Frequency modulation and electric energy combined clearing method, device and equipment in electricity market

Abstract

The invention discloses a frequency modulation and electric energy combined clearing method, a frequency modulation and electric energy combined clearing device and equipment in an electric power market, and relates to the technical field of electric power data scheduling management. The fluctuation amplitude and potential conflicts of price signals in the electricity market can be accurately judged; potential risks in power operation can be effectively prevented by monitoring and processing conflicts between price signal fluctuation and power grid frequency data in real time, and various data of power operation can be effectively scheduled and managed to guarantee the stability of a power grid; besides, the design of a regulation and control operation mechanism can dynamically adjust constraint conditions, optimize the balance between power supply and frequency modulation service, improve the safety and economy of a power system, and finally realize stable price signals, reduce market fluctuation and improve efficient utilization of power resources.

Description

Technical Field

[0001] The present invention relates to the technical field of power data dispatching management, and in particular to a frequency regulation and electric energy joint clearing method, device and equipment in a power market. Background Art

[0002] The electricity spot market refers to the form of electricity trading on a day-ahead and intraday time scale. Compared with the medium- and long-term electricity market, its core feature is that the trading results need to be closely integrated with the physical characteristics of the power grid. This feature requires the spot market to consider not only the economic efficiency of market transactions, but also the safety and stability of power system operation, which makes the market trading mechanism more complex; in the electricity spot market, power trading and frequency regulation services are gradually incorporated into market-oriented operations. The main function of the power market is to achieve a balance between power supply and demand through market mechanisms, while the ancillary service market provides necessary support for maintaining frequency stability and voltage stability in the operation of the power system. However, the frequency regulation and power joint clearing devices in the traditional power market usually rely on the supply and demand relationship to determine the price during the power clearing process, while the price of frequency regulation services is often affected by frequency fluctuations or real-time demand changes. Therefore, in the case of conflicting price signals, the frequency regulation market price is inconsistent with the power clearing price, resulting in low resource allocation efficiency and inflexibility, and even affecting the price reliability of the overall output of the device.

[0003] Therefore, the frequency regulation and electricity joint clearing method of this application combines electricity trading with the frequency regulation service market through a unified optimization framework, thereby coordinating price signals to achieve a balance between electricity supply and demand, while optimizing the configuration of frequency regulation services to improve resource utilization efficiency and reduce system operating costs. This can better reflect the operating constraints and economic requirements of the generator set, achieve a deep integration of the market mechanism and the physical characteristics of the power grid, and provide a strong guarantee for the efficient and safe operation of the modern power system.

[0004] To sum up, how to organically combine electricity trading with the frequency regulation service market to make the power system operate efficiently and flexibly is an urgent problem to be solved and optimized in the frequency regulation and electricity joint clearing device under the electricity market. Summary of the invention

[0005] The present invention provides a method, device and equipment for frequency regulation and electric energy joint clearing in the power market, which solves the technical problem in the related technology of how to make the power system operate efficiently and flexibly by organically combining electric energy trading and frequency regulation service market.

[0006] In order to solve the above technical problems, the present invention provides a method, device and equipment for frequency regulation and electric energy joint clearing in the power market. The specific technical solution is as follows:

[0007] In a first aspect, a frequency regulation and electric energy joint clearing method in an electric power market comprises the following steps:

[0008] Collect various frequency regulation service data and power joint clearing data to obtain data sets;

[0009] The data set is trained to construct a prediction model to obtain stable price signal data; at least one frequency modulation and electric energy joint clearing data item in the newly acquired data set is input into the prediction model to obtain a price signal prediction result of the newly acquired data set;

[0010] wherein, the price signal fluctuation amplitude is obtained according to the stable price signal data and the price signal prediction result;

[0011] Based on the newly acquired data set, collecting power grid frequency data of corresponding time nodes;

[0012] By using the price signal fluctuation amplitude and the power grid frequency data, it is determined whether a price signal conflict occurs between the stable price signal data and the price signal prediction result;

[0013] When a price signal conflict occurs, a data set of potential risk indicators for power operation is obtained; a control operation mechanism is designed based on the data set of potential risk indicators for power operation; the control operation mechanism constrains the data set price signal through the control constraint indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index;

[0014] The price signal after eliminating signal conflicts is evaluated to coordinate the balance of power supply and the stability of frequency regulation services.

[0015] As a further optimization scheme of the present invention, the prediction model includes:

[0016] Preprocessing the collected multiple frequency regulation service data and electric energy joint clearing data to obtain a preprocessed data set; encoding the preprocessed data set into sequence data to obtain a training set; and constructing the prediction model through training with the training set;

[0017] At least one data item of the preprocessed data set is input into the prediction model; the prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the intermediate representation data of multiple hidden layers are transmitted to the output layer, and the output layer outputs the price signal recognition result representing the frequency modulation service data and the electricity joint clearing data.

[0018] As a further optimization scheme of the present invention, judging whether the stable price signal data conflicts with the price signal prediction result by using the price signal fluctuation amplitude and the power grid frequency data includes:

[0019] Setting a price signal fluctuation range based on the data set; obtaining a price signal fluctuation amplitude through the price signal prediction result and the stable price signal data;

[0020] Compare the price signal fluctuation amplitude with the price signal fluctuation range to determine whether the fluctuation amplitude is within the price signal fluctuation range; when the fluctuation amplitude exceeds or is lower than the price signal fluctuation range, it can be obtained that there is a signal conflict risk between the stable price signal data and the price signal prediction result;

[0021] Preset a frequency standard range based on the risk of signal conflict; compare the power grid frequency with the preset frequency standard range; when the power grid frequency deviates from the preset frequency standard range, determine that the stable price signal data and the price signal prediction result have a signal conflict risk;

[0022] Based on the comparison result and the judgment result, it is determined that the price signal data conflicts with the stable price signal data.

[0023] As a further optimization scheme of the present invention, the price signal fluctuation range is set based on the data set; and the price signal fluctuation amplitude is obtained by using the price signal prediction result and the stable price signal data, including:

[0024] According to the price signal prediction result and the stable price signal data, by:

[0025] , to obtain the mean fluctuation of price signals; represents the mean fluctuation of the price signal in the ith period; Indicates the number of price signal fluctuations;

[0026] According to the price signal fluctuation mean, by: , to obtain the price signal slope data; where, Represents the price signal slope data; Price signal data representing the price signal prediction moment; represents the price signal data at the time when the price signal is stable, and m represents the m moments before the price signal prediction moment;

[0027] Based on the price signal slope data, by: , to obtain the price signal fluctuation amplitude; where, represents the fluctuation amplitude of the price signal; m represents the fluctuation frequency of the price signal;

[0028] Set the price signal fluctuation range ; In the formula, Indicates the upper limit of the price signal fluctuation range; Indicates the lower limit of the price signal fluctuation range; according to the price signal fluctuation amplitude, set an array Δt for storing the fluctuation amplitude;

[0029] when hour, ;when hour, ;when hour, ; It is thus determined that there is a risk of signal conflict between the stable price signal data and the price signal prediction result.

[0030] As a further optimization scheme of the present invention, when the price signals have conflicted, a data set of potential risk indicators for power operation is obtained, including:

[0031] Based on the data set, by: ; To obtain the power dispatch imbalance risk index data; where R i Represents the power dispatch imbalance risk indicator data; P i represents the actual output power of the ith generator set during power operation, P d represents the expected power determined according to the market clearing results; n represents the number of generating units;

[0032] Based on the power dispatch imbalance risk indicator data, by: ;

[0033] To obtain the load gap risk index data; where R y represents the load gap risk indicator data; Δf(t) represents the time period [t 1 ,t 2 ] frequency deviation within ;

[0034] Based on the load gap risk index data obtained and combined with the power dispatch imbalance risk index data, a data set of potential risk indicators for power operation is formed. The larger the data set of potential risk indicators for power operation is, the greater the risk of price signal conflict is.

