Dynamic pricing method and device for providing auxiliary service adjustment by multiple subjects

Abstract

The invention discloses a dynamic pricing method and device for providing auxiliary service adjustment by multiple subjects, and relates to the technical field of dynamic pricing, and the method comprises the following steps: obtaining historical data of all units in a power market, and carrying out the preprocessing of the historical data to obtain first data; constructing an auxiliary service adjustment dynamic pricing mechanism model based on a system dynamics theory in combination with the first data; judging whether adjustment is needed or not according to the operation condition of the model, and if adjustment is not needed, performing dynamic pricing calculation; if adjustment is needed, influence parameters are obtained based on sensitivity test analysis, coefficients on an influence parameter link are preferentially adjusted, and a logic relation is reconstructed to carry out feedback correction on the model; and calculating according to the corrected model to obtain a correlation adjustment reasonable cost reference value. And dynamic adjustment of the auxiliary service price is realized through the established causal relationship graph and the like. Through real-time data acquisition and updating, the model can dynamically calculate the pricing of the auxiliary service according to the constructed flow graph, and a scientific basis is provided for pricing.

Description

Technical Field

[0001] The present invention relates to the technical field of auxiliary services in the electricity spot market, and more specifically, to a dynamic pricing method and device for auxiliary service regulation provided by multiple entities. Background Art

[0002] Limited by the market supply and demand, market development maturity, grid structure and technical resources of each province, the construction progress of the spot market in different provinces is different. At present, most of the pilot projects are still in the initial stage of spot construction, and the reform focus of this stage is to promote the trial operation of spot electricity. Since the energy structure of most provinces is still dominated by thermal power, the security of the power grid system has not yet faced the large-scale volatility of a high proportion of clean energy. For practical and economic considerations, most of the pilot provinces at this stage have promulgated some types of auxiliary service rules, but have not actually carried out the operation of the auxiliary service market. Considering the limited technical support and maturity of market players in the spot transition stage, optimization and cultivation are gradual processes, and some provinces will still be in the spot transition stage for a long time. Therefore, auxiliary services such as frequency regulation and standby in the transition stage are still reserved in a non-market manner and called by the power grid control system.

[0003] At present, the compensation for regulation services in the ancillary service market that has not yet been developed is still priced according to the "two detailed rules". With the development and changes of the power market, this standard has gradually become outdated. Especially in the context of developing a new power system with energy innovation, it cannot effectively adapt to the new market environment and it is difficult to promote multiple entities to provide flexible regulation and incentives for production. In the new market situation in the transition stage, different types of multiple entities such as energy storage equipment, distributed energy, and demand response resources continue to emerge, and the traditional fixed price cannot fully consider the regulation characteristics and costs of these entities.

[0004] In addition, the single-price ancillary service regulation pricing ignores the external impact of spot electricity and energy prices on the cost changes of the subject. The long-term lack of adjustment to ancillary service pricing during the spot transition phase cannot effectively incentivize new subjects to recover costs and reduce the enthusiasm of multiple subjects to provide flexibility regulation. This not only causes inefficient allocation of flexibility resources, but also fails to incentivize compatible promotion of multiple subjects to participate in the provision of ancillary services, reducing the economic efficiency of the power market and affecting the stability and reliability of the power system.

[0005] The above disclosed technical solutions have at least the following technical problems: At present, the compensation for regulation services cannot effectively adapt to the new market environment, and it is difficult to promote multiple entities to provide flexibility regulation and incentivize production. The single-price ancillary service regulation leads to inefficient allocation of flexibility resources, and it is also impossible to incentivize compatibility and promote multiple entities to participate in the provision of ancillary services, which reduces the economic efficiency of the power market and affects the stability and reliability of the power system. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a dynamic pricing method and apparatus for providing auxiliary service regulation through multiple subjects, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A dynamic pricing method for auxiliary service regulation provided by multiple entities includes the following steps: obtaining historical data of all units in the power market and preprocessing to obtain first data; constructing a dynamic pricing mechanism model for auxiliary service regulation based on system dynamics theory and the first data; judging whether adjustment is needed according to the operation of the model, and performing dynamic pricing calculation if no adjustment is needed; if adjustment is needed, obtaining influencing parameters based on sensitivity test analysis and giving priority to adjusting coefficients on influencing parameter links and reconstructing logical relationships to feedback and correct the model; and calculating a reasonable cost reference value for associated regulation based on the corrected model.

