Simulation clearing factor tracing method and device for regional electric power spot market

Abstract

The invention provides a simulation clearing factor traceability method and device for a regional electric power spot market. The method comprises the following steps: obtaining a simulation clearing result for the regional electric power spot market; if the simulation clearing result does not meet the preset constraint condition, triggering a clearing factor traceability process; the clearing factor traceability process comprises the following steps: acquiring original input data of a simulation model oriented to a regional electric power spot market; calculating a sensitivity index of each factor to the simulation clearing result according to the original input data and the simulation clearing result; taking the factors of which the sensitivity indexes of the factors to the clearing results are greater than a third threshold value as key factors after screening; inputting the screened key factors into a traceability model to obtain the contribution degree of each key factor to the simulation clearing result deviation; and if the contribution degree of the key factor to the simulation clearing result deviation is greater than a decision threshold, the factor is the main cause of the simulation clearing result deviation.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and in particular to a method and device for tracing the source of simulated clearing factors in a regional electric power spot market. Background Art

[0002] As energy transition accelerates, the development of regional electricity spot markets, a core component, is booming and expanding. While existing research has achieved initial success in power market simulation, by constructing mathematical models based on optimization theory and developing simulation platforms that incorporate physical constraints and economic logic, initial simulations of market operations have been achieved. However, significant deficiencies remain in the two core areas of identifying key factors and tracing the provenance of simulation results.

[0003] When it comes to analyzing key factors, most studies are limited to isolating single variables, such as renewable energy penetration, load forecasting errors, and generator bidding strategies, to explore their impact on market-clearing prices and traded electricity. This "variable-disaggregation" approach overlooks the complex multi-agent dynamics within the power system, such as the coupling effect between renewable energy output fluctuations and load forecasting errors, or the dynamic interplay between generator bidding strategies and grid congestion management. This makes it difficult for these conclusions to fully reflect the true mechanisms of market operation.

[0004] The traceability of simulation results also faces technical bottlenecks. Power market simulation systems involve thousands of input parameters and operational constraints. When simulation results deviate from actual market data, existing research often relies on manual experience-based troubleshooting and lacks a systematic error diagnosis framework. For example, during a provincial power market simulation, a clearing result showed abnormal price fluctuations. However, due to a lack of effective data tracking and causal analysis tools, technicians spent weeks locating the cause as a conflict between transmission congestion parameter settings and renewable energy ramp-up constraints.

[0005] This inefficient traceability mechanism not only restricts the iterative optimization efficiency of the simulation model, but may also create risks in the market rule design stage, resulting in operating conditions that are inconsistent with expectations when the rules are implemented. Summary of the Invention

[0006] Based on this, the present invention provides a simulation clearing factor tracing method for the regional electricity spot market. By constructing a multi-factor interaction model, a key factor identification method, a simulation result tracing framework, and a data-driven tracing algorithm, it realizes the key factor analysis and precise tracing of the market simulation clearing results, thereby improving the accuracy and traceability of market simulation.

[0007] In a first aspect, the present invention provides a method for tracing the source of simulated clearing factors in a regional electricity spot market, comprising:

[0008] Obtain simulation clearing results for the regional electricity spot market;

[0009] If the simulation clearing result does not meet the preset constraints, the clearing factor tracing process is triggered;

[0010] The clearing factor tracing process includes the following steps:

[0011] Obtaining raw input data for simulation models targeting regional electricity spot markets;

[0012] Calculating the sensitivity index of each factor to the simulated clearing result based on the original input data and the simulated clearing result;

[0013] Factors whose sensitivity index to the liquidation results is greater than the third threshold are taken as the key factors after screening;

[0014] Input the screened key factors into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result;

[0015] If the contribution of the key factor to the deviation of the simulation clearing result is greater than the decision threshold, then the factor is the main cause of the deviation of the simulation clearing result.

[0016] Wherein, the simulation clearing result includes clearing price and clearing quantity;

[0017] The simulation clearing result does not meet the preset constraint conditions, including that the clearing price deviation rate exceeds a first preset threshold or the clearing electricity quantity deviation exceeds a second preset threshold.

