Electricity market energy storage data interaction feature analysis method and system

Abstract

The invention belongs to the technical field of electric power data analysis, and discloses an electric power market energy storage data interaction feature analysis method and system, and the method comprises the steps: collecting the original data of an electric power market, energy storage equipment and environmental conditions, carrying out the data preprocessing, recognizing and cleaning the abnormal data in the original data, and generating a data set in a unified format; extracting related features of each type of original data in the data set, based on variance threshold analysis, removing invalid features in the related features, and retaining valid features to form a feature set; based on a time sequence prediction algorithm, a power market prediction model is constructed, future demand data and power price fluctuation of the power market are predicted, and market risks existing in the energy storage system are evaluated. The scheduling precision and efficiency of the energy storage system can be effectively improved by combining data acquisition, preprocessing, feature extraction, market prediction, decision optimization and a dynamic feedback mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of power data analysis, and in particular to a method and system for analyzing interactive characteristics of energy storage data in a power market. Background Art

[0002] With the continuous growth of global energy demand and the focus on sustainable development, the operation of the power market and the dispatch of energy storage systems have become particularly important. Especially in the power market, energy supply and demand fluctuate greatly and prices are unstable, which makes the dispatch of the power system face great challenges. Energy storage equipment, as an important response measure, can store electricity when the power market price is low and release electricity when the power demand peaks, thereby balancing the supply and demand relationship in the power market and reducing the risks brought by fluctuations. However, how to efficiently and accurately dispatch energy storage equipment to maximize its benefits and reduce energy costs is still a problem that needs to be solved.

[0003] At present, although there are many dispatching methods based on data analysis in the electricity market, the data formats between different data sources vary greatly, resulting in inconsistent or incomplete information, which affects subsequent analysis and decision-making. Many forecasting models cannot effectively capture the complexity of price fluctuations and demand changes in the electricity market, resulting in large forecasting errors, which affects the accuracy of energy storage dispatch. Most energy storage dispatching systems rely on static rules or preset dispatching models and cannot be dynamically adjusted according to real-time data, resulting in insufficient utilization of energy storage resources.

[0004] Therefore, how to provide a method and system for analyzing the interactive characteristics of energy storage data in the power market is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present invention provide a method and system for analyzing interactive characteristics of energy storage data in a power market to solve the above-mentioned technical problems existing in the prior art.

[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be a general review, nor is it intended to identify key / important components or to delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a method for analyzing interactive characteristics of energy storage data in a power market is provided.

[0008] In one embodiment, the method for analyzing interactive characteristics of energy storage data in the power market includes:

[0009] Collecting raw data on the power market, energy storage equipment and environmental conditions, identifying and cleaning abnormal data in the raw data through data preprocessing, and generating a data set in a unified format;

[0010] Extract relevant features of each type of original data in the data set, remove invalid features from the relevant features based on variance threshold analysis, and retain valid features to form a feature set;

[0011] Based on the time series prediction algorithm, we build a power market prediction model to predict future power market demand data and power price fluctuations, and evaluate the market risks in the energy storage system.

[0012] Establish optimization objectives and constraints for the electricity market, and solve the optimal scheduling decision for energy storage equipment based on linear programming optimization algorithms;

[0013] Based on real-time data and changes in the electricity market, online learning algorithms are used to optimize the dispatching decisions of energy storage equipment in real time, and the dispatching decisions are continuously adjusted according to the feedback mechanism.

[0014] In one embodiment, the collecting of raw data of the power market, energy storage equipment and environmental conditions, identifying and cleaning abnormal data in the raw data through data preprocessing, and generating a data set in a unified format includes:

[0015] Collecting raw data of the power market, energy storage equipment and environmental conditions in real time, and the raw data includes power market data, energy storage equipment data and environmental data;

[0016] Using linear interpolation to process missing values ​​in the original data, remove redundant data, set an abnormal threshold for the original data, and identify and clean up abnormal data that does not meet the abnormal threshold;

[0017] The raw data are converted into standardized data with a mean of 0 and a standard deviation of 1, and the raw data from different sources are timestamp aligned and fused to form a data set in a unified format.

[0018] In one embodiment, extracting relevant features of each type of original data in the data set, eliminating invalid features from the relevant features based on variance threshold analysis, and retaining valid features to form a feature set includes:

[0019] Extracting relevant features of the original data, wherein the relevant features include time features, statistical features, historical data features and differential features;

[0020] Obtaining electricity price and demand data of the current electricity market, performing Fourier transform on the electricity price and demand data, converting the time domain signal into a frequency domain signal using the Fourier transform formula, extracting periodic components in different frequency domains, and analyzing the frequency characteristics of the periodic components;

[0021] The variance of each of the related features is calculated and compared with a preset variance threshold. If the variance of the related feature is less than or equal to the preset variance threshold, it is determined to be an invalid feature and is eliminated. If the variance of the related feature is greater than the preset variance threshold, it is determined to be a valid feature, and all valid features are integrated to form a feature set.