[0008] In a preferred embodiment, the historical data of all units in the power market are obtained and preprocessed to obtain the first data, specifically: all units in the power market are classified and marked according to their resource types, and all data and factor tables are stored with unique corresponding unit serial number code index; all parameters are divided into static parameters and dynamic parameters according to their attributes; the historical data required for dynamic parameter calculation is indexed by unit serial number and stored in the form of factor tables; historical data is cleaned and denoised; and data is obtained in real time to update the factor table.

[0009] In a preferred embodiment, the cleaning and denoising of historical data are specifically as follows: for historical data, CEMD is first performed, and the signal is decomposed into multiple intrinsic mode functions through the complex data empirical mode decomposition method; before each execution of CEMD, random white noise is added; CEMD is initialized M times using different white noises; after M iterations, the intrinsic mode functions obtained from each decomposition are summarized, and the IMFs are recombined through screening and weighted combination to reconstruct the first data.

[0010] In a preferred embodiment, the auxiliary service regulation dynamic pricing mechanism model is constructed based on the system dynamics theory in combination with the first data, specifically: defining the data scope involved in the model, the data scope includes historical electricity spot electric energy data, auxiliary service operation data, status and performance parameters of different types of units; determining the participants of the model, the participants include multiple entities that provide auxiliary services such as energy storage and thermal power, and other relevant parties in the electricity market; analyzing the causal relationship between the various elements in the system and drawing a causal loop diagram; based on the causal loop diagram, further drawing a stock-flow diagram to obtain the stock and flow data in the system; according to the stock-flow diagram, defining various variables in the model, the various variables include level variables, rate variables and auxiliary variables; establishing energy storage modules, thermal power modules and electric energy modules, and constructing an auxiliary service regulation dynamic pricing mechanism model in combination with various variables in the model; the various elements include electric energy clearing, power grid control system, regulation cost, spot electric energy price; the stock includes power supply and demand balance, auxiliary service capacity; the flow includes power trading and auxiliary service call.

[0011] In a preferred embodiment, the step of determining whether adjustment is required based on the operation of the model is specifically as follows: calculating the mean square error and mean absolute error between the model prediction result and the actual data; Evaluation model's prediction results fluctuation data in different time periods or under different scenarios based on standard deviation and coefficient of variation indicators; calculate change data of economic indicators such as transaction costs in the power market and unit operating efficiency after the model runs; obtain monitoring indicators and set thresholds for each monitoring indicator based on historical data and industry standards; regularly collect actual operation data and model prediction data from power market and power grid control system channels; use programming languages ​​to process and analyze actual operation data and model prediction data to obtain key monitoring indicators; compare the calculated key monitoring indicators with the set thresholds; if the monitoring indicators exceed the threshold range, it is preliminarily judged that the model needs to be adjusted.

[0012] In a preferred embodiment, the influencing parameters are obtained based on the sensitivity test analysis, the coefficients on the influencing parameter links are adjusted preferentially, and the logical relationship is reconstructed to perform feedback correction on the model, specifically: List all parameters in the model; select the gradient method to perform sensitivity tests on all parameters in the model according to the complexity of the model and the test requirements; identify the links where high-sensitivity parameters are located based on the sensitivity test results, where small changes in the highly sensitive parameters will lead to large fluctuations in the model output results; use the historical data of month t-1 to fit the impact of the compensation effect and adjust the links where the highly sensitive parameters are located, and feed back to the overall link along the links; use the compensation effect in the feedback loop as the independent variable, and the compensation effect is calculated by deducting the theoretical cost from the revenue calculated by the pricing results of the past months, and use the data of the clearing results as the dependent variable to establish a regression model, and use the logistic regression function sigmoid to train the model to predict the results; after loading the parameters obtained by the training model, calculate the final value of the correlation according to the corresponding historical data factor table.