[0035] As a further optimization scheme of the present invention, a control operation mechanism is designed according to the power operation potential risk indicator data set, including:

[0036] According to the electric power operation potential risk indicator data set, a control constraint indicator data set is obtained; the control constraint indicator data set includes power imbalance scheduling constraint conditions and load gap risk constraint conditions;

[0037] The control operation mechanism is designed according to the power grid constraint condition indicators; the control operation mechanism constrains the price signal of the data set through the control constraint condition indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index.

[0038] As a further optimization scheme of the present invention, the control operation mechanism constrains the data set price signal through the control constraint condition indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index, including:

[0039] The control operation mechanism is based on the power imbalance scheduling constraint and load gap risk constraints , to eliminate the risk of price risk conflict; where, Indicates the minimum power indicator data; Indicates the maximum power index data; represents the set of generators participating in the gap constraint;

[0040] Based on the power imbalance dispatch constraint and the load gap risk constraint, by:

[0041] ; To obtain the control operation index; where, represents the control operation index; k represents the control response coefficient;

[0042] When the regulation operation index is within a preset range, the regulation operation mechanism dynamically eliminates the price conflict risk.

[0043] As a further optimization scheme of the present invention, the price signal after eliminating the signal conflict is evaluated to coordinate the balance of power supply and the stability of frequency regulation service, including:

[0044] Based on the price signal data after eliminating conflicts, a price signal evaluation model is constructed by training; the price signal evaluation model is constructed according to the objective function Combined with the regulatory constraint indicator data set to evaluate the price signal after eliminating the conflict; where C i represents the cost function of the i-th generator set, Pl represents the power data after the dispatching operation mechanism; λ j represents the jth price signal after the dispatch operation mechanism, P mrepresents the mth grid reserve capacity that provides the dispatching operation mechanism;

[0045] The price signal after conflict elimination is newly entered into the price signal evaluation model, and the price signal evaluation model outputs the identification result of the newly entered price signal after conflict elimination to obtain an accurate price signal, otherwise it returns to the step of eliminating price signal conflict and re-operates; thereby coordinating the balance of power supply and the stability of frequency regulation services.

[0046] In the second aspect, a frequency regulation and electric energy joint clearing device in the power market includes:

[0047] Data collection module: It is used to collect various frequency regulation service data and electric energy joint clearing data to obtain a data set;

[0048] Data analysis module: used to train the data set to construct a prediction model to obtain stable price signal data; input at least one frequency modulation and electric energy joint clearing data item in the newly acquired data set into the prediction model to obtain the price signal prediction result of the newly acquired data set;

[0049] The dispatching operation module is used to obtain a data set of potential risk indicators for power operation when a conflict occurs in the price signal; design a control operation mechanism based on the data set of potential risk indicators for power operation, wherein the control operation mechanism constrains the data set price signal through the control constraint indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index;

[0050] Evaluation module: It is used to evaluate the price signal after eliminating signal conflicts to coordinate the balance of power supply and the stability of frequency regulation services.

[0051] In the third aspect, a device for frequency regulation and electric energy joint clearing in the power market includes:

[0052] A processor, and a memory connected to the processor;

[0053] The memory is used to store a computer program, and the computer program is used to execute a frequency regulation and electric energy joint clearing method in an electric power market;

[0054] The processor is used to call and execute the computer program in the memory.

[0055] The present invention has at least the following beneficial effects: by comprehensively collecting frequency regulation services and joint clearing data of electric energy, the present invention can establish a more comprehensive data foundation, providing high-quality input for subsequent modeling and analysis. The diversity and completeness of the data set help to capture multi-dimensional information in the electricity market and improve prediction accuracy; by training the data set, a prediction model is constructed to generate stable price signal data, and this process can effectively reduce random fluctuations in the data. Stable price signal data can be used as a benchmark for subsequent analysis and regulation, providing a standardized measurement tool; the joint clearing data in the newly acquired data set is input into the prediction model to obtain the price signal prediction result. The prediction model can quickly generate the corresponding price signal prediction result by analyzing the new data, and adapt to the ever-changing electricity market situation. This step improves the system's responsiveness to new data and supports dynamic adjustment and real-time prediction.

[0056] According to the stable price signal data and the price signal prediction results, the price signal fluctuation amplitude is obtained; by comparing the stable price signal data and the prediction results, the fluctuation amplitude is calculated, and abnormal changes in the price signal can be identified, which is convenient for real-time monitoring of the market stability. This provides an important basis for conflict judgment and risk management; based on the newly acquired data set, the grid frequency data is collected; the grid frequency data reflects the operating status of the power system. Combining the newly acquired data set with the grid frequency data can more comprehensively reflect the correlation between the price signal and the grid operation, laying a data foundation for subsequent analysis.

[0057] Price signal conflicts can be judged through the price signal fluctuation amplitude and power grid frequency data; the judgment of price signal conflicts can timely identify price anomalies and potential risks, ensuring the rationality and stability of power market transactions. This step provides a key diagnostic basis for risk management; obtain a data set of potential risk indicators for power operation; through in-depth analysis of price signal conflicts and extraction of potential risk indicators for power operation, it can help identify possible operational problems in the system and provide direction for the design of regulation mechanisms.

[0058] Design a control and regulation operation mechanism to regulate constraints in real time; the control mechanism can quickly respond to market fluctuations by dynamically adjusting the constraints of frequency regulation services and joint clearing of electricity, reduce the occurrence of price signal conflicts, and improve the flexibility and adaptability of power system operation; collect and compare price signals of the regulated data set to eliminate signal conflicts; verify the effectiveness of the control mechanism by comparing the regulated data, further optimize the price signal performance of the data set, and ensure the stability and consistency of the price signal.

[0059] Evaluate the price signal after eliminating signal conflicts, and coordinate the balance of power supply and the stability of frequency regulation services; the final evaluation ensures the coordination between the balance of power supply and the stability of frequency regulation services, which can not only meet market price demands, but also ensure the safe operation and reliability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of a frequency regulation and electric energy joint clearing method in a power market provided by an embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of a frequency regulation and electric energy joint clearing device in a power market provided by an embodiment of the present invention;

[0062] Figure 3 It is a schematic diagram of a frequency regulation and electric energy joint clearing device in a power market provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.

[0064] This embodiment provides a method, device and equipment for frequency regulation and electric energy joint clearing in the power market, and the specific implementation methods are as follows:

[0065] like Figure 1 As shown, a frequency regulation and electric energy joint clearing method in the power market includes the following steps:

[0066] Step 11, collecting multiple frequency regulation service data and electric energy joint clearing data to obtain a data set;

[0067] Step 12: training the data set to construct a prediction model to obtain stable price signal data; inputting at least one frequency modulation and electric energy joint clearing data item in the newly acquired data set into the prediction model to obtain a price signal prediction result of the newly acquired data set;

[0068] wherein, the price signal fluctuation amplitude is obtained according to the stable price signal data and the price signal prediction result;

[0069] Based on the newly acquired data set, collecting power grid frequency data of corresponding time nodes;

[0070] By using the price signal fluctuation amplitude and the power grid frequency data, it is determined whether a price signal conflict occurs between the stable price signal data and the price signal prediction result;

[0071] Step 13, when the price signal has conflicted, obtain a data set of potential risk indicators for power operation; design a control operation mechanism based on the data set of potential risk indicators for power operation; the control operation mechanism constrains the data set price signal through the control constraint indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index;

[0072] Step 14, evaluating the price signal after eliminating signal conflicts to coordinate the balance of power supply and the stability of frequency regulation services.

