a second market-clearing result;

[0029] a parameter optimization unit for calculating the sensitivity corresponding to the target parameter based on the first market-clearing result and the second market-clearing result; sorting the sensitivities in descending order, selecting the target parameters corresponding to the first target number of sensitivities as key parameters, and optimizing the key parameters using a genetic algorithm to obtain an optimized market-clearing model, wherein the optimized market-clearing model is used for market-clearing prediction.

[0030] A third aspect of the present application provides an electronic device, the device comprising a processor and a memory;

[0031] The memory is used to store program code and transmit the program code to the processor;

[0032] The processor is used to execute the electricity spot market clearing model optimization method described in any one of the first aspects according to the instructions in the program code.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium for storing program code. When the program code is executed by a processor, the method for optimizing the electricity spot market clearing model described in any one of the first aspects is implemented.

[0034] It can be seen from the above technical solutions that this application has the following advantages:

[0035] The present application provides an optimization method for an electricity spot market clearing model. By performing sensitivity analysis on model parameters, the degree of influence of each parameter on the model output result is clarified, and a genetic algorithm is used to perform key optimization on key parameters with greater influence. The optimal parameter combination can be found under complex constraints, so that the model is more in line with the actual market operation situation, the accuracy of the model output result is improved, and more reasonable decision support is provided for market clearing, thereby improving the technical problem that the key parameter configuration of the existing electricity spot market clearing model is unreasonable, resulting in low accuracy of the model output result. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0037] Figure 1 A flow chart of a method for optimizing a power spot market clearing model provided in an embodiment of the present application;

[0038] Figure 2 A structural schematic diagram of an electricity spot market clearing model optimization device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0040] For easier understanding, please refer to Figure 1 , an embodiment of the present application provides a method for optimizing a power spot market clearing model, comprising:

[0041] Step 110: Acquire historical power generation data, load data, and market transaction data;

[0042] Collect historical power generation data (including the power output of different generators) from various data sources in the power market, such as power generation enterprise monitoring systems, load monitoring terminals, market trading platforms, etc. , power generation costs etc.), load data (different regions , different time periods Load demand ), market transaction data (transaction price , trading volume etc.) to ensure the integrity, accuracy and time series continuity of the data and provide a reliable data basis for subsequent analysis. Indicates the generator set number, Indicates the generator set type number, Indicates time, Indicates an area.

[0043] After obtaining the aforementioned electricity spot market data, statistical analysis methods can be used to process the collected electricity spot market data. Particular attention is paid to important parameters closely related to the operation of the electricity spot trading market, such as power generation costs, load demand, and electricity prices. These important parameters are related to the performance and profitability of each market participant in the electricity spot market. The statistical indicators of important parameters are calculated as follows:

[0044] Average power generation cost:

[0045]

[0046] in, is the number of data samples, It represents the average power generation cost of a certain type of generator set, reflecting the average level of power generation cost of this type of generator set;

[0047] Load demand variance:

[0048]

[0049] in, is the average load demand in a certain area, It indicates the degree of dispersion of load demand in the area. The larger the variance, the greater the load fluctuation.

[0050] Electricity price skewness:

[0051]

[0052] in, is the average electricity price, is the standard deviation of electricity prices, and the electricity price skewness is used to measure the asymmetry of the distribution of electricity price data;

[0053] Power generation peak:

[0054]

[0055] in, is the average power output of type g generator set, is the standard deviation of the power output of type g generator set; the power output kurtosis reflects the peak degree of the power output data distribution.

[0056] It is also possible to conduct correlation analysis on the collected electricity spot market data and screen the electricity spot market data based on the correlation between the electricity spot market data. The Pearson correlation coefficient can be used to calculate the relationship between important parameters, such as the relationship between power generation cost and power generation output. and power generation output The Pearson correlation coefficient calculation formula is:

[0057]

[0058] in, The closer the value is to 1 or -1, the stronger the correlation; the closer it is to 0, the weaker the correlation. The purpose of calculating correlation between parameters is to avoid duplication and to select parameters with minimal correlation, thus enabling a multi-dimensional assessment of market conditions. If the correlation between two parameters is equal to 1, only one of them needs to be selected.

[0059] The autoregressive moving average model can also be used to perform time series analysis on the collected electricity spot market data. Taking load demand as an example, the corresponding autoregressive moving average model expression is:

[0060]

[0061] in, 、 is the model order, 、 are model parameters, is a white noise sequence. Through model identification, parameter estimation and model testing, the model parameters are determined, thereby identifying the changing trend of load demand over time, such as seasonal fluctuations and long-term changing trends of load.