[0013] In a preferred embodiment, a dynamic pricing device for auxiliary service regulation provided by multiple entities includes the following modules: a data collection module, a model building module, a judgment module, a feedback correction module and a dynamic pricing calculation module; a data collection module: used to obtain historical data of all units in the power market and preprocess them to obtain first data; a model building module: used to construct a dynamic pricing mechanism model for auxiliary service regulation based on system dynamics theory and the first data; a judgment module: used to determine whether adjustment is required based on the operation of the model, and directly perform dynamic pricing calculation if no adjustment is required; a feedback correction module: used to obtain the influencing parameters based on sensitivity test analysis and give priority to adjusting the coefficients on the influencing parameter link and reconstructing the logical relationship to perform feedback correction on the model if adjustment is required; a dynamic pricing calculation module: used to calculate a reasonable cost reference value for associated regulation based on the corrected model.

[0014] The technical effects and advantages of the dynamic pricing method and device for regulating auxiliary services provided by multiple entities of the present invention are as follows: 1. The present invention introduces the idea of ​​system dynamics method based on system dynamics theory, comprehensively sorts out the transmission interaction relationship between ancillary service price and cost, spot-related opportunity cost, etc., and constructs a global feedback model. On the one hand, the different performance and costs of multiple subjects are taken into consideration to construct a pricing method for ancillary services. This refined cost consideration makes pricing more fair and reasonable, and can fully motivate different types of multiple subjects to actively participate in the provision of ancillary services. On the other hand, the impact of fluctuations in spot electricity boundary conditions on the opportunity cost of ancillary services is considered through spot prices, and the externalities of ancillary service adjustment costs are more comprehensively considered. Therefore, the innovative method of the present invention can more accurately reflect the actual operation of the ancillary service market and provide a scientific basis for pricing.

[0015] 2. The automated dynamic pricing method adapted to different scenarios of the present invention is based on data-driven, and realizes dynamic adjustment of the price of auxiliary services through the establishment of cause-and-effect diagrams, etc. Through real-time data collection and updating, the model can dynamically calculate the pricing of auxiliary services based on the constructed flow chart, providing a scientific basis for pricing. The innovative dynamic adjustment pricing method of the present invention more accurately reflects the actual operation of the auxiliary service market, can respond to market changes in a timely manner, improve the accuracy and adaptability of pricing, and provide a new idea and method for the pricing of auxiliary services in the transition stage. . BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the structure of a dynamic pricing method for providing auxiliary service regulation for multiple entities of the present invention.

[0017] Figure 2 A schematic diagram of the structure of a dynamic pricing device for providing auxiliary service regulation for multiple entities of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 creative work are within the scope of protection of the present invention.

[0019] Embodiment 1, Figure 1 The present invention provides a dynamic pricing method for regulating auxiliary services provided by multiple entities, including the following steps: S1, obtaining historical data of all units in the power market and preprocessing them to obtain first data; The obtaining of historical data of all units in the power market and preprocessing to obtain the first data is specifically: All units in the power market are classified and marked according to their resource types, and all data and factor tables are stored with unique corresponding unit serial number code index; All parameters are divided into static parameters and dynamic parameters according to their attributes. For example, the loss rate and life discount rate are usually fixed coefficient parameters and are called static parameters; the operation-related clearing price, clearing volume and other parameters with time scales are dynamic parameters; The historical data required for dynamic parameter calculation is stored in the form of a factor table with the unit serial number as the index; Clean and denoise historical data; The rolling time period is one month, and data is collected daily. At the end of the month, the corresponding first data is collected and updated in the factor table.