[0022] In one embodiment, the construction of a power market forecasting model based on a time series forecasting algorithm, forecasting future power market demand and power price fluctuations, and evaluating market risks in the energy storage system include:

[0023] Obtain the electricity price and demand data of the current electricity market, determine the order of the autoregressive part and the moving average part based on the autoregressive integral moving average model time prediction algorithm, and build an electricity market prediction model;

[0024] The preprocessed data set is divided into a training set and a test set, the training set and the test set are used to train and optimize the electricity market forecasting model respectively, and the trained electricity market forecasting model is used to forecast future electricity market demand to obtain a forecast result.

[0025] In one embodiment, the expression of the power market forecasting model is:

[0026]

[0027] Where Y t is the electricity market price and demand data at the current moment; μ is a constant term, is the coefficient of the autoregressive (AR) part; θ j is the coefficient of the moving average (MA) part; ∈ t is the error term; Y t-i is the observed value at time ti; p is the order of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t-j is the error term at time tj; q is the order of the sliding average part.

[0028] In one embodiment, the establishment of optimization objectives and constraints of the power market and the generation of optimal scheduling decisions for energy storage devices based on acquired real-time data and prediction results include:

[0029] Obtain the electricity price in the electricity market and the power, price and quantity of electricity required to be purchased, and establish the objective function of the electricity market with the goal of minimizing costs;

[0030] Set the constraints of the electricity market, use the linear programming optimization algorithm to calculate the energy storage equipment scheduling strategy, and output the optimal scheduling strategy for the energy storage equipment.

[0031] In one embodiment, the objective function of the electricity market is:

[0032]

[0033] In the formula, C t is the electricity price; t represents the time index; P t is the power required to be purchased from the grid at time t; t is the electricity price of the energy storage device at time t; E t It is the amount of electricity discharged by the energy storage device at time t; T represents the total time period length.

[0034] In one embodiment, the expression for calculating the energy storage device scheduling strategy using the linear programming optimization algorithm is:

[0035] minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0

[0036] In the formula, P is one of the decision variables; E is another decision variable; f(P,E) is the objective function; g(P,E) is the function representing the inequality constraint; h(P,E) is the function representing the inequality constraint.

[0037] According to a second aspect of an embodiment of the present invention, a system for analyzing interactive characteristics of energy storage data in a power market is provided.

[0038] In one embodiment, the power market energy storage data interactive feature analysis system includes:

[0039] The data acquisition module is used to collect raw data of the power market, energy storage equipment and environmental conditions, identify and clean up abnormal data in the raw data through data preprocessing, and generate a data set in a unified format;

[0040] An extraction modeling module is used to extract relevant features of various types of original data in the data set, and based on variance threshold analysis, remove invalid features from the relevant features and retain valid features to form a feature set;

[0041] The forecasting analysis module is used to build a power market forecasting model based on the time series forecasting algorithm, predict future demand data and power price fluctuations in the power market, and evaluate the market risks in the energy storage system;

[0042] The decision optimization module is used to establish the optimization objectives and constraints of the power market and solve the optimal scheduling decision of energy storage equipment based on the linear programming optimization algorithm;

[0043] The feedback regulation module is used to optimize the dispatching decisions of energy storage equipment in real time based on real-time data and changes in the electricity market, using online learning algorithms, and continuously adjusting the dispatching decisions according to the feedback mechanism.

[0044] In one embodiment, the data acquisition module includes: a data acquisition module, a data preprocessing module and a standardization merging module, wherein:

[0045] The data acquisition module is used to collect raw data of the power market, energy storage equipment and environmental conditions in real time, and the raw data includes power market data, energy storage equipment data and environmental data;

[0046] The data preprocessing module is used to process missing values ​​in the original data using a linear interpolation method, remove redundant data, set an abnormal threshold for the original data, and identify and clean up abnormal data that does not meet the abnormal threshold;

[0047] The standardization merging module is used to convert the original data into standardized data with a mean of 0 and a standard deviation of 1, and to align the timestamps of the original data from different sources to form a data set in a unified format.

[0048] In one embodiment, the extraction modeling module includes: a feature extraction module, a Fourier transform module and a feature selection module, wherein:

[0049] The feature extraction module is used to extract relevant features of the original data, and the relevant features include time features, statistical features, historical data features and differential features;

[0050] The Fourier transform module is used to obtain the power price and demand data of the current power market, perform Fourier transform on the power price and demand data, convert the time domain signal into the frequency domain signal using the Fourier transform formula, extract the periodic components in different frequency domains, and analyze the frequency characteristics of the periodic components;

[0051] The feature selection module is used to calculate the variance of each of the related features and compare it with a preset variance threshold. If the variance of the related feature is less than or equal to the preset variance threshold, it is determined to be an invalid feature and is eliminated. If the variance of the related feature is greater than the preset variance threshold, it is determined to be a valid feature, and all valid features are integrated to form a feature set.