[0073] In an embodiment of the present invention, step 11 is to collect relevant frequency regulation service data and joint clearing data of electric energy from multiple data sources. Frequency regulation services are usually related to the regulation of power grid frequency, while joint clearing data of electric energy refers to the clearing results of matching supply and demand of electric energy in the power market. These data may include information such as power demand, supply, and price; by collecting these data, a data set is obtained, which includes multi-dimensional data on power frequency regulation and power supply, providing a basis for the subsequent construction of a prediction model; ensuring the diversity of data, being able to fully reflect the real-time operating status and market regulation of the power system, and providing rich input data for establishing an accurate prediction model.

[0074] It can effectively capture the dynamic changes in the electricity market and frequency regulation services, and provide necessary data support for subsequent steps.

[0075] Step 12 analyzes the multi-dimensional data collected in step 11 and uses machine learning or statistical models (such as regression analysis, neural networks, time series models, etc.) to train a prediction model; the purpose of the prediction model is to predict the price trend of the electricity market and the changes in the demand for frequency regulation services based on past data patterns, so as to obtain stable price signal data; then, the newly acquired data set (i.e., the new round of frequency regulation and electricity joint clearing data) is input into the model, and the new price signal prediction results are obtained through the model's prediction; by establishing a reliable prediction model, stable and real-time price signal predictions can be provided. This is crucial for power systems and market operations, and can predict the fluctuation trend of electricity prices in advance, helping power companies and dispatching agencies make scientific decisions; stable price signals can reduce market uncertainty and help power dispatchers optimize power distribution; the price signal fluctuation amplitude is obtained based on stable price signal data and price signal prediction results;

[0076] Based on the obtained stable price signal data and price signal prediction results, the price fluctuation is analyzed by calculating the fluctuation amplitude between the two; the fluctuation amplitude reflects the range and frequency of changes in electricity market prices, and can measure the stability of the market and the reliability of price signals; through the calculation of the fluctuation amplitude, the stability of price signals and market uncertainty can be evaluated, which facilitates the subsequent response measures (such as price signal adjustment or frequency regulation service optimization) to ensure the smooth operation of the system.

[0077] Based on the newly acquired data set, the grid frequency data of the corresponding time node is collected; under the new data set (i.e., a new round of frequency modulation and electric energy joint clearing data), the grid frequency data is collected; the grid frequency is one of the important indicators of power system stability, and the frequency fluctuation usually reflects whether the power supply and demand are balanced. The combination of frequency data and price signal analysis can help identify potential system risks; the grid frequency data provides a direct reflection of the stability of the power system. Combined analysis with price signals helps to timely identify potential problems in the power market and system operation, such as supply and demand imbalance or abnormal price fluctuations; price signal conflicts are judged through the price signal fluctuation amplitude and grid frequency data.

[0078] Using the price signal fluctuation amplitude and grid frequency data obtained in step 12 and step 13, a certain threshold judgment rule is used to determine whether a price signal conflict occurs. Specifically, if the price signal fluctuates too much and the grid frequency fluctuates abnormally (for example, the frequency deviates from the normal range), it may mean that the price signal does not match the actual demand of the grid, resulting in a conflict; price signal conflicts usually indicate that there is an inconsistency between market dispatch and grid dispatch, which may lead to unstable system operation or an imbalance between power supply and demand; identifying the conflict between price signals and grid frequency in advance can help avoid potential power supply interruptions or system instability problems, and ensure the safety and stability of the power system.

[0079] Step 13: When a conflict in price signals is detected, obtain an indicator data set related to potential risks in power operation. These indicators may include information such as grid load, generator status, and system safety margin; the purpose of these data sets is to provide support for subsequent risk analysis and regulation decisions; the collection of potential risk indicators for power operation can provide key data for judging the operating status of the power system, help decision makers identify risk sources, and take effective measures to prevent potential failures; through real-time monitoring and risk assessment, timely adjustment measures can be taken when conflicts occur to avoid large-scale instability of the power system; according to the potential risk indicators for power operation, design a regulation operation mechanism, which will adjust the dispatching strategy according to the real-time system status and predicted risk level; the regulation mechanism constrains the price signal through the constraint condition indicator data set, such as adjusting the power demand response, the frequency regulation service provision, or the start and stop of the generator set to eliminate the conflict between the price signal and the grid frequency data; the regulation operation mechanism can realize dynamic optimization and adjustment of the system, eliminate the contradiction between the market and the grid, and ensure the balance between power supply and demand; through precise regulation, the stability of the power system can be improved and the system risk caused by price signal fluctuations or grid frequency fluctuations can be reduced.

[0080] Step 14 evaluates the price signal after eliminating the signal conflict in step 13 to ensure that it maintains a balance between power supply and frequency regulation services. This evaluation process may include a comprehensive analysis of the frequency of the power grid, power demand and supply, price fluctuations, etc.; ensure the balance of power supply and the stability of frequency regulation services, and provide efficient and safe operation support for the power system; through comprehensive evaluation and coordination, the stability of the power market and frequency regulation services can be ensured to avoid excessive fluctuations in price signals affecting power supply; ultimately, while ensuring that the power grid is operating efficiently and stably, the power market can provide reasonable price signals to participants to ensure the supply of power and system stability.

[0081] The above steps work together, and the specific core goal is to ensure the coordination between the price signal of the power system and the operation status of the power grid through accurate data collection, model prediction, risk assessment and control mechanism, so as to achieve the purpose of stabilizing the power market and ensuring power supply. Each step provides strong support for the next step of optimization decision-making, thereby effectively improving the safety and economy of the power system.

[0082] In a preferred embodiment of the present invention, the prediction model in step 12 above includes:

[0083] Step 121, preprocessing the collected multiple frequency regulation service data and electric energy joint clearing data to obtain a preprocessed data set; encoding the preprocessed data set into sequence data to obtain a training set; and constructing the prediction model through training with the training set;

[0084] Step 122, input at least one data item of the preprocessed data set into the prediction model; the prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the intermediate representation data of multiple hidden layers are transmitted to the output layer, and the output layer outputs the price signal recognition result representing the frequency modulation service data and the electricity joint clearing data.

[0085] In an embodiment of the present invention, in step 121, the various frequency regulation service data include various service indicators for grid frequency regulation during system operation (such as power response speed, frequency deviation, response time, etc.); the electric energy joint clearing data include result data of electric energy clearing in the power market, including electricity price, load demand, and supply and demand balance.

[0086] Data preprocessing: The collected raw data is processed through data cleaning methods (such as filtering, removing missing values, and detecting outliers) to remove invalid data; then the data of different dimensions are normalized (such as compressing the data to the [0,1] interval) or standardized (such as zero mean unit variance standardization) to ensure that the data has a consistent scale; then feature data that is highly relevant to the prediction task is selected, such as historical price fluctuations, the degree of matching between service response indicators and power clearing, etc., and the preprocessed data is converted into a time series format and encoded into sequence data with a time dimension. The purpose is to retain the temporal nature and dynamic change relationship of the data. Finally, the time series data is divided into a training set (for model training) and a validation set / test set (for model verification and testing); data preprocessing can effectively improve data quality, remove redundant noise, and make model training more efficient and accurate; time series encoding can capture the dynamic time series characteristics between frequency regulation services and power joint clearing data; the construction of the training set provides a reliable data foundation for subsequent prediction models and improves the generalization ability and performance of the model.