[0020] The cleaning and denoising of historical data are specifically as follows: For the captured data, CEMD is first performed, that is, the signal is decomposed into multiple intrinsic mode functions through the complex data empirical mode decomposition method; Before each CEMD execution, random white noise was added to enhance the decomposability of the signal; Perform M initializations of CEMD, each using a different white noise; Add noise multiple times and decompose the data to smooth out random fluctuations in the data After M iterations, the intrinsic mode functions obtained from each decomposition are summarized, and the IMFs are recombined through screening and weighted combination to reconstruct the first data; The signal-to-noise ratio of the first data after denoising is evaluated to ensure that the noise component has been successfully removed.

[0021] In this embodiment, the first data includes the following: (1) The unit types in the market are marked as , referred to by type number.

[0022] (2) Annual utilization hours H: The annual utilization hours of each type of unit are calculated based on the total market electricity and average power generation in the previous year. The specific performance of this parameter will gradually increase with the participation of new entities in the market, further reducing the amortization of fixed costs.

[0023] (3) Coal price , obtained from the public data channels of China Electricity Council and updated on a rolling basis.

[0024] (4) Parameters related to spot electricity clearing include electricity quotation , spot clearing volume Q and spot clearing average electricity price P are calculated from the actual declaration and spot clearing links, obtained and stored in the factor table according to the unit index. Rolling update according to the operation status.

[0025] (5) Ancillary service regulation parameters include thermal power generation regulation , Energy storage adjusts discharge time , Adjust capacity reservation , which is obtained from the auxiliary service adjustment data of the actual operation and stored in the factor table according to the unit index. It is updated in a rolling manner according to the operation status.

[0026] (6) Lifetime discount rate d of thermal power units and loss rate of energy storage and battery degradation coefficient . In the process of providing flexibility adjustment, the coal-fired power unit will affect the unit's standard coal consumption and equipment depreciation rate to a certain extent, reflecting the parameters that cause the increase in depreciation costs of coal-fired power plants; the energy storage loss coefficient is a measure of the cost loss efficiency caused by the participation of energy storage in power auxiliary services. Due to the limitations of battery technology, during the charging and discharging process, the energy loss caused by various reasons such as heat release from chemical reactions and losses in the lines in the battery cells cannot fully achieve 100% charging and discharging, and part of it will be lost during the period. The life discount rate and loss rate are generally fixed coefficients; the battery degradation coefficient is a measure of the degradation cost caused by frequent switching of charging and discharging states. Energy storage needs to continuously switch its charging and discharging states to provide regulation, and perform multiple charging and discharging cycles, which will accelerate the cycle aging of battery energy storage.

[0027] (7) Performance adjustment factor According to the theoretical performance and actual performance of ancillary service regulation provided by different types of entities, the performance adjustment coefficient is calculated on a rolling basis. It is a quantitative parameter for measuring the quality of ancillary services provided by power ancillary service providers and is also used to correct compensation situations.

[0028] S2, constructs a dynamic pricing mechanism model for auxiliary service regulation based on system dynamics theory combined with first data; System dynamics is a discipline that analyzes and studies information feedback systems. It is based on system theory and draws on the essence of cybernetics and information theory. System dynamics believes that the behavior patterns and characteristics of a system are mainly rooted in the dynamic structure and feedback mechanism within the system. Therefore, we can use the theory and methods of system dynamics to construct a dynamic pricing mechanism model for auxiliary service regulation.

[0029] Determine the model objectives and boundaries: When the model is used to solve the settlement of a certain m-month electricity market, the model is constructed based on historical spot electricity energy, operating data of ancillary services, and status and performance parameters of different types of units. It sorts out the connections and interactions and builds feedback loops. Combined with the system flow chart, it intuitively displays the interaction and feedback mechanism between various factors, describes the dynamic change process of each variable in the system, and simulates and calculates the reference value of the ancillary service adjustment cost.

[0030] Model definition: In the transitional stage of the electricity spot market, the reservation and regulation of ancillary services are achieved through the clearing of electric energy and the power grid control system. Combined with the impact of regulation costs and spot electric energy, the interaction between model influencing factors constitutes different modules under the influence of internal and external systems. The entire model can be quantitatively represented by causal relationships as a feedback system. Therefore, considering the different performance and costs of regulation provided by multiple entities, taking energy storage and thermal power as examples, the establishment of a dynamic pricing mechanism model for ancillary service regulation in the transitional stage includes energy storage modules, thermal power modules and electric energy modules.