[0052] In one embodiment, the prediction analysis module includes: a model building module and a training prediction module, wherein:

[0053] The model building module is used to obtain the power price and demand data of the power market at the current moment, determine the order of the autoregressive part and the sliding average part based on the autoregressive integral sliding average model time prediction algorithm, and build a power market prediction model;

[0054] The training prediction module is used to divide the preprocessed data set into a training set and a test set, respectively use the training set and the test set to train and optimize the electricity market prediction model, and use the trained electricity market prediction model to predict future electricity market demand to obtain a prediction result.

[0055] In one embodiment, the expression of the power market forecasting model is:

[0056]

[0057] Where Y t is the electricity market price and demand data at the current moment; μ is a constant term, is the coefficient of the autoregressive (AR) part; θ j is the coefficient of the moving average (MA) part; ∈ t is the error term; Y t-i is the observed value at time ti; p is the order of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t-j is the error term at time tj; q is the order of the sliding average part.

[0058] In one embodiment, the decision optimization module includes: a target setting module and a strategy output module, wherein:

[0059] The target setting module is used to obtain the electricity price in the electricity market and the power, electricity price and electricity quantity required to be purchased, and to establish the objective function of the electricity market with the goal of minimizing the cost;

[0060] The strategy output module is used to set the constraints of the power market, calculate the energy storage device scheduling strategy using a linear programming optimization algorithm, and output the optimal scheduling strategy for the energy storage device.

[0061] In one embodiment, the objective function of the electricity market is:

[0062]

[0063] In the formula, C t is the electricity price; t represents the time index; P t is the power required to be purchased from the grid at time t; t is the electricity price of the energy storage device at time t; Et It is the amount of electricity discharged by the energy storage device at time t; T represents the total time period length.

[0064] In one embodiment, the expression for calculating the energy storage device scheduling strategy using the linear programming optimization algorithm is:

[0065] minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0

[0066] In the formula, P is one of the decision variables; E is another decision variable; f(P,E) is the objective function; g(P,E) is the function representing the inequality constraint; h(P,E) is the function representing the inequality constraint.

[0067] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0068] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0069] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0070] In one embodiment, the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0071] The technical solution provided by the embodiment of the present invention may include the following beneficial effects: The present invention combines data collection, preprocessing, feature extraction, market forecasting, optimization decision-making and dynamic feedback mechanism to effectively improve the scheduling accuracy and efficiency of the energy storage system, which is reflected in the following aspects:

[0072] 1. By integrating real-time data from the power market, energy storage equipment and the environment, and preprocessing and cleaning, data redundancy and missing data can be effectively eliminated, ensuring the high quality and consistency of data, so as to provide accurate and reliable input for subsequent modeling and analysis.

[0073] 2. The cyclical characteristics of electricity market prices and demand are extracted through Fourier transform, and time series features, statistical features and historical data features are extracted from the preprocessed data to provide sufficient input information for electricity market forecasting and energy storage system scheduling. This feature extraction method can help the system extract key features with high predictive value from complex electricity market data and improve the accuracy of the model.

[0074] 3. Based on time series forecasting algorithms such as the ARIMA autoregressive integrated moving average model, the demand and price fluctuations in the electricity market are predicted, and market risks are assessed in combination with risk analysis methods. Through accurate market forecasts, the system can provide forward-looking guidance for the scheduling of energy storage equipment and reduce the risks caused by market fluctuations.

[0075] 4. Through the linear programming optimization algorithm, the scheduling strategy of the energy storage equipment is dynamically adjusted according to the real-time data and prediction results to ensure that the charging and discharging operations of the energy storage equipment in different time periods are the most efficient and maximize the benefits or minimize the costs. The system can also adjust the optimization strategy according to real-time feedback to further improve the dynamic adaptability of the system.

[0076] 5. Based on real-time data and market changes, an online learning algorithm is used to optimize the dispatch strategy of the energy storage system. This allows the system to automatically adjust the operation strategy of the energy storage equipment when the power market and environmental conditions change, ensuring the flexibility and responsiveness of the system.

[0077] 6. Through accurate predictions based on market price and demand fluctuations, combined with real-time data to adjust scheduling strategies, energy storage equipment can be more efficiently charged when prices are low and discharged when prices are high, maximizing the economic and market benefits of energy storage equipment.

[0078] 7. Optimized scheduling strategies can reduce unnecessary energy waste and excessive consumption, and reduce the operating costs of energy storage systems. At the same time, accurate market forecasts and risk analysis can effectively avoid the risks brought about by market fluctuations and help decision makers make more favorable decisions in an uncertain market environment.

[0079] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0081] Figure 1 is a flow chart of a method for analyzing interactive characteristics of energy storage data in a power market according to an exemplary embodiment;

[0082] Figure 2 It is a structural schematic diagram of a system for analyzing interactive characteristics of energy storage data in a power market according to an exemplary embodiment;

[0083] Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0084] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0085] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0086] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0087] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0088] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0089] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0090] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0091] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0092] Figure 1 An embodiment of a method for analyzing interactive characteristics of energy storage data in a power market according to the present invention is shown.