[0087] Step 122 inputs at least one data item in the preprocessed data set into the prediction model; the data item is serialized and encoded to retain the historical temporal relationship;

[0088] Prediction model structure:

[0089] Input layer: Receives preprocessed input data, with dimensions matching the number of data features.

[0090] First hidden layer, second hidden layer, third hidden layer:

[0091] Each hidden layer extracts data features through neural network units (such as fully connected layers, LSTM, GRU, etc.); the role of each hidden layer is to gradually extract more advanced features and learn nonlinear relationships and time series dependencies in the data.

[0092] Intermediate representation data: refers to the feature vectors output by the hidden layer. These vectors represent the model's abstract expression of data features.

[0093] Output layer: The intermediate representation data from multiple hidden layers is transmitted to the output layer, and the final output result is calculated through the activation function (such as Softmax, Sigmoid); the output result is the price signal recognition result, which represents the price relationship between the frequency regulation service data and the electricity joint clearing data.

[0094] Result output: Through the trained prediction model, the input data can quickly output the recognition results, such as the prediction of electricity clearing price and the price change trend of frequency regulation service; the multi-layer hidden layer can extract complex data features step by step, and improve the model's learning ability for nonlinear relationships and time series dependencies; the multi-dimensional understanding of data by different hidden layers is retained, which helps the model make more accurate predictions at the output layer; through the model output results, the price signals of frequency regulation services and electricity clearing can be better identified, assisting power market decision-making and scheduling optimization.

[0095] Step 121 improves data quality through data preprocessing, constructs a training set, and encodes the data into a time series input model; Step 122 uses a deep learning model to perform multi-layer feature extraction on the input data, and finally outputs an accurate price signal recognition result; improves model training efficiency and data utilization; extracts deep features through a multi-layer structure and enhances the prediction accuracy of the model; The output price signal recognition result has an important guiding role in frequency regulation services and the electric energy market, optimizes market operation, and improves economy and stability.

[0096] In a preferred embodiment of the present invention, the above step 12 uses the price signal fluctuation amplitude and the power grid frequency data to determine whether the stable price signal data conflicts with the price signal prediction result, including:

[0097] Step 123, setting a price signal fluctuation range based on the data set; obtaining a price signal fluctuation amplitude through the price signal prediction result and the stable price signal data;

[0098] Step 124, comparing the price signal fluctuation amplitude with the price signal fluctuation range to determine whether the fluctuation amplitude is within the price signal fluctuation range; when the fluctuation amplitude exceeds or is lower than the price signal fluctuation range, it is determined that there is a signal conflict risk between the stable price signal data and the price signal prediction result;

[0099] Step 125, presetting a frequency standard range based on the existence of a signal conflict risk; comparing the power grid frequency with the preset frequency standard range; when the power grid frequency deviates from the preset frequency standard range, determining that a signal conflict risk has occurred between the stable price signal data and the price signal prediction result;

[0100] Step 126: Based on the comparison result and the judgment result, determine whether the price signal data conflicts with the stable price signal data.

[0101] In the embodiment of the present invention, in step 123, the price signal fluctuation range is set and the fluctuation amplitude is calculated; the normal fluctuation range of the price signal is set according to the data set used (including historical data or real-time market price signal data). This is usually based on statistical analysis, such as mean and standard deviation, or a preset threshold; the predicted price signal is compared with the stable price signal data to obtain the fluctuation amplitude; by setting the price signal fluctuation range and calculating the fluctuation amplitude, it is helpful to quickly detect abnormal fluctuations of the price signal, laying a foundation for subsequent judgment of signal conflict risks;

[0102] Step 124 compares the fluctuation amplitude obtained in step 123 with the set price signal fluctuation range to determine whether it exceeds or falls below the range;

[0103] If the fluctuation amplitude is within the range, it means that the signal fluctuation is normal and no further measures are needed;

[0104] If the fluctuation amplitude exceeds or falls below the range, it indicates that there is a potential risk of signal conflict between the price signal prediction result and the stable price signal data;

[0105] By clearly comparing the fluctuation amplitude with the normal fluctuation range, signal anomalies can be accurately identified, potential conflicts can be discovered in a timely manner, and the further spread of signal distortion or misjudgment can be prevented.

[0106] When the price signal obtained in step 124 has a risk of signal conflict, step 125 introduces a preset grid frequency standard range, which is usually based on industry specifications or standards for stable grid operation: the grid frequency is normal within the range of 50±0.2Hz.

[0107] Frequency comparison, comparing the actual grid frequency with the preset frequency standard range:

[0108] If the grid frequency deviates from the standard range, the risk of conflict between the price signal prediction results and the stable price signal data will be further confirmed;

[0109] If the grid frequency is within the standard range, the possibility of signal conflict is eliminated.

[0110] By introducing the standard range and comparison of power grid frequency, the authenticity of signal conflict risk can be further verified, the accuracy of abnormal signal judgment can be ensured, and the reliability and stability of the system can be enhanced.

[0111] Step 126 comprehensively analyzes the result of the price signal fluctuation amplitude determination in step 124 and the result of the grid frequency comparison in step 125;

[0112] If both judgments show abnormality: Confirm that the price signal data conflicts with the stable price signal data;

[0113] If only one item shows an abnormality: further analyze the cause, which may be data noise or temporary fluctuations.

[0114] Output conflict results: Output conflict judgment results to notify related operations or adjust the prediction algorithm of price signals; by comprehensively judging the fluctuation amplitude and comparing the results with the grid frequency, the accuracy of judging signal conflicts can be improved to prevent false alarms or missed alarms. At the same time, it provides strong support for subsequent grid stability control and price signal adjustment.

[0115] In summary, steps 123 and 124 effectively capture abnormal fluctuations in price signals by setting the fluctuation range and comparing the fluctuation amplitude; step 125 further verifies the authenticity of the anomaly and prevents misjudgment by introducing grid frequency comparison; step 126 comprehensively analyzes all judgment results to ensure accurate judgment of signal conflicts and improve the stability and reliability of grid operation; the overall process can not only identify anomalies, but also provide data support for real-time adjustment of price signal prediction models and optimization of grid operation.

[0116] In a preferred embodiment of the present invention, the above step 123 further includes:

[0117] Step 1231, according to the price signal prediction result and the stable price signal data, by:

[0118] , to obtain the mean fluctuation of price signal; represents the mean fluctuation of the price signal in the i-th period; Indicates the number of price signal fluctuations;

[0119] Step 1232, according to the price signal fluctuation mean, by: , to obtain the price signal slope data; where, Represents the price signal slope data; Price signal data representing the price signal prediction moment; represents the price signal data at the time when the price signal is stable, and m represents the m moments before the price signal prediction moment;

[0120] Step 1233, based on the price signal slope data, by: , to obtain the price signal fluctuation amplitude; where, represents the fluctuation amplitude of the price signal; m represents the fluctuation frequency of the price signal;

[0121] Step 1234, setting the price signal fluctuation range ; In the formula, Indicates the upper limit of the price signal fluctuation range; Indicates the lower limit of the price signal fluctuation range; according to the price signal fluctuation amplitude, set an array Δt for storing the fluctuation amplitude;

[0122] Step 1235, when hour, ;when hour, ;when hour, ; It is thus determined that there is a risk of signal conflict between the stable price signal data and the price signal prediction result.