[0062] Step 120: construct a market clearing model based on historical power generation data, load data, and market transaction data with the objectives of minimizing total power generation cost and maximizing social welfare, and solve the market clearing model based on set constraints to obtain a first market clearing result;

[0063] This application takes minimizing the total cost of power generation TC as the main optimization goal. The objective function corresponding to the minimum total cost of power generation is:

[0064]

[0065] Then, based on minimizing the total cost of power generation TC, we consider maximizing social welfare. The objective function corresponding to maximizing social welfare is:

[0066]

[0067] Where, is the power generation cost of type g generator set i at time t, is the power output of type g generator set i at time t, is the electricity transaction price in region r at time t, is the electricity trading volume in region r at time t. Under the premise of meeting load demand, by rationally arranging the power output of generators, we can achieve optimal allocation of power resources, reduce power generation costs, and improve the overall economic benefits of society.

[0068] The embodiments of the present application take into account multiple constraints, including generator set capacity constraints, generator set ramp rate constraints, generator start and stop cost constraints, load uncertainty constraints, transmission line capacity constraints, node voltage constraints and transmission cost constraints.

[0069] The generator capacity constraint is:

[0070]

[0071] in, and These are the minimum and maximum power outputs of the i-type g-type generator set, ensuring that the generator set operates within a safe and stable range to avoid over- or under-generation.

[0072] The generator set ramp rate constraint is:

[0073]

[0074] in, and They are the upward and downward climbing rates of the i-type g generator set, respectively, which limit the upper limit of the unit's power output change per unit time;

[0075] Generator start-up and shutdown cost constraints:

[0076]

[0077] in, and are the starting cost and stopping cost of the i-type g generator set, It is the start / stop status of the type g generator set i at time t (1 means running, 0 means stopped).

[0078] Load uncertainty constraint: The normal distribution model is used to describe the load uncertainty, and the load demand forecast value is set to , the standard deviation is , then the actual load demand satisfy:

[0079]

[0080] The above expression shows that the actual load demand Obey the mean , the variance is When building electricity market clearing models, this normal distribution characteristic is used to account for load uncertainty. For example, when setting power supply plans, the probabilistic characteristics of the normal distribution are used to ensure that sufficient power is available to meet potential load demands under different confidence intervals, thereby safeguarding the reliability and stability of the power system. By setting confidence intervals for load demand forecasts, such as a 95% confidence interval, load uncertainty is incorporated into model constraints, ensuring that power demand can be met under different load conditions.

[0081] The transmission line capacity constraint is:

[0082]

[0083] in, shows the set of generators connected to line l, The maximum transmission capacity of the line is l, ensuring the safety and reliability of the power grid operation;

[0084] The node voltage constraints are:

[0085]

[0086] in, is the voltage of node n at time t, and are the lower and upper voltage limits of the n-node respectively;

[0087] The transmission cost constraint is:

[0088]

[0089] in, is the unit transmission cost of line l, The transmission power of line l at time t is used to optimize the transmission path of electricity in the power grid and reduce the transmission cost.

[0090] Based on the above optimization objectives and constraints, a mixed integer programming model is constructed. The model is solved using professional optimization algorithms, such as branch and bound method, cutting plane method, etc., to find the optimal solution through iterative calculation. The first market clearing result output by the model includes the power output of each generator set. , electricity trading volume , market clearing price These results provide a basis for decision-making by electricity market participants, such as power generation companies arranging production based on power output and market managers formulating policies based on market clearing prices.

[0091] Step 130: Adjust the target parameters in the market-clearing model, solve the market-clearing model based on the adjusted target parameters, and obtain a second market-clearing result;

[0092] Based on collected historical data and expert experience, initial values are set for the model's target parameters (including power generation cost, average power generation cost, load demand, and electricity price). For power generation cost parameters, the average cost of different generator types is determined based on statistical analysis of historical power generation cost data and the actual cost structure of power generation companies. Parameters for load demand calculation are set based on the distribution characteristics of historical load data and expert judgment of load fluctuation patterns.

[0093] Adjust the target parameter while keeping other parameters unchanged, and obtain the second market clearing result of the market clearing model with the adjusted target parameter.

[0094] Step 140: Calculate the sensitivity corresponding to the target parameter based on the first market clearing result and the second market clearing result; sort the sensitivities in descending order, select the target parameters corresponding to the first target number of sensitivities as key parameters, and optimize the key parameters using a genetic algorithm to obtain an optimized market clearing model.