[0093] In this optional embodiment, the method for analyzing interactive characteristics of energy storage data in the power market includes:

[0094] Step S101, collecting raw data of the power market, energy storage equipment and environmental conditions, identifying and cleaning abnormal data in the raw data through data preprocessing, and generating a data set in a unified format;

[0095] Step S103, extracting relevant features of each type of original data in the data set, removing invalid features from the relevant features based on variance threshold analysis, and retaining valid features to form a feature set;

[0096] Step S105: constructing a power market forecasting model based on a time series forecasting algorithm, forecasting future power market demand data and power price fluctuations, and evaluating market risks in the energy storage system;

[0097] Step S107: Establish optimization objectives and constraints for the electricity market, and solve the optimal scheduling decision for energy storage equipment based on a linear programming optimization algorithm;

[0098] Step S109: Based on real-time data and changes in the electricity market, an online learning algorithm is used to optimize the dispatching decision of the energy storage equipment in real time, and the dispatching decision is continuously adjusted according to the feedback mechanism.

[0099] In this optional embodiment, when collecting the original data of the electricity market, energy storage equipment and environmental conditions, identifying and cleaning the abnormal data in the original data through data preprocessing to generate a data set in a unified format, the original data of the electricity market, energy storage equipment and environmental conditions can be collected in real time, and the original data includes electricity market data, energy storage equipment data and environmental data; linear interpolation is used to process missing values ​​in the original data, redundant data is removed, and an abnormal threshold of the original data is set to identify and clean abnormal data that does not meet the abnormal threshold; the original data is converted into standardized data with a mean of 0 and a standard deviation of 1, and the original data from different sources are timestamp aligned to merge into a data set in a unified format.

[0100] In this optional embodiment, when extracting relevant features of each type of original data in the data set, based on variance threshold analysis, eliminating invalid features in the relevant features, and retaining valid features to form a feature set, the relevant features of the original data can be extracted, and the relevant features include time features, statistical features, historical data features and differential features; obtaining the electricity price and demand data of the current electricity market, performing Fourier transform on the electricity price and demand data, converting the time domain signal into a frequency domain signal using the Fourier transform formula, extracting periodic components in different frequency domains, and analyzing the frequency characteristics of the periodic components; calculating the variance of each of the relevant features, and comparing it with a preset variance threshold. If the variance of the relevant feature is less than or equal to the preset variance threshold, it is determined to be an invalid feature and is eliminated. If the variance of the relevant feature is greater than the preset variance threshold, it is determined to be a valid feature, and all valid features are integrated to form a feature set.

[0101] In this optional embodiment, when constructing an electricity market forecasting model based on the time series forecasting algorithm, predicting future electricity market demand and electricity price fluctuations, and evaluating market risks in the energy storage system, the electricity price and demand data of the current electricity market can be obtained, and based on the autoregressive integral sliding average model time forecasting algorithm, the orders of the autoregressive part and the sliding average part are determined to construct an electricity market forecasting model; the preprocessed data set is divided into a training set and a test set, and the training set and the test set are used to train and optimize the electricity market forecasting model respectively, and the trained electricity market forecasting model is used to predict future electricity market demand to obtain a forecast result.

[0102] In this optional embodiment, the expression of the power market forecasting model is:

[0103]

[0104] Where Y tis the electricity market price and demand data at the current moment; μ is a constant term, is the coefficient of the autoregressive (AR) part; θ j is the coefficient of the moving average (MA) part; ∈ t is the error term; Y t-i is the observed value at time ti; p is the order of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t-j is the error term at time tj; q is the order of the sliding average part.

[0105] In this optional embodiment, when establishing the optimization objectives and constraints of the electricity market and generating the optimal scheduling decision for the energy storage device based on the acquired real-time data and prediction results, the electricity price in the electricity market and the required electric power, electricity price and electricity volume can be obtained, and the objective function of the electricity market can be established with the goal of minimizing costs; the constraints of the electricity market are set, the scheduling strategy of the energy storage device is calculated using a linear programming optimization algorithm, and the optimal scheduling strategy of the energy storage device is output.

[0106] In this optional embodiment, the objective function of the electricity market is:

[0107]

[0108] In the formula, C t is the electricity price; t represents the time index; P t is the power required to be purchased from the grid at time t; t is the electricity price of the energy storage device at time t; E t It is the amount of electricity discharged by the energy storage device at time t; T represents the total time period length.

[0109] In this optional embodiment, the expression for calculating the energy storage device scheduling strategy using the linear programming optimization algorithm is:

[0110] minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0

[0111] In the formula, P is one of the decision variables; E is another decision variable; f(P,E) is the objective function; g(P,E) is the function representing the inequality constraint; h(P,E) is the function representing the inequality constraint.

[0112] Figure 2 An embodiment of a system for analyzing interactive characteristics of energy storage data in a power market according to the present invention is shown.

[0113] In this optional embodiment, the power market energy storage data interactive feature analysis system includes:

[0114] The data acquisition module 201 is used to collect raw data of the power market, energy storage equipment and environmental conditions, identify and clean up abnormal data in the raw data through data preprocessing, and generate a data set in a unified format.

[0115] The extraction modeling module 203 is used to extract relevant features of each type of original data in the data set, and based on variance threshold analysis, remove invalid features from the relevant features and retain valid features to form a feature set.