[0031] The auxiliary service adjustment dynamic pricing mechanism model is constructed based on the system dynamics theory and combined with the first data, specifically: Define the data scope involved in the model, including historical spot electricity data, auxiliary service operation data, status and performance parameters of different types of units; Identify the participants of the model, including multiple entities providing ancillary services such as energy storage and thermal power, as well as other stakeholders in the electricity market; Analyze the cause-effect relationship between various elements in the system and draw a cause-effect loop diagram; Based on the causal loop diagram, a stock-flow diagram is further drawn to obtain the stock and flow data in the system; Based on the stock-flow diagram, define various variables in the model, including level variables, rate variables, and auxiliary variables; Establish energy storage modules, thermal power modules and electric energy modules, and build a dynamic pricing mechanism model for auxiliary service regulation based on various variables in the model; The various elements include electricity energy clearing, power grid control system, regulation cost, and spot electricity energy price; the stocks include electricity supply and demand balance and ancillary service capacity; and the flows include electricity trading and ancillary service calls.

[0032] Energy storage module construction: Based on the energy storage cost calculation idea, combined with the main factors affecting the adjustment cost of energy storage auxiliary services, the adjustment cost mainly includes fixed cost, operating cost and loss cost, and the cause and effect relationship is established as shown in the attached Figure 2 The main equations of the model are:

[0033]

[0034]

[0035]

[0036] In the formula, They represent fixed cost variables, operating cost variables and loss cost variables respectively, p is the effective installed power of the unit, is the total annual fixed cost of energy storage, is the rated power of the unit, is the replacement cost of the energy storage battery. and battery degradation coefficient , energy storage adjusts discharge time , spot clearing average electricity price P, annual utilization hours H.

[0037] Thermal power module construction: Based on the thermal power cost calculation idea, combined with the main factors affecting the adjustment cost of energy storage auxiliary services, the adjustment cost mainly includes fixed cost, operating cost and loss cost, and the cause and effect relationship is established as shown in the attached Figure 2 The main equations of the model are:

[0038]

[0039]

[0040]

[0041] In the formula, They represent fixed cost variables, operating cost variables and loss cost variables respectively. is the total annual fixed cost of thermal power, is the rated power of the unit, is the residual value of thermal power fixed assets, Y is the designed operating life of thermal power, It represents the fuel increment caused by regulation. The life discount rate of thermal power unit is d, and the coal price is , annual utilization hours H, thermal power regulation power generation .

[0042] Electric energy module construction: The spot electric energy module is mainly used to calculate the loss of profits of market entities in the electric energy market due to the impact of ancillary services as the opportunity cost of electric energy, and to update the spot parameters and feed back to other modules.

[0043]

[0044] In the formula, Determine the cost of different units.

[0045] S3, judging whether adjustment is needed according to the operation of the model, and performing dynamic pricing calculation if adjustment is not needed; When judging whether the ancillary service regulation dynamic pricing mechanism model needs to be adjusted based on the operation of the model, the following aspects can be considered comprehensively: Accuracy and stability: Monitor the accuracy of the model in predicting power market prices or unit output, as well as the stability of the model. If the model's accuracy drops significantly or its stability is insufficient, adjustments may be required.

[0046] Error analysis: Compare and analyze the model's prediction results with the actual data, and calculate indicators such as the error rate. If the error rate remains high or shows an upward trend, it indicates that there may be problems with the model and adjustments are needed.

[0047] Economic benefit analysis: Evaluate the economic benefits of the model in actual operation, such as whether it can effectively reduce transaction costs in the power market, improve unit operating efficiency, etc. If the economic benefits are not obvious or show a downward trend, the model may need to be adjusted.

[0048] User feedback collection: Collect feedback from power market participants and relevant stakeholders to understand their satisfaction with the model operation and existing problems. If the feedback indicates that the model has obvious deficiencies or needs improvement, the model should be adjusted.