[0018] Furthermore, the original input data of the simulation model includes: a power supply side factor set, a load side factor set, a grid side factor set and a market side factor set;

[0019] The power supply side factor set includes wind power output forecast value, photovoltaic output forecast value, unit start-up and shutdown costs and quotation strategy;

[0020] The load side factor set includes load peak-valley difference, load forecast curve and elastic coefficient;

[0021] The grid-side factor set includes line congestion rate and node marginal price;

[0022] The market-side factor set includes trading rule parameters and competitors' historical quotes.

[0023] Furthermore, the sensitivity index of each factor to the simulated clearing result is calculated based on the original input data and the simulated clearing result, specifically:

[0024] ,

[0025] in, Factor Changes in market clearing outcome indicators Variance The contribution of Factor The main effect variance of After that, the variance of the conditional expectation of the output result when other factors change, , is the variance of the market clearing outcome indicator, .

[0026] Furthermore, the filtered key factors are input into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result:

[0027] ,

[0028] in, The key factor Contribution to the deviation of simulation clearing results, The key factor The change in the deviation rate for each standard deviation change is To simulate the prediction deviation of the clearing results, Factor The standard deviation of It is the reference value for clearing results.

[0029] Furthermore, the simulated clearing factor tracing method for the regional electricity spot market also includes: encrypting and storing the original input data, simulated clearing results and main incentives of the clearing factor tracing process in the blockchain using a hash encryption algorithm, and generating a unique traceability certificate.

[0030] Furthermore, the simulation clearing factor tracing method for the regional electricity spot market also includes: establishing a tracing case library based on several original input data of the simulation model for the regional electricity spot market, the corresponding simulation clearing results and main incentives; combining the tracing case library, and obtaining corresponding predicted clearing results and predicted incentives based on the real-time input data for the regional electricity spot market.

[0031] In a second aspect, the present invention further provides a simulated clearing factor tracing device for a regional electricity spot market, comprising:

[0032] The clearing result acquisition module is used to obtain the simulation clearing results for the regional electricity spot market;

[0033] A tracing trigger module is used to trigger a clearing factor tracing process if the simulation clearing result does not meet the preset constraint conditions;

[0034] The clearing factor tracing process includes the following modules:

[0035] An input data acquisition module is used to obtain the original input data of the simulation model for the regional electricity spot market;

[0036] A sensitivity calculation module, configured to calculate the sensitivity index of each factor to the simulated clearing result based on the original input data and the simulated clearing result;

[0037] A factor screening module is used to select factors whose sensitivity index to the liquidation result is greater than a third threshold as key factors after screening;

[0038] A deviation contribution calculation module is used to input the screened key factors into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result;

[0039] The inducement determination module is used to determine that if the contribution of the key factor to the deviation of the simulation clearing result is greater than a decision threshold, then the factor is the main inducement of the deviation of the simulation clearing result.

[0040] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the simulated clearing factor tracing method for the regional electricity spot market as described in any one of the first aspects.

[0041] In a fourth aspect, the present invention further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it executes the simulation clearing factor tracing method for the regional electricity spot market described in any one of the first aspects.

[0042] The beneficial effects of adopting the above technical solution are as follows: This embodiment, through the deep integration of global sensitivity analysis and machine learning models, achieves a comprehensive quantitative assessment of the factors influencing the clearing results of regional electricity spot market simulations. Compared with traditional single-factor analysis methods, this not only captures the main effects of single factors such as load peak-valley differences and wind power output fluctuations, but also quantifies the interactions between these factors, avoiding the simplistic misjudgment of complex market mechanisms that are often encountered in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0044] Figure 1 This is a schematic diagram of a method for tracing the source of simulated clearing factors for a regional electricity spot market in one embodiment of the present application;

[0045] Figure 2 This is a schematic diagram of a simulated clearing factor tracing device for a regional electricity spot market in one embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In order to explain the present invention in more detail, the simulation clearing factor tracing method and device for the regional electricity spot market provided by the present invention will be specifically described below in conjunction with the drawings.