[0116] The prediction and analysis module 205 is used to construct a power market prediction model based on a time series prediction algorithm, predict future demand data and power price fluctuations in the power market, and evaluate the market risks existing in the energy storage system.

[0117] The decision optimization module 207 is used to establish the optimization objectives and constraints of the power market and solve the optimal scheduling decision of the energy storage equipment based on the linear programming optimization algorithm.

[0118] The feedback adjustment module 209 is used to optimize the dispatching decision of the energy storage equipment in real time based on the real-time data and the changes in the power market by using an online learning algorithm, and continuously adjust the dispatching decision according to the feedback mechanism.

[0119] In this optional embodiment, the data acquisition module 201 includes: a data acquisition module (not shown in the figure), a data preprocessing module (not shown in the figure) and a standardization merging module (not shown in the figure), wherein the data acquisition module is used to collect raw data of the electricity market, energy storage equipment and environmental conditions in real time, and the raw data includes electricity market data, energy storage equipment data and environmental data; the data preprocessing module is used to process missing values ​​in the raw data using linear interpolation, remove redundant data, and set an abnormal threshold for the raw data, identify and clean up abnormal data that does not meet the abnormal threshold; the standardization merging module is used to convert the raw data into standardized data with a mean of 0 and a standard deviation of 1, and align the timestamps of the raw data from different sources to form a data set in a unified format.

[0120] In this optional embodiment, the extraction modeling module 203 includes: a feature extraction module (not shown in the figure), a Fourier transform module (not shown in the figure) and a feature selection module (not shown in the figure), wherein the feature extraction module is used to extract relevant features of the original data, and the relevant features include time features, statistical features, historical data features and differential features; the Fourier transform module is used to obtain the electricity price and demand data of the current electricity market, perform Fourier transform on the electricity price and demand data, use the Fourier transform formula to convert the time domain signal into a frequency domain signal, extract the periodic components in different frequency domains, and analyze the frequency characteristics of the periodic components; the feature selection module is used to calculate the variance of each of the relevant features, compare it with a preset variance threshold, if the variance of the relevant feature is less than or equal to the preset variance threshold, it is determined to be an invalid feature and is eliminated, if the variance of the relevant feature is greater than the preset variance threshold, it is determined to be a valid feature, and all valid features are integrated to form a feature set.

[0121] In this optional embodiment, the prediction and analysis module 205 includes: a model building module (not shown in the figure) and a training prediction module (not shown in the figure), wherein the model building module is used to obtain the electricity price and demand data of the electricity market at the current moment, determine the order of the autoregressive part and the sliding average part based on the autoregressive integral sliding average model time prediction algorithm, and construct an electricity market prediction model; the training prediction module is used to divide the preprocessed data set into a training set and a test set, and use the training set and the test set to train and optimize the electricity market prediction model respectively, and use the trained electricity market prediction model to predict future electricity market demand to obtain a prediction result.

[0122] In this optional embodiment, the expression of the power market forecasting model is:

[0123]

[0124] Where Y t is the electricity market price and demand data at the current moment; μ is a constant term, is the coefficient of the autoregressive (AR) part; θ j is the coefficient of the moving average (MA) part; ∈ t is the error term; Y t-i is the observed value at time ti; p is the order of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t-j is the error term at time tj; q is the order of the sliding average part.

[0125] In this optional embodiment, the decision optimization module 207 includes: a target setting module (not shown in the figure) and a strategy output module (not shown in the figure), wherein the target setting module is used to obtain the electricity price in the electricity market and the required electric power, electricity price and electricity volume to be purchased, and establish the objective function of the electricity market with the goal of minimizing costs; the strategy output module is used to set the constraints of the electricity market, calculate the energy storage device scheduling strategy using a linear programming optimization algorithm, and output the optimal scheduling strategy for the energy storage device.

[0126] In this optional embodiment, the objective function of the electricity market is:

[0127]

[0128] In the formula, C t is the electricity price; t represents the time index; P t is the power required to be purchased from the grid at time t; t is the electricity price of the energy storage device at time t; E t It is the amount of electricity discharged by the energy storage device at time t; T represents the total time period length.

[0129] In this optional embodiment, the expression for calculating the energy storage device scheduling strategy using the linear programming optimization algorithm is:

[0130] minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0

[0131] In the formula, P is one of the decision variables; E is another decision variable; f(P,E) is the objective function; g(P,E) is the function representing the inequality constraint; h(P,E) is the function representing the inequality constraint.

[0132] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0133] A power market energy storage data interactive feature analysis system includes: a data acquisition module 201, an extraction modeling module 203, a prediction analysis module 205, a decision optimization module 207 and a feedback regulation module 209.

[0134] 1. For the data acquisition module 201, collect various types of power market, energy storage equipment and environmental conditions data, integrate data from different sources, pre-process the collected raw data, and automatically identify and clean up abnormal data based on the anomaly detection algorithm. The composition structure of the data acquisition module 201 and its implementation principle include the following aspects:

[0135] 1.1 Data acquisition module: obtain power market data, energy storage equipment data and environmental data in real time through sensors.