[0049] The step of judging whether adjustment is needed according to the operation status of the model is as follows: Calculate the mean square error and mean absolute error between the model prediction results and the actual data; The fluctuation data of the prediction results of the evaluation model in different time periods based on the standard deviation and coefficient of variation indicators; Calculate the transaction costs of the power market and the change data of unit operating efficiency indicators after the model is run; Obtain monitoring indicators and set thresholds for each monitoring indicator based on historical data and industry standards; Regularly collect actual operation data and model prediction data from power market and grid control system channels; Use programming languages ​​to process and analyze actual operation data and model prediction data to obtain key monitoring indicators; Compare the calculated key monitoring indicators with the set thresholds; If the monitoring indicator exceeds the threshold range, it is preliminarily judged that the model needs to be adjusted.

[0050] S4, if adjustment is needed, the influencing parameters are obtained based on the sensitivity test analysis and the coefficients on the influencing parameter links are adjusted first and the logical relationship is reconstructed to feedback and correct the model; Dimensional testing: The simulated behavior of the model is compared with the actual behavior of the system, but the test is more involved than reproducing historical behavior. Each variable corresponds to a meaningful concept in the electricity market and each equation must be checked for dimensional consistency.

[0051] Adjustment of logical relationships: Affected by changes in the external environment, the accuracy of the model is determined by logical associations. Therefore, the sensitivity test method can be used to effectively analyze the parameters with greater influence. When the simulation effect is not good, the coefficients on these parameter links can be adjusted and the logical relationships can be reconstructed to optimize and adapt to the external changing environment.

[0052] The influencing parameters are obtained based on the sensitivity test analysis, and the coefficients on the influencing parameter links are adjusted preferentially and the logical relationship is reconstructed to perform feedback correction on the model, specifically: List all parameters in the model; According to the complexity of the model and the test requirements, the gradient method is selected to perform sensitivity tests on all parameters in the model; According to the sensitivity test results, the links where the high-sensitivity parameters are located are identified, wherein the high-sensitivity parameters refer to the parameters whose small changes will lead to large fluctuations in the model output results; The impact of the compensation effect is fitted using historical data for month t-1 and the link where the high-sensitivity parameter is located is adjusted, and feedback is fed back to the link along the link; The compensation effect in the feedback loop is used as the independent variable. The compensation effect is calculated by deducting the theoretical cost from the revenue calculated by the pricing results of the past months. The data of the clearing results is used as the dependent variable to establish a regression model. The logistic regression function sigmoid is used to train the model to predict the results. After loading the parameters obtained from the training model, the final value of the correlation is calculated based on the corresponding historical data factor table.

[0053] Feedback correction: Taking into account the impact of the compensation income received by market entities from the settlement of the previous month on this month's decision-making and enthusiasm, use the historical data of month t-1 to fit the impact of the compensation effect and predict the adjustment of this month's operating data, and then feed it back to this month's price along the link.

[0054] Taking the compensation effect in the feedback loop as the independent variable, the compensation effect is calculated by deducting the theoretical cost from the revenue calculated by the pricing results of the past months. Taking the data of the clearing results as the dependent variable, a regression model is established. The logistic regression function sigmoid is used to train the model for prediction. Then,

[0055] After loading the parameters obtained from the training model, the final value of the correlation is calculated according to the corresponding historical data factor table. The calculation formula is as follows:

[0056]

[0057]

[0058] Where w and b are the weight and bias of the regression function obtained by training the model.

[0059] Rolling update of annual utilization hours: Annual utilization hours are updated with the data of the past year. The calculation formula is as follows:

[0060]

[0061] S5, calculating the reasonable cost reference value of the associated adjustment according to the revised model.

[0062] The cost-plus pricing mechanism is priced based on the method of "reasonable cost + reasonable profit". According to the habit of "daily settlement and monthly settlement" in the electricity market, the weighted average price is calculated based on the calculation results of each module during the monthly settlement as the reference value of the reasonable cost of the associated adjustment. The calculation formula is as follows:

[0063] In the formula, Market player adjustment costs calculated for energy storage and thermal power modules, is the corresponding opportunity cost of the electric energy module.