[0047] Unless otherwise defined, the technical or scientific terms used in this application should have the usual meanings understood by people with ordinary skills in the field to which the invention belongs. The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "an" or "the" do not indicate a quantity limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0048] Regional electricity spot markets refer to day-ahead and intraday electricity trading across provinces. As a core component of the national unified electricity market system, they reflect interprovincial supply and demand fluctuations through real-time price signals, optimize interprovincial power resource allocation, and support the large-scale adoption of renewable energy and secure power supply. Regional electricity spot markets precisely match peak and trough load periods through price fluctuations, and through market-based incentives for flexible adjustments by power generation, alleviate localized power shortages.

[0049] With the continuous advancement of the construction of regional electricity spot markets, the accuracy of market simulation clearing results is affected by many factors. Although existing research has explored electricity market simulation to some extent, it is still insufficient in identifying key factors and tracing the source of simulation results. Some studies simply analyze the impact of a single factor on market clearing without considering the complex interactions between factors, making it difficult to fully reveal the key factors. In terms of tracing the source of simulation results, there is a lack of systematic methods and tools, which makes it difficult to quickly locate the root cause of the deviation in simulation results. Based on this, combined with the attached Figure 1 The schematic diagram of the simulation clearing factor tracing method for the regional electricity spot market is shown, and a simulation clearing factor tracing method for the regional electricity spot market is proposed to improve the quality and efficiency of regional electricity spot market simulation.

[0050] Step S101: obtaining simulation clearing results for the regional electricity spot market.

[0051] Specifically, the simulation clearing result includes the clearing price and the clearing quantity.

[0052] Among them, the clearing price is the core indicator of the operation of the electricity spot market, which refers to the real-time transaction price of electricity formed through market bidding, reflecting the process dynamics and system constraints. The relationship between the clearing price and various factors in the original input data can be expressed as , is a nonlinear function that represents the interaction between different factors. is the clearing price, is the power supply side factor set, is the set of load-side factors, is the grid side factor set, is a collection of market-side factors, is the first random error term.

[0053] Cleared electricity volume is the core concept of electricity spot market bidding transactions, which refers to the transaction volume determined by market supply and demand matching and optimization calculation. Its essence is the quantitative result of the optimal allocation of power resources under the market mechanism. The relationship between cleared electricity volume and various factors in the original input data can be expressed as , is a nonlinear function that represents the interaction between different factors. is the clearing price, is the power supply side factor set, is the set of load-side factors, is the grid side factor set, is a collection of market-side factors, is the second random error term.

[0054] Step S102: If the simulation clearing result does not meet the preset constraint conditions, the clearing factor tracing process is triggered.

[0055] Specifically, in this embodiment, the simulated clearing result does not meet the preset constraint conditions, which means that there is a deviation between the simulated clearing result and the actual clearing result, and the deviation exceeds the acceptable range. Among them, the simulated clearing result does not meet the preset constraint conditions, including the clearing price deviation rate exceeding the first preset threshold or the clearing electricity deviation exceeding the second preset threshold. The specific expression of the clearing price deviation rate is: , is the clearing price deviation rate, To simulate the clearing price, The clearing reference price can be determined based on the average or median of historical clearing prices, or based on the results of the clearing price benchmark model. The specific expression of the clearing electricity deviation is: , To clear the power deviation, To simulate the power clearing, For clearing reference electricity, the clearing reference electricity can be determined based on the average or median of historical clearing electricity, or it can be derived based on historical input factors of a specific historical electricity spot market.

[0056] The clearing factor tracing process includes the following steps:

[0057] Step S103: obtaining original input data of a simulation model for the regional electricity spot market.

[0058] The original input data of the simulation model includes the power side factor set , Load side factor set , grid-side factor set and a collection of market-side factors .

[0059] The power side factor set Including but not limited to the type of generator set (such as thermal power, wind power, photovoltaic, etc.), generator set output characteristics, generator set start-up and shutdown costs, generator set quotation strategy, etc. Indicates that, Indicates the regional electricity spot market In this embodiment, the power supply side factors specifically include wind power output forecast value, photovoltaic output forecast value, unit start-up and shutdown costs and quotation strategy.

[0060] The load-side factor set Including but not limited to regional load forecast value, load characteristics (such as peak-valley difference, load elasticity, etc.), user electricity consumption behavior, etc., using the collection Indicates that, Indicates the regional electricity spot market In this embodiment, the set of load-side factors specifically includes load peak-to-valley difference, load forecast curve, and elastic coefficient.