[0136] 1.2 Data preprocessing module: Remove redundant data: Remove duplicate records and use linear interpolation algorithm to process missing values. The linear interpolation algorithm formula is:

[0137]

[0138] In the formula, x(t) is the missing value, t0 and t1 are the previous and next time points, and x(t0) and x(t1) are the known data at the corresponding time points;

[0139] Statistical anomaly detection uses statistical methods to detect data points that do not conform to the expected distribution. If the data point exceeds a predetermined threshold, the data is considered abnormal. The anomaly detection formula is:

[0140]

[0141] Where x is the data point, μ is the mean of the data, σ is the standard deviation of the data, and z is a standardized measure of how far the data point is from the mean;

[0142] 1.3 Standardization and merging module: Standardize the data and transform it into a distribution with a mean of 0 and a standard deviation of 1; align the timestamps of data from different sources and fuse the information from different data sources to generate a set of data sets in a unified format.

[0143] 2. The extraction modeling module 203 is electrically connected to the data acquisition module 201. The extraction modeling module 203 is used to extract features for power storage scheduling and market analysis from the pre-processed data.

[0144] The composition structure and implementation principle of the extraction modeling module 203 include the following aspects:

[0145] 2.1 Feature extraction module: extract features from the preprocessed data, including time features, statistical features, historical data features and differential features.

[0146] 2.2 Fourier transform module: By performing Fourier transform on the electricity price and demand data, the periodic components of different frequencies are extracted. The Fourier transform formula is:

[0147]

[0148] Where FT(f) represents the Fourier transform result at frequency f, x t Represents signal data in the time domain, N is the total length of the signal, f is the frequency, e -2πift / N is a complex exponential term, i is the imaginary unit, 2π is a periodic constant, and ft / N is a proportional factor.

[0149] 2.3 Feature selection module: Calculate the variance of each feature, set a threshold, select features with variance greater than the threshold, remove features with variance close to zero, and form a new feature set with the remaining features with larger variance.

[0150] 3. The prediction and analysis module 205 is electrically connected to the extraction and modeling module 203. The prediction and analysis module 205 is used to predict the power market based on the time series prediction algorithm, including power price fluctuations and market demand, and provide forward-looking guidance for energy storage system scheduling. The composition structure and implementation principle of the prediction and analysis module 205 include the following aspects:

[0151] 3.1 Model building module: The power market forecasting model is constructed based on the autoregressive integrated moving average model time series forecasting algorithm, where the power market forecasting model formula is:

[0152]

[0153] Where Y t is the electricity market price and demand at the current moment, μ is a constant term, is the coefficient of the AR part, θ j is the coefficient of the MA part, ∈ t is the error term, Y t-i is the observed value at time ti, p is the order of the autoregressive part, θ j is the coefficient of the sliding average part, ∈ t-j is the error term at time tj, and q is the order of the sliding average part.

[0154] 3.2 Training prediction module: The preprocessed data is divided into training set and test set, the prediction model is trained and verified using the cross-validation method, and the trained model is used to predict the future demand of the electricity market.

[0155] 4. The decision optimization module 207 is electrically connected to the prediction analysis module 205. The decision optimization module 207 is used to provide a scheduling strategy for energy storage equipment through an optimization algorithm based on real-time data and prediction data. The composition structure and implementation principle of the decision optimization module 207 include the following aspects:

[0156] 4.1 Goal setting module: Establish the objective function based on cost minimization, where the objective function formula is:

[0157]

[0158] In the formula, C t is the electricity price, t represents the time index, P t is the power required to be purchased from the grid at time t, γ tis the electricity price of the energy storage device at time t, E t It is the amount of electricity discharged by the energy storage device at time t, and T represents the total time period length.

[0159] 4.2 Strategy output module: Set constraints to ensure that the scheduling strategy is executed within a feasible range, and use the linear programming optimization algorithm to solve the energy storage scheduling problem; after solving the problem through the optimization algorithm, the system outputs the optimal energy storage equipment scheduling strategy, combines these results with the real-time monitoring system, and adjusts the operating status of the equipment in real time.

[0160] The use of a linear programming optimization algorithm to solve the energy storage scheduling problem specifically includes:

[0161] The optimization formula is:

[0162] minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0

[0163] Where P represents one of the decision variables, E represents another decision variable, f(P,E) is the objective function, g(P,E) is the function representing the inequality constraint, and h(P,E) is the function representing the inequality constraint.

[0164] 5. The feedback adjustment module 209 is electrically connected to the decision optimization module 207. The feedback adjustment module 209 is used to optimize the dispatching strategy of the energy storage system based on real-time data and market changes by using an online learning algorithm.

[0165] In addition, an analysis of the interactive characteristics of energy storage data in the power market can be summarized as follows:

[0166] Step 1: Collect raw data on the power market, energy storage equipment, and environmental conditions through multiple data sources, including price fluctuations in the power market, market demand, the status of energy storage equipment, and environmental conditions data. Clean and standardize the collected raw data, and use anomaly detection algorithms to automatically identify and clean abnormal data to ensure data quality and consistency.