[0064] According to the profit range coefficient , we can deduce the dynamic pricing with reasonable profit as follows:

[0065] In the formula, It is an adjustable parameter.

[0066] Embodiment 2, a dynamic pricing device for auxiliary service regulation provided by multiple entities, characterized in that it includes the following modules: a data collection module, a model building module, a judgment module, a feedback correction module and a dynamic pricing calculation module; Data collection module: used to obtain historical data of all units in the power market and perform preprocessing to obtain first data; Model building module: used to build a dynamic pricing mechanism model for auxiliary service regulation based on system dynamics theory combined with first data; Judgment module: used to determine whether adjustments are needed based on the operation of the model. If no adjustments are needed, dynamic pricing calculations are performed; Feedback correction module: if adjustment is needed, the influencing parameters are obtained based on sensitivity test analysis and the coefficients on the influencing parameter link are adjusted first and the logical relationship is reconstructed to perform feedback correction on the model; Dynamic pricing calculation module: used to calculate the reasonable cost reference value of the associated adjustment based on the revised model The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0067] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0068] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0069] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0070] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0071] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dynamic pricing method for regulating auxiliary services provided by multiple entities, characterized in that: The following steps are involved: Acquire historical data of all units in the power market and perform preprocessing to obtain first data; Based on the theory of system dynamics and combined with First Data, a dynamic pricing mechanism model for auxiliary service regulation is constructed; Determine whether adjustments are needed based on the model's operating conditions. If no adjustments are needed, perform dynamic pricing calculations. If adjustment is needed, the influencing parameters are obtained based on sensitivity test analysis and the coefficients on the influencing parameter links are adjusted first and the logical relationship is reconstructed to perform feedback correction on the model; The reasonable cost reference value of association adjustment is calculated based on the revised model.

2. The dynamic pricing method for auxiliary service regulation provided by multiple entities according to claim 1 is characterized in that: The acquiring of historical data of all units in the power market and preprocessing to obtain the first data is specifically: All units in the power market are classified and marked according to their resource types, and all data and factor tables are stored with unique corresponding unit serial number code index; Divide all parameters into static parameters and dynamic parameters according to their properties; The historical data required for dynamic parameter calculation is stored in the form of a factor table using the unit serial number as an index; Clean and denoise historical data; Get data in real time to update the factor table.

3. The method and device for dynamic pricing of auxiliary service regulation provided by multiple entities according to claim 2, characterized in that: The cleaning and denoising of historical data are specifically as follows: For historical data, CEMD is performed to decompose the signal into multiple intrinsic mode functions through the complex data empirical mode decomposition method; Before each execution of CEMD, random white noise was added; Perform M initializations of CEMD using different white noises; After M iterations, the intrinsic mode functions obtained from each decomposition are summarized, and the IMFs are recombined through screening and weighted combination to reconstruct the first data.

4. The dynamic pricing method for auxiliary service regulation provided by multiple entities according to claim 3 is characterized in that: The auxiliary service adjustment dynamic pricing mechanism model is constructed based on the system dynamics theory and combined with the first data, specifically: Define the data scope involved in the model, including historical spot electricity data, auxiliary service operation data, status and performance parameters of different types of units; Identify the participants of the model, including multiple entities providing auxiliary services such as energy storage and thermal power, as well as other stakeholders in the electricity market; Analyze the cause-effect relationship between various elements in the system and draw a cause-effect loop diagram; Based on the causal loop diagram, a stock-flow diagram is further drawn to obtain the stock and flow data in the system; Based on the stock and flow data, define various variables in the model, including level variables, rate variables and auxiliary variables; Establish energy storage modules, thermal power modules and electric energy modules, and build a dynamic pricing mechanism model for auxiliary service regulation based on various variables in the model; The various elements include electricity energy clearing, power grid control system, regulation cost, and spot electricity energy price; the stocks include electricity supply and demand balance and ancillary service capacity; and the flows include electricity trading and ancillary service calls.