[0095] Using sensitivity analysis, we study the impact of changes in the model's target parameters on the model's output, thereby identifying the key parameters with the greatest impact on the model's results. We calculate the adjustment between the target parameter and the adjusted target parameter, and then calculate the ratio of the adjustment to the target parameter to obtain a first ratio. We also calculate the deviation between the first market-clearing result and the second market-clearing result, and then calculate the ratio of the deviation to the first market-clearing result to obtain a second ratio. We then calculate the ratio of the second ratio to the first ratio to obtain the sensitivity of the target parameter.

[0096] Sensitivity is the effect of the calculated target parameter on a certain output indicator, but this output indicator will affect other output indicators. For example, the adjustment of power generation cost will affect the total power generation cost, and the total power generation cost will affect the output indicators such as the clearing transaction volume and price in the clearing model. For example, change its value to , The adjustment amount of the mean power generation cost, while keeping other parameters unchanged, obtain the output of the market clearing model at this time. Observe the total power generation cost output by the model , power generation output , electricity trading volume , market clearing price Changes in indicators such as power generation cost. The sensitivity calculation formula for the total cost of power generation TC is:

[0097]

[0098] Sensitivities are sorted in descending order, and the target parameters corresponding to the first target number of sensitivities are selected as key parameters. For example, a 5% increase in the average power generation cost yields a new set of outputs (e.g., a 3% increase in total cost, a 6% decrease in output, a 4% decrease in traded electricity, and a 2% increase in price). A 10% increase in the average power generation cost yields yet another set of outputs. Generally, the market focuses on trading volume and clearing price, so the key objective is to examine the impact of changes in different target parameters on key outputs (traded electricity volume and market-clearing price). The target parameter with the most significant change is considered the most influential, and is designated the first key parameter. This ranking of the importance of the key parameters is then determined using a genetic algorithm to optimize the key parameters, resulting in an optimized market-clearing model. This optimization is guided by objective functions such as minimizing total power generation cost. While satisfying model constraints, the optimal or suboptimal parameter combinations are found through iterative calculations. The main steps of genetic algorithms include encoding (converting parameters into genetic codes), initializing the population, calculating fitness (calculating individual fitness based on the objective function), selection (selecting excellent individuals based on fitness), crossover (exchanging individual gene fragments), and mutation (randomly changing gene values). Continuous iterative optimization ensures that the model output results are more in line with actual market operations.

[0099] Furthermore, after obtaining the optimized market clearing model, it can be simulated and verified.

[0100] The optimized parameter configuration scheme is applied to a simulated electricity market environment for verification. Using historical data or simulated data generated based on actual market conditions as input data for the simulation environment, the optimized electricity market clearing model is run to obtain the simulated market clearing results.

[0101] The effectiveness, stability and economy of the optimization scheme can be evaluated from multiple aspects.

[0102] Effectiveness evaluation: The effectiveness of the optimized market clearing model is evaluated based on the simulated market clearing results and the historical actual market clearing results. If the evaluation results do not meet the preset requirements, the key parameters are optimized again. By comparing the simulated clearing results with the actual historical market clearing results, the mean square error (MSE) can be used to evaluate the degree of fit of the model to the actual market operation. Taking power generation as an example, the formula for calculating the mean square error of power generation output is:

[0103]

[0104] in, To simulate the cleared power generation output, is the actual historical power generation output. The smaller the MSE, the higher the effectiveness of the optimized electricity market clearing model.

[0105] Stability assessment: Perturb the simulation data, input the perturbed simulation data into the optimized market-clearing model, and obtain the simulated market-clearing results after the perturbation; conduct a stability assessment on the optimized market-clearing model based on the simulated market-clearing results before and after the perturbation. If the assessment results do not meet the preset requirements (which can be set according to actual conditions), optimize the key parameters again.

[0106] In a simulation environment, we perturb the input data to a certain degree (for example, increasing load uncertainty to 1.2 times the original load standard deviation, or changing the generation cost data to cause it to fluctuate randomly within a certain range) and observe how the output of the optimized market-clearing model changes. If the model output fluctuates slightly, it indicates that the optimized market-clearing model has good stability under different market conditions.

[0107] Economic evaluation: Input the simulation data into the market clearing model before optimization to obtain the simulated market clearing results before optimization; calculate the total power generation cost and social welfare before and after optimization based on the simulated market clearing results before and after optimization; and conduct an economic evaluation of the optimized market clearing model based on the total power generation cost and social welfare before and after optimization. If the evaluation results do not meet the preset requirements, the key parameters will be optimized again.