[0167] Step 2: Extract features related to power storage scheduling and market analysis from the preprocessed data, including time series features, power market features, energy storage equipment features, and environmental condition features, and combine interactive features for modeling and analysis.

[0168] Step 3: Predict future demand and price fluctuations in the electricity market based on a time series forecasting algorithm, and use risk assessment methods to assess the market risks that may be faced in the scheduling of energy storage systems;

[0169] Step 4: Use optimization algorithms to provide the best scheduling strategy for energy storage equipment based on real-time data and prediction results.

[0170] Step 5: Based on real-time data and market changes, use online learning algorithms to optimize the energy storage system’s dispatch strategy, and continuously adjust dispatch decisions based on the feedback mechanism.

[0171] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0172] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0174] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0176] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for analyzing interactive characteristics of energy storage data in a power market, characterized in that: include: Collecting raw data on the power market, energy storage equipment and environmental conditions, identifying and cleaning abnormal data in the raw data through data preprocessing, and generating a data set in a unified format; Extract relevant features of each type of original data in the data set, remove invalid features from the relevant features based on variance threshold analysis, and retain valid features to form a feature set; Based on the time series prediction algorithm, we build a power market prediction model to predict future power market demand data and power price fluctuations, and evaluate the market risks in the energy storage system. Establish optimization objectives and constraints for the electricity market, and solve the optimal scheduling decision for energy storage equipment based on linear programming optimization algorithms; Based on real-time data and changes in the electricity market, online learning algorithms are used to optimize the dispatching decisions of energy storage equipment in real time, and the dispatching decisions are continuously adjusted according to the feedback mechanism.

2. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 1, characterized in that: The raw data of the power market, energy storage equipment and environmental conditions are collected, and abnormal data in the raw data is identified and cleaned through data preprocessing to generate a data set in a unified format, including: Collecting raw data of the power market, energy storage equipment and environmental conditions in real time, and the raw data includes power market data, energy storage equipment data and environmental data; Using linear interpolation to process missing values ​​in the original data, remove redundant data, set an abnormal threshold for the original data, and identify and clean up abnormal data that does not meet the abnormal threshold; The raw data are converted into standardized data with a mean of 0 and a standard deviation of 1, and the raw data from different sources are timestamp aligned and fused to form a data set in a unified format.

3. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 1, characterized in that: The extracting of relevant features of each type of original data in the data set, eliminating invalid features in the relevant features based on variance threshold analysis, and retaining valid features to form a feature set includes: Extracting relevant features of the original data, wherein the relevant features include time features, statistical features, historical data features and differential features; Obtaining electricity price and demand data of the current electricity market, performing Fourier transform on the electricity price and demand data, converting the time domain signal into a frequency domain signal using the Fourier transform formula, extracting periodic components in different frequency domains, and analyzing the frequency characteristics of the periodic components; The variance of each of the related features is calculated and compared with a preset variance threshold. If the variance of the related feature is less than or equal to the preset variance threshold, it is determined to be an invalid feature and is eliminated. If the variance of the related feature is greater than the preset variance threshold, it is determined to be a valid feature, and all valid features are integrated to form a feature set.

4. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 1, characterized in that: The time series prediction algorithm is used to construct a power market prediction model, predict future power market demand and power price fluctuations, and evaluate market risks in energy storage systems, including: Obtain the electricity price and demand data of the current electricity market, determine the order of the autoregressive part and the moving average part based on the autoregressive integral moving average model time prediction algorithm, and build an electricity market prediction model; The preprocessed data set is divided into a training set and a test set, the training set and the test set are used to train and optimize the electricity market forecasting model respectively, and the trained electricity market forecasting model is used to forecast future electricity market demand to obtain a forecast result.

5. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 4, characterized in that: The expression of the power market forecasting model is: Where Y t is the electricity market price and demand data at the current moment; μ is a constant term, is the coefficient of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t is the error term; Y t-i is the observed value at time ti; p is the order of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t-j is the error term at time tj; q is the order of the sliding average part.

6. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 1, characterized in that: The optimization objectives and constraints of the electricity market are established, and the optimal dispatching decision of the energy storage equipment is generated based on the acquired real-time data and prediction results, including: Obtain the electricity price in the electricity market and the power, price and quantity of electricity required to be purchased, and establish the objective function of the electricity market with the goal of minimizing costs; Set the constraints of the electricity market, use the linear programming optimization algorithm to calculate the energy storage equipment scheduling strategy, and output the optimal scheduling strategy for the energy storage equipment.

7. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 6, characterized in that: The objective function of the electricity market is: In the formula, C t is the electricity price; t represents the time index; P t is the power required to be purchased from the grid at time t; t is the electricity price of the energy storage device at time t; E t It is the amount of electricity discharged by the energy storage device at time t; T represents the total time period length.