[0123] In the embodiment of the present invention, in step 1231, based on the price signal prediction result and the stable price signal data, the fluctuation mean of the price signal is calculated by statistically analyzing the change (fluctuation) of the price signal. The fluctuation mean can be understood as the average fluctuation degree of the price signal over a period of time;

[0124] This step helps understand the overall volatility level of the price signal, thus providing a basis for further analysis; it provides a rough fluctuation range, thus helping the subsequent steps to determine whether the price signal is in a stable state.

[0125] Step 1232 calculates the slope of the price signal based on the fluctuation mean of the price signal. The slope indicates the rate of change of the price signal over time; the slope data is calculated by comparing the difference between the predicted moment and the stable moment of the price signal, combined with the data of the previous m moments. That is, compare the predicted price at the current moment with the price at the historical stable moment, and analyze the change trend between them; the calculated slope can reflect the direction and rate of price change, and help determine whether the price is rising, falling or stable. If the slope value is large, it means that the price fluctuates violently, otherwise, it means that the fluctuation is small, which helps to determine whether the market has a large risk of change.

[0126] Step 1233 further calculates the amplitude of the price signal fluctuation based on the slope data of the price signal. The amplitude of fluctuation generally refers to the intensity or range of the price signal fluctuation;

[0127] The fluctuation amplitude is related to the fluctuation frequency (i.e. the number of fluctuations). The fluctuation amplitude can be calculated through the relationship between the slope data and the fluctuation frequency; this step can reflect the absolute amplitude of price fluctuations, so that we can understand the intensity of price fluctuations more clearly; when the fluctuation amplitude is large, it indicates that the market volatility is high, which is of great value for predicting market risks.

[0128] Step 1234 sets the fluctuation range of the price signal based on the fluctuation amplitude of the price signal and the calculation result of the fluctuation amplitude. The fluctuation range usually includes upper and lower limits, that is, within a preset time period, the expected fluctuation amplitude of the price signal will not exceed this range; the upper and lower limits of the price signal fluctuation range can be set according to historical data or a prediction model; the setting of the fluctuation range can be achieved by establishing an array Δt for storing the fluctuation amplitude, which records the price fluctuation amplitude at each time point.

[0129] This step can set the expected range of price fluctuations, helping the subsequent steps to determine whether the price is within the normal fluctuation range; when the actual fluctuation exceeds the predetermined range, it may indicate abnormal fluctuations, which in turn affects the accuracy of the prediction results.

[0130] Step 1235 determines whether there is a conflict risk by comparing the difference between the price signal prediction result and the actual stable price signal data based on the price signal fluctuation range and the stable price signal data. If there is a large difference between the prediction result and the stable price signal data, it may indicate that there is an error in the prediction or the market state has changed significantly. According to the set fluctuation range and the stable price signal, it is determined whether the prediction result exceeds the normal fluctuation range, thereby determining whether there is a conflict risk. This can timely discover the difference between the prediction signal and the actual signal, determine whether there is a signal conflict, and then make corrections or adjustments, which is very beneficial for risk management and decision-making, and helps to respond quickly when the market fluctuates greatly, and avoid losses caused by prediction errors.

[0131] In summary, through various steps, the price signal's fluctuation mean, slope, amplitude, fluctuation range and other multi-dimensional analysis can be coordinated to help more accurately predict market price trends and identify potential conflicts or abnormal fluctuations in a timely manner. Its beneficial effects are reflected in the following aspects:

[0132] Through multi-level fluctuation analysis, the fluctuation pattern of price signals can be grasped more accurately;

[0133] Timely detection of abnormal fluctuations in price signals helps to warn of possible market risks;

[0134] By setting a reasonable fluctuation range, it helps manage price fluctuations and avoids risks caused by sharp fluctuations;

[0135] By calculating and analyzing data such as fluctuation mean, slope, and amplitude, we can effectively judge the stability and abnormal fluctuations of the market.

[0136] In a preferred embodiment of the present invention, when the price signals conflict in the above step 13, obtaining a data set of potential risk indicators for power operation includes:

[0137] Step 131, based on the data set, by: ; To obtain the power dispatch imbalance risk index data; where R i Represents the power dispatch imbalance risk indicator data; P i represents the actual output power of the ith generator set during power operation, P d represents the expected power determined according to the market clearing results; n represents the number of generating units;

[0138] Step 132, based on the power scheduling imbalance risk indicator data, by: ; To obtain the load gap risk index data; where R y represents the load gap risk indicator data; Δf(t) represents the time period [t 1 ,t 2 ] frequency deviation within ;

[0139] Step 133, based on the load gap risk index data obtained and combined with the power dispatch imbalance risk index data, a data set of potential risk indexes for power operation is formed. The larger the data set of potential risk indexes for power operation is, the greater the risk of price signal conflict is.

[0140] In an embodiment of the present invention, in step 131, the deviation between the actual output power and the expected power is obtained for each generator set, and this deviation reflects the difference between the actual and expected power of the generator set in the market dispatch; the power dispatch imbalance risk index is a certain aggregation or weighted value of these deviations, which may comprehensively consider the imbalance risk of all generator sets; by evaluating the power dispatch imbalance risk, the possible risk of power shortage or surplus in the power system can be discovered in time, helping operation and maintenance personnel to optimize the dispatch and avoid system instability caused by the mismatch between power supply and demand; it can also provide necessary risk information for the price mechanism of the power market, so as to make dynamic adjustments according to market demand and actual system conditions.

[0141] Step 132 can obtain the gap between load and generation by monitoring the frequency fluctuation of the power system. For example, a decrease in frequency may mean that the load demand exceeds the generation capacity, while an increase in frequency may mean that there is excess generation. yAssess the risk of load gap based on frequency deviation. The greater the frequency deviation, the more serious the imbalance between system load and power generation, and thus the greater the risk of load gap. Assessing the risk of load gap helps to discover the load change trend in the power system, so as to take scheduling measures in advance to adjust power generation and load, avoid frequency imbalance, and maintain system stability. For power grid operators, being able to accurately grasp the risk of load gap helps improve the scheduling efficiency and safety of the power grid.

[0142] Step 133 calculates the power dispatch imbalance risk index data through step 131, and step 132 calculates the load gap risk index data.

[0143] In step 133, the two indicator data will be combined and summarized into a data set of potential risk indicators for power operation. This means that the risks of power dispatch imbalance and load gap will be comprehensively considered to form a data set for comprehensively evaluating the potential risks of the power system; this comprehensive data set contains comprehensive information on the two main risks of system dispatch imbalance and load gap. When the value of this potential risk data set increases, it means that the risks faced by the power system are more serious, and price signal conflicts or other system instability problems may occur; after summarizing the two risk indicators, it can provide a more comprehensive risk assessment for the power market and power grid operation, and help formulate more accurate power dispatch and market price strategies; by continuously monitoring and analyzing the data set of potential risk indicators for power operation, it can predict possible price fluctuations or conflicts in the power system, make plans in advance, and avoid the spread of risks; in terms of market mechanisms, it can better understand the changes in risk premiums and promote the stable operation of the market.

[0144] Step 131 provides an assessment of the actual and expected power deviation for power system dispatch by calculating the risk of power dispatch imbalance, helping to make power market dispatch more accurate; Step 132 assesses the risk of load gap by frequency deviation, further optimizing the power system's ability to respond to load changes; Step 133 combines the two risk assessments to generate a potential risk data set for power operation, enabling the power system to more comprehensively assess potential dispatch imbalance and load gap risks, and take risk prevention and control measures in advance; The beneficial effects of this risk assessment method include improving the dispatch accuracy of the power system, ensuring the safe operation of the power grid, and providing the power market with more scientific prices and risk signals.