[0061] The grid side factor set Including but not limited to transmission line capacity, line loss, node marginal price distribution (LMP), etc., using the set Indicates that Indicates the regional electricity spot market In this embodiment, the grid-side factor set specifically includes line congestion rate and node marginal price.

[0062] The market-side factors set Including but not limited to market trading rules, clearing algorithms, congestion management strategies, etc., using a collection ,in, Indicates the regional electricity spot market In this embodiment, the market-side factor set specifically includes transaction rule parameters and competitors' historical quotations.

[0063] Step S104: Calculate the sensitivity index of each factor to the simulation clearing result based on the original input data and the simulation clearing result.

[0064] Specifically, this embodiment uses a global sensitivity analysis method to calculate the sensitivity index of various factors in the regional electricity spot market to the market clearing results. By decomposing the variance of the system output into the contributions of various factors and their interactions, the influence of individual factors or combinations of factors on the output results is quantitatively assessed. The specific expression of the sensitivity index of each factor to the simulated clearing results (including the simulated clearing price and the simulated clearing quantity) is:

[0065] ,

[0066] in, Factor Changes in market clearing outcome indicators Variance The contribution of all factors in the regional electricity spot market (including the power supply side factor set , Load side factor set , grid-side factor set and a collection of market-side factors ) is summarized as a set of input factors , It is the first in the regional electricity spot market. factors, the market clearing result indicators include simulated clearing price and simulated clearing quantity, Factor The main effect variance of After that, the variance of the conditional expectation of the output result when other factors change reflects the variance of the output result. The contribution of other factors to the uncertainty of the output results, , is the variance of the market clearing result indicator, which indicates the uncertainty of the output result. , is the mathematical expectation.

[0067] Step S105: taking factors whose sensitivity index to the clearing result is greater than a third threshold as the key factors after screening.

[0068] Specifically, the third threshold represents the contribution threshold of factors in the regional electricity spot market to the market clearing result index, and is represented by the symbol Indicates that when the sensitivity index of any factor in the regional electricity spot market to the clearing result is greater than the third threshold It means that the change of this factor has a greater impact on the market clearing result indicator. Can be composed into traceable feature vectors , Indicates the The standardized values ​​of the key factors after screening, , Factor The historical average of Factor The historical standard deviation.

[0069] In addition, with respect to the key factors after threshold screening in step S105, in order to improve the efficiency of calculating the contribution of subsequent key factors to the deviation of the simulation clearing results, this embodiment may further include the following steps:

[0070] Use random forest model or gradient boosting model to select key factors As input, the market clearing outcome indicator For output, the Gini importance calculation model is used to calculate the factor importance score, and the preliminary key factors are sorted according to the factor importance score to determine the final key factor set. .

[0071] Gini importance is based on the splitting mechanism of the decision tree. If a factor can significantly reduce the sample impurity (such as the chaos of the price distribution) when splitting the node, then the factor has a greater impact on the result. The specific expression of the above factor importance score is , Factor The factor importance score of is the total number of nodes in the random forest model, is the total number of samples, For nodes The number of samples, For nodes The number of child nodes after splitting, For child nodes The number of samples, is the Gini impurity of the node before splitting, For child nodes Gini impurity, , For category probability.

[0072] Taking the clearing price as an example, if the "load peak-to-valley difference" factor is used multiple times to split nodes in the random forest model, and the clearing price variance within the node is significantly reduced after each split (for example, price fluctuations are greater when the load peak-to-valley difference is high), then the importance score of this factor is high, indicating that this factor is a key factor affecting the fluctuation of the clearing price.

[0073] Step S106: input the screened key factors into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result.

[0074] Specifically, the contribution of each factor to the deviation of the simulation clearing result is calculated through the gradient. The specific expression is:

[0075] ,

[0076] in, The key factor Contribution to the deviation of simulation clearing results, The key factor The change in the deviation rate for each standard deviation change is To simulate the prediction deviation of the clearing results, Factor The standard deviation of It is the reference value for clearing results.