8. The method for analyzing interactive characteristics of energy storage data in the power market according to claim 6, characterized in that: The expression for calculating the energy storage device scheduling strategy using the linear programming optimization algorithm is: minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0 In the formula, P is one of the decision variables; E is another decision variable; f(P,E) is the objective function; g(P,E) is the function representing the inequality constraint; h(P,E) is the function representing the inequality constraint.

9. A power market energy storage data interactive feature analysis system, characterized in that: include: The data acquisition module is used to collect raw data of the power market, energy storage equipment and environmental conditions, identify and clean up abnormal data in the raw data through data preprocessing, and generate a data set in a unified format; An extraction modeling module is used to extract relevant features of various types of original data in the data set, and based on variance threshold analysis, remove invalid features from the relevant features and retain valid features to form a feature set; The forecasting analysis module is used to build a power market forecasting model based on the time series forecasting algorithm, predict future demand data and power price fluctuations in the power market, and evaluate the market risks in the energy storage system; The decision optimization module is used to establish the optimization objectives and constraints of the power market and solve the optimal scheduling decision of energy storage equipment based on the linear programming optimization algorithm; The feedback regulation module is used to optimize the dispatching decisions of energy storage equipment in real time based on real-time data and changes in the electricity market, using online learning algorithms, and continuously adjusting the dispatching decisions according to the feedback mechanism.

10. The power market energy storage data interactive feature analysis system according to claim 9, characterized in that: The data acquisition module includes: a data acquisition module, a data preprocessing module and a standardization merging module, wherein: The data acquisition module is used to collect raw data of the power market, energy storage equipment and environmental conditions in real time, and the raw data includes power market data, energy storage equipment data and environmental data; The data preprocessing module is used to process missing values ​​in the original data using a linear interpolation method, remove redundant data, set an abnormal threshold for the original data, and identify and clean up abnormal data that does not meet the abnormal threshold; The standardization merging module is used to convert the original data into standardized data with a mean of 0 and a standard deviation of 1, and to align the timestamps of the original data from different sources to form a data set in a unified format.

11. The power market energy storage data interactive feature analysis system according to claim 9, characterized in that: The extraction modeling module includes: a feature extraction module, a Fourier transform module and a feature selection module, wherein: The feature extraction module is used to extract relevant features of the original data, and the relevant features include time features, statistical features, historical data features and differential features; The Fourier transform module is used to obtain the power price and demand data of the current power market, perform Fourier transform on the power price and demand data, convert the time domain signal into a frequency domain signal using the Fourier transform formula, extract the periodic components in different frequency domains, and analyze the frequency characteristics of the periodic components; The feature selection module is used to calculate the variance of each of the related features and compare it with a preset variance threshold. If the variance of the related feature is less than or equal to the preset variance threshold, it is determined to be an invalid feature and is eliminated. If the variance of the related feature is greater than the preset variance threshold, it is determined to be a valid feature, and all valid features are integrated to form a feature set.

12. The power market energy storage data interactive feature analysis system according to claim 9, characterized in that: The prediction analysis module includes: a model building module and a training prediction module, wherein: The model building module is used to obtain the power price and demand data of the power market at the current moment, determine the order of the autoregressive part and the sliding average part based on the autoregressive integral sliding average model time prediction algorithm, and build a power market prediction model; The training prediction module is used to divide the preprocessed data set into a training set and a test set, respectively use the training set and the test set to train and optimize the electricity market prediction model, and use the trained electricity market prediction model to predict future electricity market demand to obtain a prediction result.

13. The power market energy storage data interactive feature analysis system according to claim 12, characterized in that: The expression of the power market forecasting model is: Where Y t is the electricity market price and demand data at the current moment; μ is a constant term, is the coefficient of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t is the error term; Y t-i is the observed value at time ti; p is the order of the autoregressive part; θ j is the coefficient of the sliding average part; ∈ t-j is the error term at time tj; q is the order of the sliding average part.

14. The power market energy storage data interactive feature analysis system according to claim 9, characterized in that: The decision optimization module includes: a target setting module and a strategy output module, wherein: The target setting module is used to obtain the electricity price in the electricity market and the power, electricity price and electricity quantity required to be purchased, and to establish the objective function of the electricity market with the goal of minimizing the cost; The strategy output module is used to set the constraints of the power market, calculate the energy storage device scheduling strategy using a linear programming optimization algorithm, and output the optimal scheduling strategy for the energy storage device.

15. The power market energy storage data interactive feature analysis system according to claim 14, characterized in that: The objective function of the electricity market is: In the formula, C t is the electricity price; t represents the time index; P t is the power required to be purchased from the grid at time t; t is the electricity price of the energy storage device at time t; E t It is the amount of electricity discharged by the energy storage device at time t; T represents the total time period length.

16. The power market energy storage data interactive feature analysis system according to claim 14, characterized in that: The expression for calculating the energy storage device scheduling strategy using the linear programming optimization algorithm is: minf(P,E),subject-to,g(P,E)≤0,h(P,E)=0 In the formula, P is one of the decision variables; E is another decision variable; f(P,E) is the objective function; g(P,E) is the function representing the inequality constraint; h(P,E) is the function representing the inequality constraint.

Images