[0145] In a preferred embodiment of the present invention, in the above step 13, designing a control operation mechanism according to the power operation potential risk indicator data set includes:

[0146] Step 134, obtaining a control constraint condition indicator data set according to the power operation potential risk indicator data set; the control constraint condition indicator data set includes a power imbalance dispatch constraint condition and a load gap risk constraint condition;

[0147] Step 135, designing the control operation mechanism according to the power grid constraint condition index; the control operation mechanism constrains the data set price signal through the control constraint condition index data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index.

[0148] In the embodiment of the present invention, in step 134, based on the previously calculated power operation potential risk indicator data set (including power dispatch imbalance risk and load gap risk), a new data set, namely, a control constraint indicator data set, is generated; the control constraint indicator data set includes two main constraints:

[0149] Power imbalance scheduling constraints: According to the power scheduling imbalance risk index (such as R in the power scheduling imbalance dataset), i ), evaluate the possible imbalance degree of each generator set in the system during scheduling, so as to set the upper and lower limits of the output power of the generator set;

[0150] Load gap risk constraint: According to the load gap risk indicator (such as R in the load gap risk dataset), y ), assess the gap between the system's load demand and power generation supply, and determine how the power system should adjust power generation output or load distribution to reduce risks.

[0151] These constraints dynamically adjust the generation capacity, load distribution, and dispatch strategies in the system by analyzing the power imbalance and load gap risks. Through the risk data set, the grid can adjust the constraints of different types of generators (such as adjustable load, base load, and renewable energy).

[0152] By introducing control constraints, the operating behavior of the power grid under different load and power generation conditions can be controlled more accurately, which helps to reduce system instability and avoid possible power failures; it provides more detailed dispatch rules and enhances the power system's ability to respond to uncertain factors, such as market price fluctuations, demand changes, etc.; it helps to balance the dispatch between different power sources in actual operations, especially when a high proportion of renewable energy is connected, to ensure the safety and reliability of the power system.

[0153] Step 135 designs a control operation mechanism according to the control constraint indicator data set (including power imbalance dispatch constraint and load gap risk constraint) in step 134. The purpose of this mechanism is to optimize the power system dispatch through reasonable control strategies and reduce the risks caused by unbalanced power dispatch or load gap; the mechanism should include how to dynamically adjust the price signal in the power market to balance the relationship between power demand and supply and ensure the stable operation of the power grid and the market.

[0154] Price signal constraints: Price signals in the power market usually reflect the supply and demand situation and market risks. If there is an imbalance in power dispatch or a load gap in the power system, the price signal may fluctuate violently, leading to instability in the power market price. At this time, the control operation mechanism constrains the price signal to avoid excessive fluctuations in these price signals and stabilize the market; by setting corresponding constraints in the control operation mechanism (for example, limiting the maximum power generation of the generator set, setting the maximum deviation of the load response, etc.), it can effectively reduce the conflict of price signals and avoid the contradiction between market prices and the actual situation of the system.

[0155] The role of the regulation and control operation index: The regulation and control operation index is an indicator to measure the regulation effect of the power system. It reflects the effectiveness of the regulation strategy, especially how the system achieves balance under the constraints of power imbalance and load gap risks. The signal conflict between the regulation and control operation index and the price signal prediction results is small, which means that the regulation mechanism can effectively guide the system towards a more stable operating state and avoid drastic fluctuations or distortions in price signals.

[0156] By designing a control and operation mechanism, the power system can find a balance between the market mechanism and actual operating needs, avoiding market chaos or supply and demand mismatch caused by unstable price signals; the control and operation mechanism can effectively reduce the contradiction between market prices and the actual operation of the power system, and improve the forecast accuracy of the power market and the stability of price signals; this mechanism helps to achieve the dual goals of the power market and the power grid: while ensuring the security of power supply, it reduces price fluctuations and improves the efficiency and transparency of market operation; the control and operation index can be used to quantify the dispatch effect, provide feedback to dispatchers, help adjust strategies, and further optimize the operation of the power system.

[0157] Step 134 introduces a data set of control constraint indicators, so that the power system can dynamically adjust the dispatching rules and operation constraints according to the risk assessment results to ensure that the power grid can still operate smoothly under unstable conditions; Step 135 constrains the price signals in the power market by designing a control operation mechanism, combining the power dispatch imbalance and load gap risk constraints, thereby achieving stable dispatch of the power system and avoiding market risks caused by excessive price fluctuations.

[0158] In a preferred embodiment of the present invention, the control operation mechanism in the above step 13 constrains the price signal of the data set through the control constraint condition indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index, including:

[0159] Step 136: the control operation mechanism is based on the power imbalance scheduling constraint condition and load gap risk constraints , to eliminate the risk of price risk conflict; where, Indicates the minimum power indicator data; Indicates the maximum power index data; represents the set of generators participating in the gap constraint;

[0160] Step 137, based on the power imbalance scheduling constraint and the load gap risk constraint, by: ; To obtain the control operation index; where, represents the control operation index; k represents the control response coefficient;

[0161] Step 138: When the control operation index is within a preset range, the control operation mechanism dynamically eliminates the price conflict risk.

[0162] In the embodiment of the present invention, step 136 ensures the balance between supply and demand by scheduling the power output of the generator set based on the "power imbalance scheduling constraint condition". The goal of power imbalance scheduling is to minimize the power difference of the system and reduce the uneconomic operation state by optimizing the power output of the power generation unit. Considering the gap risk between the power generation capacity and the load demand, the system performs constraint management on the generator sets involved in the regulation. The load gap risk reflects the potential risk of insufficient or excessive power supply, and these risks need to be dynamically balanced during regulation.

[0163] Reflects the minimum acceptable power output of the system under the control constraints; Maximum power index: reflects the maximum allowable power output of the system under the load safety constraints; defines a group of generating units that meet the constraints through scheduling and control responses, thereby forming an effective dynamic balance between supply and demand; in the process of eliminating power imbalance, the system realizes the optimal scheduling of power generation units through power index constraints and gap risk constraints; reduces the contradiction between price risk and imbalance between power supply and demand, and ensures system stability and economy.

[0164] Step 137 calculates the control operation index based on the "power imbalance scheduling constraint" and the "load gap risk constraint"; the control operation index is used to measure the key indicator of the degree of deviation between the current control state of the system and the target;

[0165] The dispatch operation index is dynamically calculated based on the real-time power imbalance and load gap risks. The response coefficient can be weighted according to the response characteristics of different units to more accurately reflect the actual regulation capability of the power generation unit. By calculating the regulation operation index, the system can intuitively measure the rationality of the current regulation state. A quantitative standard is provided so that the system can optimize the output of the generator set based on the index value during regulation, thereby improving the overall dispatch efficiency.

[0166] In step 138, the power output of the generator set is dynamically adjusted according to the changes in the control operation index to ensure the elimination of price conflict risks; the dynamic mechanism will adjust the response coefficient k and power index data in real time to achieve further balance between supply and demand; price conflict risks generally arise from market supply and demand imbalances, which may lead to sharp fluctuations in electricity market prices; the dynamic elimination mechanism stabilizes electricity supply and market prices by optimizing scheduling and risk control; through dynamic feedback of the control operation index, the system can effectively reduce the conflict risk between power scheduling and market prices; ensure the smooth operation of electricity market prices, prevent abnormal price fluctuations caused by supply and demand imbalances; and improve the reliability and economy of power grid operation.