[0077] When considering the contribution of each key factor to the simulated clearing price deviation, the above expression can be modified to , The key factor Contribution to the simulated clearing price deviation, To simulate the forecast deviation of the clearing price.

[0078] When considering the contribution of each key factor to the simulated clearing power deviation, the above expression can be modified as follows: , The key factor Contribution to the simulation clearing power deviation, To simulate the forecast deviation of cleared electricity.

[0079] Step S107: If the contribution of the key factor to the deviation of the simulation clearing result is greater than the decision threshold, then the factor is the main cause of the deviation of the simulation clearing result.

[0080] It should be noted that the decision threshold can be determined based on the contribution rate of the main inducement of the simulation clearing result deviation, and the decision threshold can be adjusted according to the contribution requirements of the specific inducement analysis plan.

[0081] To better illustrate the method for tracing the source of simulated clearing factors for the regional electricity spot market in this embodiment, a specific example is provided below:

[0082] When the clearing price deviation rate in the simulation clearing results of the regional electricity spot market is Or clear the power deviation When , the traceability process is triggered;

[0083] Assume that the simulation results for a certain period show that the price deviation rate When the sensitivity index of each factor to the clearing price is used, the key factors after screening are obtained, including the load peak-valley difference , line blocking rate , Wind power output fluctuations The key factors after the above screening together form the corresponding traceability feature vector: ;

[0084] Input the screened key factors into the traceability model to calculate the gradient ,like , it can be restored to the original dimensional contribution ;

[0085] Therefore, it can be concluded that the load peak-valley difference and line congestion rate are the main factors leading to the simulated clearing price deviation in the regional power grid spot market. Among them, the load peak-valley difference contributes 54% to the simulated clearing price deviation, and the line congestion rate contributes 36% to the simulated clearing price deviation. In other words, the excessive market clearing price deviation rate during this period is mainly caused by the load peak-valley difference, and secondly, line congestion is also a core factor causing price deviation.

[0086] Furthermore, the simulated clearing factor tracing method for the regional electricity spot market also includes: encrypting the original input data, simulated clearing results and main incentives of the clearing factor tracing process in combination with a hash encryption algorithm and storing them in the blockchain, and generating a unique traceability certificate, which includes a timestamp, operation record and data hash value to ensure that the traceability process cannot be tampered with.

[0087] Furthermore, the method for tracing the source of simulated clearing factors for the regional electricity spot market also includes: establishing a traceability case library based on a number of original input data from the simulation model for the regional electricity spot market, the corresponding simulated clearing results, and the main incentives; and combining the traceability case library with the real-time input data for the regional electricity spot market to obtain the corresponding predicted clearing results and predicted incentives. By establishing the traceability case library, historical experience is accumulated, providing rapid retrieval and reuse capabilities for similar anomalies.

[0088] In addition, in this embodiment, the time consumption of each traceability link can be recorded for the above-mentioned traceability process, which can be used for subsequent bottleneck analysis and optimization of specific algorithms, such as using parallel computing to accelerate the sensitivity analysis link.

[0089] The simulated clearing factor tracing method for the regional electricity spot market provided in this embodiment has the following advantages:

[0090] (1) Ability to accurately identify multi-dimensional key factors: Through the deep integration of global sensitivity analysis and machine learning models, a full-dimensional quantitative assessment of the factors affecting the results of regional power spot market simulation clearing is achieved. Compared with traditional single analysis methods, it can not only capture the main effects of single factors such as load peak-valley difference and wind power output fluctuation, but also quantify the interaction between factors, avoiding the traditional method's simplistic misjudgment of complex market mechanisms. For example, it can accurately identify the "amplifying effect of line congestion on prices during high load peak-valley difference periods", providing a more comprehensive basis for market participants to formulate bidding strategies.

[0091] (2) Data-driven dynamic traceability efficiency of simulation deviations: Based on the traceability model of deep learning and blockchain evidence storage technology, a minute-level response chain from anomaly detection to cause location is constructed. Through the gradient algorithm, the clearing price deviation (such as +8%) can be broken down into the contribution ratio of specific factors (such as 54% load peak-valley difference and 36% line congestion rate). Compared with traditional manual troubleshooting methods, the traceability accuracy is higher, and the historical case library can be used to quickly reuse similar problems, improve the traceability efficiency, and significantly reduce the debugging cost and operational risk of market simulation.