[0108] Calculate the total cost of electricity generation in the optimized simulated market clearing results , social welfare and other economic indicators, and compared with the total power generation cost in the simulated market clearing results before optimization , social welfare Compare and calculate the total cost reduction rate of power generation and the social welfare improvement rate. The formula for calculating the total cost reduction rate of power generation is:

[0109]

[0110] The formula for calculating the social welfare improvement rate is:

[0111]

[0112] If the total cost of power generation decreases and social welfare increases, the optimized market-clearing model has better economic efficiency. If the total cost of power generation decreases and social welfare decreases, the optimized market-clearing model has poor economic efficiency and further optimization of key parameters is needed.

[0113] Furthermore, during the actual operation of the electricity market, key parameters in the model can be updated promptly based on real-time market changes (such as new generators, sudden load changes, and grid failures) and policy adjustments (such as electricity pricing and subsidy policies). For example, when a new generator is put into operation, the generator's parameter information (such as the average power generation cost and capacity limit) is updated; when the load changes abnormally, the parameters of the load demand calculation model are readjusted.

[0114] Furthermore, a market operation data collection mechanism can be established to collect real-time data on the actual operation of the power market, including power generation data, load data, and market transaction data. This data can be compared and analyzed with the model's predictions to evaluate the effectiveness of the current parameter configuration. If a significant deviation between the model's predictions and actual conditions is found, the model parameters can be further optimized using the aforementioned parameter adjustment method based on the deviation and market trends, achieving dynamic optimization of the model to adapt to the ever-changing power market environment.

[0115] The present invention has the following advantages due to the adoption of the above technical solution:

[0116] (1) Data-driven accurate decision-making: During the data collection and analysis phase, all types of power market data are comprehensively collected, and the changing trends and interrelationships of key parameters are deeply explored. Through detailed statistical analysis, correlation analysis, and time series analysis, the data characteristics can be accurately grasped. This provides a solid data foundation for model construction and parameter setting, avoiding decision-making bias caused by insufficient data or in-depth analysis in traditional methods. For example, through accurate load forecasting and power generation cost analysis, power generation plans can be arranged more reasonably, the accuracy of power resource allocation can be improved, and the waste of power generation resources can be reduced.

[0117] (2) Model construction that comprehensively considers complex factors: The constructed power market clearing model comprehensively covers multiple factors such as the cost characteristics of power generation units, load uncertainty, and the physical and economic constraints of the power grid. Compared with traditional models, it can more realistically reflect the actual operation of the power market. Taking load uncertainty as an example, a normal distribution model is used to describe it and incorporate model constraints to ensure that the reliability of power supply can be guaranteed under different load conditions. At the same time, considering various constraints of the power grid helps to improve the safety and stability of power grid operation and ensure the stable operation of the power market.

[0118] (3) Scientific parameter setting and optimization: During the parameter setting and adjustment process, the initial parameters are set based on historical data and expert experience, and then adjusted using sensitivity analysis and optimization algorithms. This method can quickly find the optimal or suboptimal parameter configuration scheme, significantly improving the accuracy and practicality of the model. Through sensitivity analysis, the influence of each parameter on the model output can be clearly determined, and key parameters can be optimized. The optimization algorithm can find the best parameter combination under complex constraints, making the model more consistent with the actual market operation and providing more reasonable decision support for market clearing.

[0119] (4) Strict verification and evaluation to ensure effectiveness: During the verification and evaluation phase, the optimized parameter configuration scheme is applied to the simulation environment and comprehensively evaluated from multiple dimensions such as effectiveness, stability, and economy. The reliability of the model and parameter configuration scheme is ensured by comparing with actual historical data, performing perturbation tests on input data, and calculating economic indicators. For example, the degree of fit of the model to the actual market operation is evaluated through indicators such as mean square error, and the economic feasibility of the optimization scheme is measured through indicators such as the total power generation cost reduction rate and the social welfare improvement rate, providing strong guarantees for the actual application of the model.

[0120] (5) Real-time feedback and dynamic optimization to adapt to market changes: In the actual operation of the power market, key parameters are updated in real time and a feedback mechanism is established. Model parameters are adjusted promptly according to market changes and policy adjustments, so that the model can adapt to the ever-changing market environment. By collecting market operation data in real time and comparing actual data with model prediction results, problems are promptly identified and optimized to ensure that the model can always accurately reflect market conditions, provide continuous and effective support for real-time decision-making in the power market, and improve the power market's adaptability and operational efficiency.