[0167] A closed-loop control mechanism is formed between steps 136, 137, and 138; step 136 performs power scheduling through constraints, defining the boundaries and constraint sets of system control; step 137 dynamically calculates the control operation index, quantifies the degree of the control state and the gap between supply and demand; step 138 dynamically adjusts the output of the generator set according to the range of the control operation index, and ultimately eliminates the risk of price conflict.

[0168] This regulatory mechanism improves the supply and demand balance efficiency of the power system; eliminates the risk of price conflicts in the power market; and enhances the stability and economy of power grid operation.

[0169] In a preferred embodiment of the present invention, the above step 14 includes:

[0170] Step 141, based on the price signal data after eliminating conflicts, a price signal evaluation model is constructed by training; the price signal evaluation model is constructed according to the objective function Combined with the regulatory constraint indicator data set to evaluate the price signal after eliminating the conflict; where C i represents the cost function of the i-th generator set, Pl represents the power data after the dispatching operation mechanism; λ j represents the jth price signal after the dispatch operation mechanism, P m represents the mth grid reserve capacity that provides the dispatching operation mechanism;

[0171] Step 142, the price signal after the conflict is eliminated is newly entered into the price signal evaluation model, and the price signal evaluation model outputs the identification result of the newly entered price signal after the conflict is eliminated to obtain an accurate price signal, otherwise it returns to the step of eliminating the price signal conflict and re-operates; thereby, the balance of power supply and the stability of frequency regulation services are coordinated.

[0172] In the embodiment of the present invention, a price signal evaluation model is constructed in step 141; model training is performed based on price signal data after conflict elimination; the key task of this step is to construct a price signal evaluation model using price signal data after price conflicts are eliminated through the regulation mechanism. The model helps optimize the operation of the power market and effectively eliminates price fluctuations in the market by evaluating price signals;

[0173] The price signal evaluation model is constructed by combining the objective function with the control constraint indicator data set: the grid backup capacity that provides the dispatch operation mechanism represents the backup generation capacity required by the grid to ensure system stability; the goal of the evaluation model is to evaluate the effectiveness of the price signal after eliminating conflicts based on these data sets, ensuring that the price signal can reflect the balance between market demand and supply, while avoiding market instability caused by price fluctuations;

[0174] This data is used as input to train a model that can predict and evaluate price signals through machine learning or optimization algorithms (such as regression analysis, neural networks, etc.). The goal of this model is to make the output price signal more consistent with the actual market situation and match it with factors such as power generation costs and power demand;

[0175] The trained model can effectively capture the changing patterns of price signals in the electricity market and provide timely and effective feedback in actual scheduling.

[0176] After the training of the price signal evaluation model is completed in step 141 by inputting the new price signal after eliminating the conflict into step 142, step 142 inputs the new price signal data after eliminating the conflict into the established model to further verify whether the price signal meets the operation requirements of the system; the model outputs the price signal recognition result; the model outputs the recognition result based on the input new price signal, indicating whether these price signals can coordinate the balance of power supply and the stability of frequency regulation services. If the price signal meets expectations, the system considers that the price signal has been correctly identified; otherwise, it will execute a return operation and re-enter the step of eliminating price signal conflicts; that is, whether the price signal is consistent with the power dispatch target; that is, whether the price signal can effectively reflect the dynamic balance of market demand and supply; that is, whether the price signal can support the balance of power supply and demand;

[0177] Eliminate price conflicts again. If the model output does not meet the preset conditions or price signals still conflict, the system will return to step 13 and its sub-steps to readjust and eliminate price conflicts until a valid price signal is obtained.

[0178] By evaluating and identifying price signals after conflicts are resolved, the system can ensure that market prices reflect actual changes in electricity supply and demand, thereby promoting the rational allocation of market resources. Optimized price signals can effectively avoid excessive price fluctuations, reduce the frequency of price conflicts, and improve the stability of the power market; through accurate price signal feedback, generators can adjust power output in a timely manner according to market prices to ensure that the power system is always in the optimal dispatch state. This not only helps the operating efficiency of the power system, but also reduces energy waste during the dispatch process.

[0179] The price signal evaluation model can ensure the balance of supply and demand in the power system. After eliminating price conflicts, the power grid can meet real-time load demand through optimized scheduling. In addition, accurate price signals contribute to the stable operation of frequency regulation services, avoiding excessive frequency fluctuations or system imbalances; through rapid feedback and adjustment of price signals, the system can respond to market uncertainties such as sudden load changes and fluctuations in power generation capacity in a timely manner, and improve the market's response speed to changes.

[0180] Through accurate price signal evaluation, power market participants (such as power generation companies, power consumers, etc.) can better understand market dynamics and make more scientific decisions. This helps to improve market transparency and efficiency; through effective price signal feedback and evaluation, the system can maintain stable supply under different operating conditions, avoid unstable or insufficient power supply caused by price fluctuations, and reduce power supply risks; by building and applying this price signal evaluation model, the power system can further develop into a smart grid, optimize resource allocation in a more dynamic and intelligent environment, and achieve more flexible power dispatch and management.

[0181] Specifically, in another preferred embodiment of the present invention, the price signal evaluation model is based on the objective function and the regulation constraint indicator data set by: ; To evaluate the fluctuation data of power market price signals; where Pr represents the fluctuation evaluation data of power market price signals; P(t) represents the price signal at a certain moment; P represents the average value of the price signal, and T represents the length of the time period;

[0182] pass: ; To evaluate whether the price signal is helpful to achieve the balance of power supply; where Sr represents the evaluation data of the price signal of power supply balance; P sd represents the target power determined by the market clearing outcome;

[0183] pass: ; To evaluate the responsiveness of the operation and dispatch frequency regulation service and the joint clearing of electric energy; where t represents the time window, t 1 and t 2 They respectively represent the monitoring time range; dt represents the deviation of the system frequency.

[0184] like Figure 2 As shown, a frequency regulation and electric energy joint clearing device in the power market includes:

[0185] Data collection module: It is used to collect various frequency regulation service data and electric energy joint clearing data to obtain a data set;

[0186] Data analysis module: used to train the data set to construct a prediction model to obtain stable price signal data; input at least one frequency modulation and electric energy joint clearing data item in the newly acquired data set into the prediction model to obtain the price signal prediction result of the newly acquired data set;

[0187] The dispatching operation module is used to obtain a data set of potential risk indicators for power operation when a conflict occurs in the price signal; design a control operation mechanism based on the data set of potential risk indicators for power operation, wherein the control operation mechanism constrains the data set price signal through the control constraint indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index;

[0188] Evaluation module: It is used to evaluate the price signal after eliminating signal conflicts to coordinate the balance of power supply and the stability of frequency regulation services.

[0189] like Figure 3 As shown, a device for frequency regulation and electric energy joint clearing in the power market includes:

[0190] A processor, and a memory connected to the processor;

[0191] The memory is used to store a computer program, and the computer program is used to execute a frequency regulation and electric energy joint clearing method in an electric power market.

[0192] When the functions of the above modules are implemented in the form of software functional units and used as independent products, they can be stored in a storage device. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or optical disk, etc., various media that can store program codes.