[0092] (3) Enhanced market adaptability and model robustness: Through dynamically updated machine learning models and blockchain-based immutable evidence storage, continuous tracking and retrospective verification of the dynamic characteristics of the regional power market are achieved. At the same time, through the historical traceability records stored on the blockchain, the evolution path of key factors in different market stages can be traced. This closed-loop mechanism of "data-model-verification" improves the interpretability of simulation results and significantly enhances the model's ability to adapt to changes in market structure, effectively avoiding the problem of analytical failure caused by changes in the market environment in traditional static models.

[0093] (4) Scientific and compliant decision support: The combination of structured traceability reports and visualization tools facilitates rapid understanding and formulation of response strategies by different entities, such as market operators and regulators. At the same time, the full-process data (such as original input, calculation logic, and attribution results) stored on the blockchain meets regulatory audit requirements, providing technical support for the compliance of power market transactions, reducing regulatory risks caused by the non-traceability of simulation results, and enhancing the transparency and credibility of the regional power spot market.

[0094] It should be understood that although the Figure 1 The steps in the flowchart are shown in the order indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Figure 1 At least part of the steps may include multiple sub-steps or sub-stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0095] The above-mentioned embodiments disclosed in the present invention describe in detail a method for tracing the simulated clearing factors for the regional electricity spot market. The above-mentioned method disclosed in the present invention can be implemented using various forms of equipment. Therefore, the present invention also discloses a device for tracing the simulated clearing factors for the regional electricity spot market. Specific embodiments are given below for detailed description.

[0096] The clearing result acquisition module 201 is used to obtain the simulation clearing results for the regional electricity spot market;

[0097] A tracing trigger module 202 is configured to trigger a clearing factor tracing process if the simulation clearing result does not meet a preset constraint condition;

[0098] The clearing factor tracing process includes the following modules:

[0099] An input data acquisition module 203 is used to acquire original input data of a simulation model for a regional electricity spot market;

[0100] A sensitivity calculation module 204 is configured to calculate the sensitivity index of each factor to the simulated liquidation result based on the original input data and the simulated liquidation result;

[0101] A factor screening module 205 is configured to select factors whose sensitivity index to the liquidation result is greater than a third threshold as the key factors after screening;

[0102] Deviation contribution calculation module 206, used to input the selected key factors into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result;

[0103] The inducement determination module 207 is configured to determine that if the contribution of the key factor to the deviation of the simulation clearing result is greater than a decision threshold, the factor is the main inducement of the deviation of the simulation clearing result.

[0104] Regarding the simulation clearing factor tracing device for the regional electricity spot market, all of them can be found in the above-mentioned method definitions, which will not be repeated here. Each module in the above-mentioned device can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor of the terminal device in the form of hardware, or can be stored in the memory of the terminal device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0105] In one embodiment, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned simulation clearing factor tracing method for the regional electricity spot market.

[0106] The computer-readable storage medium may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), a hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code for executing any of the steps of the above-described method. This program code can be read from or written to one or more computer program products, and the program code may be compressed in a suitable form.

[0107] In one embodiment, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the above-mentioned simulation clearing factor tracing method for the regional electricity spot market when executing the computer program.

[0108] The computer device includes a memory, a processor, and one or more computer programs, wherein the one or more computer programs can be stored in the memory and configured to be executed by one or more processors, and the one or more application programs are configured to execute the above-mentioned simulation clearing factor tracing method for the regional electricity spot market.

[0109] A processor may include one or more processing cores. The processor utilizes various interfaces and circuits to connect the various components within the entire computer device. It executes instructions, programs, code sets, or instruction sets stored in memory, and accesses data stored in memory to perform various functions of the computer device and process data. Optionally, the processor may be implemented in the form of at least one of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor and may be implemented separately via a communications chip.

[0110] The memory may include random access memory (RAM) or read-only memory (ROM). The memory may be used to store instructions, programs, codes, code sets, or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the terminal device during use, etc.

[0111] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned 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 various embodiments of the present invention.