5. The dynamic pricing method for regulating auxiliary services provided by multiple entities according to claim 4 is characterized in that: The step of judging whether adjustment is needed according to the operation status of the model is as follows: Calculate the mean square error and mean absolute error between the model prediction results and the actual data; The fluctuation data of the prediction results of the evaluation model in different time periods based on the standard deviation and coefficient of variation indicators; Calculate the transaction costs of the power market and the change data of unit operating efficiency indicators after the model is run; Obtain monitoring indicators and set thresholds for each monitoring indicator based on historical data and industry standards; Regularly collect actual operation data and model prediction data from power market and grid control system channels; Use programming languages ​​to process and analyze actual operation data and model prediction data to obtain key monitoring indicators; Compare key monitoring indicators with set thresholds; If the monitoring indicator exceeds the threshold range, it is preliminarily judged that the model needs to be adjusted.

6. The dynamic pricing method for regulating auxiliary services provided by multiple entities according to claim 5 is characterized in that: The influencing parameters are obtained based on the sensitivity test analysis, and the coefficients on the influencing parameter links are adjusted preferentially and the logical relationship is reconstructed to perform feedback correction on the model, specifically: According to the complexity of the model and the test requirements, the gradient method is selected to perform sensitivity tests on all parameters in the model; Based on the sensitivity test results, identify the links where the high sensitivity parameters are located; The effect of fitting compensation of historical data in month t-1 is used to adjust the link where the high-sensitivity parameter is located, and the feedback is fed back to the overall link along the link; Taking the compensation effect in the feedback loop as the independent variable and the data of the clearing results as the dependent variable, a regression model is established, and the logistic regression function sigmoid is used to train the model to predict the results.

7. The dynamic pricing method for regulating auxiliary services provided by multiple entities according to claim 6 is characterized in that: The energy storage module is specifically: In the formula, is the performance adjustment factor, They represent fixed cost variables, operating cost variables and loss cost variables respectively, p is the effective installed power of the unit, is the total annual fixed cost of energy storage, is the rated power of the unit, is the replacement cost of energy storage battery, and the loss rate of energy storage and battery degradation coefficient , energy storage adjusts discharge time , spot clearing average electricity price P, annual utilization hours H.

8. The dynamic pricing method for auxiliary service regulation provided by multiple entities according to claim 7 is characterized in that: The thermal power module is specifically: In the formula, They represent fixed cost variables, operating cost variables and loss cost variables respectively. is the total annual fixed cost of thermal power, is the rated power of the unit, is the residual value of thermal power fixed assets, Y is the designed operating life of thermal power, represents the fuel increment caused by regulation, the life discount rate of thermal power units is d, and the coal price is , annual utilization hours H, thermal power regulation power generation .

9. The dynamic pricing method for regulating auxiliary services provided by multiple entities according to claim 8, characterized in that: The modified model is specifically: In the formula, To adjust reasonable cost reference value for association, Market player adjustment costs calculated for energy storage and thermal power modules, is the corresponding opportunity cost of the electric energy module.

10. The dynamic pricing device for providing auxiliary service regulation by multiple entities according to claim 9, characterized in that: It includes the following modules: data collection module, model building module, judgment module, feedback correction module and dynamic pricing calculation module; Data collection module: used to obtain historical data of all units in the power market and perform preprocessing to obtain first data; Model building module: used to build a dynamic pricing mechanism model for auxiliary service regulation based on system dynamics theory combined with first data; Judgment module: used to determine whether adjustments are needed based on the operation of the model. If no adjustments are needed, dynamic pricing calculations are performed; Feedback correction module: if adjustment is needed, the influencing parameters are obtained based on sensitivity test analysis and the coefficients on the influencing parameter link are adjusted first and the logical relationship is reconstructed to perform feedback correction on the model; Dynamic pricing calculation module: used to calculate the reasonable cost reference value of the associated adjustment based on the revised model.

Images