[0193] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general intelligent device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or system. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

Claims

1. A frequency regulation and electric energy joint clearing method in the power market, characterized in that: include: Collect various frequency regulation service data and power joint clearing data to obtain data sets; The data set is trained to construct a prediction model to obtain stable price signal data; at least one frequency modulation and electric energy joint clearing data item in the newly acquired data set is input into the prediction model to obtain a price signal prediction result of the newly acquired data set; wherein, the price signal fluctuation amplitude is obtained according to the stable price signal data and the price signal prediction result; Based on the newly acquired data set, collecting power grid frequency data of corresponding time nodes; By using the price signal fluctuation amplitude and the power grid frequency data, it is determined whether a price signal conflict occurs between the stable price signal data and the price signal prediction result; When a price signal conflict occurs, a data set of potential risk indicators for power operation is obtained; a control operation mechanism is designed based on the data set of potential risk indicators for power operation; the control operation mechanism constrains the data set price signal through the control constraint indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index; The price signal after eliminating signal conflicts is evaluated to coordinate the balance of power supply and the stability of frequency regulation services.

2. The frequency regulation and electric energy joint clearing method in the power market according to claim 1 is characterized in that: The prediction model comprises: Preprocessing the collected multiple frequency regulation service data and electric energy joint clearing data to obtain a preprocessed data set; encoding the preprocessed data set into sequence data to obtain a training set; and constructing the prediction model through training with the training set; At least one data item of the preprocessed data set is input into the prediction model; the prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the intermediate representation data of multiple hidden layers are transmitted to the output layer, and the output layer outputs the price signal recognition result representing the frequency modulation service data and the electricity joint clearing data.

3. The frequency regulation and electric energy joint clearing method in the power market according to claim 2 is characterized in that: Determining whether the stable price signal data conflicts with the price signal prediction result by using the price signal fluctuation amplitude and the power grid frequency data includes: Setting a price signal fluctuation range based on the data set; obtaining a price signal fluctuation amplitude through the price signal prediction result and the stable price signal data; Compare the price signal fluctuation amplitude with the price signal fluctuation range to determine whether the fluctuation amplitude is within the price signal fluctuation range; when the fluctuation amplitude exceeds or is lower than the price signal fluctuation range, it can be obtained that there is a signal conflict risk between the stable price signal data and the price signal prediction result; Preset a frequency standard range based on the risk of signal conflict; compare the power grid frequency with the preset frequency standard range; when the power grid frequency deviates from the preset frequency standard range, determine that the stable price signal data and the price signal prediction result have a signal conflict risk; Based on the comparison result and the judgment result, it is determined that the price signal data conflicts with the stable price signal data.

4. The frequency regulation and electric energy joint clearing method in the power market according to claim 3 is characterized in that: Setting a price signal fluctuation range based on the data set; The price signal fluctuation amplitude is obtained by using the price signal prediction result and the stable price signal data, including: According to the price signal prediction result and the stable price signal data, by: , to obtain the mean fluctuation of price signals; represents the mean fluctuation of the price signal in the ith period; Indicates the number of price signal fluctuations; According to the price signal fluctuation mean, by: , to obtain the price signal slope data; where, Represents the price signal slope data; Price signal data representing the price signal prediction moment; represents the price signal data at the time when the price signal is stable, and m represents the m moments before the price signal prediction moment; Based on the price signal slope data, by: , to obtain the price signal fluctuation amplitude; where, Indicates the fluctuation amplitude of price signals; m represents the price signal fluctuation frequency; Set the price signal fluctuation range ; In the formula, Indicates the upper limit of the price signal fluctuation range; Indicates the lower limit of the price signal fluctuation range; according to the price signal fluctuation amplitude, set an array Δt for storing the fluctuation amplitude; when hour, ;when hour, ;when hour, ; It is thus determined that there is a risk of signal conflict between the stable price signal data and the price signal prediction result.

5. A frequency regulation and electric energy joint clearing method in a power market according to claim 4, characterized in that: When price signals conflict, obtain a data set of potential risk indicators for power operation, including: Based on the data set, by: ; To obtain the power dispatch imbalance risk index data; where R i Represents the power dispatch imbalance risk indicator data; P i represents the actual output power of the ith generator set during power operation, P d represents the expected power determined according to the market clearing results; n represents the number of generating units; Based on the power dispatch imbalance risk indicator data, by: ; To obtain the load gap risk index data; where R y represents the load gap risk indicator data; Δf(t) represents the frequency deviation in the time period [t1, t2]; Based on the load gap risk index data obtained and combined with the power dispatch imbalance risk index data, a data set of potential risk indicators for power operation is formed. The larger the data set of potential risk indicators for power operation is, the greater the risk of price signal conflict is.

6. A frequency regulation and electric energy joint clearing method in the power market according to claim 5, characterized in that: According to the data set of potential risk indicators of power operation, a control and operation mechanism is designed, including: According to the electric power operation potential risk indicator data set, a control constraint indicator data set is obtained; the control constraint indicator data set includes power imbalance scheduling constraint conditions and load gap risk constraint conditions; The control operation mechanism is designed according to the power grid constraint condition indicators; the control operation mechanism constrains the price signal of the data set through the control constraint condition indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index.

7. A frequency regulation and electric energy joint clearing method in the power market according to claim 6, characterized in that: The control operation mechanism constrains the data set price signal through the control constraint condition indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index, including: The control operation mechanism is based on the power imbalance scheduling constraint and load gap risk constraints , to eliminate the risk of price risk conflict; where, Indicates the minimum power indicator data; Indicates the maximum power index data; represents the set of generators participating in the gap constraint; Based on the power imbalance dispatch constraint and the load gap risk constraint, by: ; To obtain the control operation index; where, represents the control operation index; k represents the control response coefficient; When the regulation operation index is within a preset range, the regulation operation mechanism dynamically eliminates the price conflict risk.

8. A frequency regulation and electric energy joint clearing method in the power market according to claim 7, characterized in that: The price signals after eliminating signal conflicts are evaluated to coordinate the balance of power supply and the stability of frequency regulation services, including: Based on the price signal data after eliminating conflicts, a price signal evaluation model is constructed by training; the price signal evaluation model is constructed according to the objective function Combined with the regulatory constraint indicator data set to evaluate the price signal after eliminating the conflict; where C i represents the cost function of the i-th generator set, Pl represents the power data after the dispatching operation mechanism; λ j represents the jth price signal after the dispatch operation mechanism, P m represents the mth grid reserve capacity that provides the dispatching operation mechanism; The price signal after conflict elimination is newly entered into the price signal evaluation model, and the price signal evaluation model outputs the identification result of the newly entered price signal after conflict elimination to obtain an accurate price signal, otherwise it returns to the step of eliminating price signal conflict and re-operates; thereby coordinating the balance of power supply and the stability of frequency regulation services.

9. A frequency regulation and electric energy joint clearing device in the power market, characterized in that: include: Data collection module: It is used to collect various frequency regulation service data and electric energy joint clearing data to obtain a data set; Data analysis module: used to train the data set to construct a prediction model to obtain stable price signal data; input at least one frequency modulation and electric energy joint clearing data item in the newly acquired data set into the prediction model to obtain the price signal prediction result of the newly acquired data set; The dispatching operation module is used to obtain a data set of potential risk indicators for power operation when a conflict occurs in the price signal; design a control operation mechanism based on the data set of potential risk indicators for power operation, wherein the control operation mechanism constrains the data set price signal through the control constraint indicator data set, and eliminates the signal conflict between the stable price signal data and the price signal prediction result through the control operation index; Evaluation module: It is used to evaluate the price signal after eliminating signal conflicts to coordinate the balance of power supply and the stability of frequency regulation services.

10. A device for frequency regulation and electric energy joint clearing in the power market, characterized in that: include: A processor, and a memory connected to the processor; The memory is used to store a computer program, and the computer program is used to execute the frequency regulation and electric energy joint clearing method in the power market according to any one of claims 1 to 8; The processor is used to call and execute the computer program in the memory.

Images