[0121] (6) Broad application prospects and comprehensive benefit improvement: The optimized electricity spot market clearing model and key parameter configuration method of this application have broad application prospects and can be applied to various electricity market scenarios. By optimizing market clearing, it can reduce power generation costs, improve social welfare, and enhance the overall economic benefits of the electricity market. At the same time, it can ensure the safe and stable operation of the power grid and improve the reliability of power supply, which is of great significance to promoting the sustainable development of the power industry and provides strong technical support for the healthy development of the power market.

[0122] Please refer to Figure 2 , the embodiment of the present application further provides an electricity spot market clearing model optimization device, comprising:

[0123] Data acquisition unit 210, used to acquire historical power generation data, load data and market transaction data;

[0124] A model building unit 220 is configured to build a market clearing model with the objectives of minimizing total power generation costs and maximizing social welfare based on historical power generation data, load data, and market transaction data, and solve the market clearing model based on set constraints to obtain a first market clearing result;

[0125] a parameter adjustment unit 230 for adjusting target parameters in the market-clearing model, solving the market-clearing model based on the adjusted target parameters, and obtaining a second market-clearing result;

[0126] The parameter optimization unit 240 is used to calculate the sensitivity corresponding to the target parameter based on the first market clearing result and the second market clearing result; sort the sensitivities in descending order, select the target parameters corresponding to the first target number of sensitivities as key parameters, and optimize the key parameters using a genetic algorithm to obtain an optimized market clearing model. The optimized market clearing model is used for market clearing prediction.

[0127] Furthermore, when the parameter optimization unit 240 is used to calculate the sensitivity corresponding to the target parameter according to the first market clearing result and the second market clearing result, it is specifically used to:

[0128] calculating an adjustment amount between the target parameter and the adjusted target parameter, and calculating a ratio of the adjustment amount to the target parameter to obtain a first ratio;

[0129] Calculating the deviation between the first market clearing result and the second market clearing result, and calculating the ratio of the deviation to the first market clearing result to obtain a second ratio;

[0130] The ratio of the second ratio to the first ratio is calculated to obtain the sensitivity corresponding to the target parameter.

[0131] Furthermore, the device also includes a data screening unit for calculating the correlation between historical power generation data, load data and market transaction data using the Pearson correlation coefficient, and screening the historical power generation data, load data and market transaction data based on the correlation.

[0132] Furthermore, the device also includes a model verification unit, which is used to obtain historical market environment data to generate simulation data, input the simulation data into the optimized market clearing model, and obtain the simulated market clearing results; based on the simulated market clearing results and the historical actual market clearing results, the effectiveness of the optimized market clearing model is evaluated. If the evaluation results do not meet the preset requirements, the parameter optimization unit 240 is triggered.

[0133] Furthermore, the model verification unit is also used to perturb the simulation data, input the perturbed simulation data into the optimized market clearing model, and obtain the simulated market clearing results after the perturbation; and perform stability evaluation on the optimized market clearing model based on the simulated market clearing results before and after the perturbation. If the evaluation result does not meet the preset requirements, the parameter optimization unit 240 is triggered.

[0134] Furthermore, the model verification unit is also used to input simulation data into the market clearing model before optimization to obtain the simulated market clearing results before optimization; calculate the total power generation cost and social welfare before and after optimization based on the simulated market clearing results before and after optimization; and perform an economic evaluation of the optimized market clearing model based on the total power generation cost and social welfare before and after optimization. If the evaluation result does not meet the preset requirements, the parameter optimization unit 240 is triggered.

[0135] An embodiment of the present application further provides an electronic device, the device including a processor and a memory;

[0136] The memory is used to store program codes and transmit the program codes to the processor;

[0137] The processor is used to execute the electricity spot market clearing model optimization method in the aforementioned method embodiment according to the instructions in the program code.

[0138] An embodiment of the present application also provides a computer-readable storage medium, which is used to store program code. When the program code is executed by a processor, it implements the electricity spot market clearing model optimization method in the aforementioned method embodiment.

[0139] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] In the specification of this application and the above-mentioned drawings, the terms "first," "second," "third," "fourth," etc. (if any) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, product, or apparatus.

[0141] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or plural.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0145] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name: Read-Only Memory, English abbreviation: ROM), random access memory (full name: Random Access Memory, English abbreviation: RAM), disk or optical disk, and other media that can store program code.