Claims

1. A method for tracing the source of simulated clearing factors in regional electricity spot markets, characterized in that: include: Obtain simulation clearing results for the regional electricity spot market; If the simulation clearing result does not meet the preset constraints, the clearing factor tracing process is triggered; The clearing factor tracing process includes the following steps: Obtaining raw input data for simulation models targeting regional electricity spot markets; Calculating the sensitivity index of each factor to the simulated clearing result based on the original input data and the simulated clearing result; Factors whose sensitivity index to the liquidation results is greater than the third threshold are taken as the key factors after screening; Input the screened key factors into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result; If the contribution of the key factor to the deviation of the simulation clearing result is greater than the decision threshold, then the factor is the main cause of the deviation of the simulation clearing result.

2. The method for tracing the source of simulated clearing factors for a regional electricity spot market according to claim 1, characterized in that: The simulation clearing results include clearing price and clearing quantity; The simulation clearing result does not meet the preset constraint conditions, including that the clearing price deviation rate exceeds a first preset threshold or the clearing electricity quantity deviation exceeds a second preset threshold.

3. The method for tracing the source of simulated clearing factors for a regional electricity spot market according to claim 1, characterized in that: The original input data of the simulation model includes: a power supply side factor set, a load side factor set, a grid side factor set and a market side factor set; The power supply side factor set includes wind power output forecast value, photovoltaic output forecast value, unit start-up and shutdown costs and quotation strategy; The load side factor set includes load peak-valley difference, load forecast curve and elastic coefficient; The grid-side factor set includes line congestion rate and node marginal price; The market-side factor set includes trading rule parameters and competitors' historical quotes.

4. The method for tracing the source of simulated clearing factors for a regional electricity spot market according to claim 1, characterized in that: The sensitivity index of each factor to the simulated clearing result is calculated based on the original input data and the simulated clearing result, specifically: ， in, Factor Changes in market clearing outcome indicators Variance The contribution of Factor The main effect variance of After that, the variance of the conditional expectation of the output result when other factors change, , is the variance of the market clearing outcome indicator, .

5. The method for tracing the source of simulated clearing factors for a regional electricity spot market according to claim 1, characterized in that: The filtered key factors are input into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result: ， in, The key factor Contribution to the deviation of simulation clearing results, The key factor The change in the deviation rate for each standard deviation change is To simulate the prediction deviation of the clearing results, Factor The standard deviation of It is the reference value for clearing results.

6. The method for tracing the source of simulated clearing factors for a regional electricity spot market according to claim 1, characterized in that: Also includes: The original input data of the clearing factor tracing process, the simulated clearing results and the main inducements are encrypted and stored in the blockchain using a hash encryption algorithm, and a unique traceability certificate is generated.

7. The method for tracing the source of simulated clearing factors for a regional electricity spot market according to claim 1, characterized in that: Also includes: Establish a traceability case library based on several original input data of the simulation model for the regional electricity spot market, the corresponding simulation clearing results and the main incentives; Combined with the traceability case library, corresponding forecast clearing results and forecast incentives are obtained based on real-time input data for the regional electricity spot market.

8. A simulation clearing factor tracing device for regional electricity spot market, characterized by: include: The clearing result acquisition module is used to obtain the simulation clearing results for the regional electricity spot market; A tracing trigger module is used to trigger a clearing factor tracing process if the simulation clearing result does not meet the preset constraint conditions; The clearing factor tracing process includes the following modules: An input data acquisition module is used to obtain the original input data of the simulation model for the regional electricity spot market; A sensitivity calculation module, configured to calculate the sensitivity index of each factor to the simulated clearing result based on the original input data and the simulated clearing result; A factor screening module is used to select factors whose sensitivity index to the liquidation result is greater than a third threshold as key factors after screening; A deviation contribution calculation module is used to input the screened key factors into the traceability model to obtain the contribution of each key factor to the deviation of the simulation clearing result; The inducement determination module is used to determine that if the contribution of the key factor to the deviation of the simulation clearing result is greater than a decision threshold, then the factor is the main inducement of the deviation of the simulation clearing result.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the simulation clearing factor tracing method for the regional electricity spot market described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it performs the simulation clearing factor tracing method for the regional electricity spot market according to any one of claims 1 to 7.

Images