[0146] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing a power spot market clearing model, characterized in that: include: Obtain historical power generation data, load data and market transaction data; constructing a market clearing model with the objectives of minimizing total power generation cost and maximizing social welfare based on the historical power generation data, the load data, and the market transaction data, and solving the market clearing model based on set constraints to obtain a first market clearing result; adjusting target parameters in the market-clearing model, solving the market-clearing model based on the adjusted target parameters, and obtaining a second market-clearing result; Calculating the sensitivity corresponding to the target parameter according to the first market clearing result and the second market clearing result; The sensitivities are sorted in descending order, target parameters corresponding to the first target number of sensitivities are selected as key parameters, and the key parameters are optimized using a genetic algorithm to obtain an optimized market-clearing model, which is used for market-clearing prediction.

2. The electricity spot market clearing model optimization method according to claim 1, characterized in that: The constraints include generator set capacity constraints, generator set ramp rate constraints, generator start-up and shutdown cost constraints, load uncertainty constraints, transmission line capacity constraints, node voltage constraints and transmission cost constraints.

3. The electricity spot market clearing model optimization method according to claim 1, characterized in that: The calculating the sensitivity corresponding to the target parameter according to the first market clearing result and the second market clearing result includes: calculating an adjustment amount between the target parameter and the adjusted target parameter, and calculating a ratio of the adjustment amount to the target parameter to obtain a first ratio; Calculating a deviation between the first market-clearing result and the second market-clearing result, and calculating a ratio of the deviation to the first market-clearing result to obtain a second ratio; The ratio of the second ratio to the first ratio is calculated to obtain the sensitivity corresponding to the target parameter.

4. The electricity spot market clearing model optimization method according to claim 1, characterized in that: The acquisition of historical power generation data, load data and market transaction data further includes: The Pearson correlation coefficient is used to calculate the correlation among the historical power generation data, the load data and the market transaction data, and data screening is performed on the historical power generation data, the load data and the market transaction data based on the correlation.

5. The electricity spot market clearing model optimization method according to claim 1, characterized in that: The method further comprises: Acquiring historical market environment data to generate simulation data, inputting the simulation data into the optimized market clearing model, and obtaining a simulated market clearing result; The effectiveness of the optimized market clearing model is evaluated based on the simulated market clearing results and the historical actual market clearing results. If the evaluation results do not meet the preset requirements, the key parameters are optimized again.

6. The electricity spot market clearing model optimization method according to claim 5, characterized in that: The method further comprises: perturbing the simulated data, inputting the perturbed simulated data into the optimized market clearing model, and obtaining a perturbed simulated market clearing result; The stability of the optimized market clearing model is evaluated based on the simulated market clearing results before and after the disturbance. If the evaluation results do not meet the preset requirements, the key parameters are optimized again.

7. The electricity spot market clearing model optimization method according to claim 5, characterized in that: The method further comprises: Inputting the simulated data into the market clearing model before optimization to obtain the simulated market clearing result before optimization; The total power generation cost and social welfare before and after optimization are calculated based on the simulated market clearing results before and after optimization. The economic evaluation of the optimized market clearing model is carried out based on the total power generation cost and social welfare before and after optimization. If the evaluation results do not meet the preset requirements, the key parameters are optimized again.

8. An electricity spot market clearing model optimization device, characterized in that: include: Data acquisition unit, used to obtain historical power generation data, load data and market transaction data; a model building unit, configured to build a market clearing model with the objectives of minimizing total power generation cost and maximizing social welfare based on the historical power generation data, the load data, and the market transaction data, and solve the market clearing model based on set constraints to obtain a first market clearing result; a parameter adjustment unit, configured to adjust target parameters in the market-clearing model, and solve the market-clearing model based on the adjusted target parameters to obtain a second market-clearing result; a parameter optimization unit, configured to calculate the sensitivity corresponding to the target parameter according to the first market clearing result and the second market clearing result; The sensitivities are sorted in descending order, target parameters corresponding to the first target number of sensitivities are selected as key parameters, and the key parameters are optimized using a genetic algorithm to obtain an optimized market-clearing model, which is used for market-clearing prediction.

9. An electronic device, characterized in that: The device includes a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the electricity spot market clearing model optimization method according to any one of claims 1 to 7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program code, and when the program code is executed by the processor, it implements the electricity spot market clearing model optimization method according to any one of claims 1 to 7.

Images