Power load prediction method and device, equipment and storage medium

Abstract

The invention discloses a power load prediction method, apparatus and device, and a storage medium. The method comprises the steps of obtaining a first power load sequence of a power system; performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; predicting a power load according to the first power load sequence and the uncertainty feature data to obtain a first predicted power load sequence, and predicting a power load predicted value at the target prediction moment; determining a power load residual sequence according to the first power load sequence and the first predicted power load sequence; predicting a power load residual error according to the power load residual error sequence to obtain a power load residual error prediction value; and determining a target power load prediction result according to the power load prediction value and the power load residual prediction value. According to the method and the device, the uncertainty analysis is performed on the historical power load sequence, and the power load is predicted based on the uncertainty analysis result, so that the accuracy of power load prediction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power load forecasting, and in particular to a power load forecasting method, device, equipment and storage medium. Background Art

[0002] There are many methods for power load forecasting at present. Traditional forecasting methods such as regression analysis, time series method, grey model, etc. have certain effects and stability when dealing with simple and linear load changes. However, these methods are often difficult to accurately capture the complex nonlinear characteristics and uncertainty factors of power load. Intelligent forecasting methods such as artificial neural networks, support vector machines, fuzzy logic, etc., although they have certain advantages in dealing with complex relationships, also have some limitations, such as neural networks are prone to fall into local optimal solutions, resulting in inaccurate forecast results.

[0003] With the widespread access to distributed energy, the diversification of user electricity consumption behavior and the development of smart grids, the changing patterns of power loads have become more complex and changeable. Traditional prediction methods and single intelligent prediction methods can no longer meet the power system's requirements for high-precision and high-reliability load prediction. Therefore, how to improve the accuracy of power load prediction has become an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, device and storage medium for power load forecasting, which performs uncertainty analysis on historical power load sequences, predicts power loads based on the uncertainty analysis results, and predicts and corrects power load residuals, thereby effectively reducing prediction errors and improving the accuracy of power load forecasting.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting power load, comprising: Acquire a historical power load sequence of the power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence; performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; Predicting the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predicting the power load at a target prediction time to obtain a power load prediction value; Determine an electric load residual sequence according to the first electric load sequence and the first predicted electric load sequence; Predicting the power load residual according to the power load residual sequence to obtain a power load residual prediction value; A target power load prediction result is determined according to the power load prediction value and the power load residual prediction value.

[0006] In a second aspect, an embodiment of the present application provides a power load prediction device, the power load prediction device comprising: a data acquisition unit, an uncertainty analysis unit, a first load prediction unit, a data processing unit, and a second load prediction unit, wherein: The data acquisition unit is used to obtain a historical power load sequence of the power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence; The uncertainty analysis unit is used to perform uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; The first load prediction unit is used to predict the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predict the power load at a target prediction time to obtain a power load prediction value; The data processing unit is used to determine a power load residual sequence according to the first power load sequence and the first predicted power load sequence; The second load prediction unit is used to predict the power load residual according to the power load residual sequence to obtain a power load residual prediction value; The data processing unit is further used to determine a target power load prediction result according to the power load prediction value and the power load residual prediction value.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0008] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0009] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0010] It can be seen that the following beneficial effects are achieved by using the embodiments of the present application: By implementing the embodiment of the present application, the historical power load sequence of the power system in a preset time period is obtained, and the historical power load sequence is preprocessed to obtain a first power load sequence; uncertainty analysis is performed on the first power load sequence to obtain uncertainty characteristic data; the power load is predicted based on the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and the power load at the target prediction time is predicted to obtain a power load prediction value; the power load residual sequence is determined based on the first power load sequence and the first predicted power load sequence; the power load residual is predicted based on the power load residual sequence to obtain a power load residual prediction value; the target power load prediction result is determined based on the power load prediction value and the power load residual prediction value. It can be seen that by performing uncertainty analysis on the historical power load sequence, predicting the power load based on the uncertainty analysis results, and predicting and error correcting the power load residual, the prediction error is effectively reduced and the accuracy of power load prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0012] Figure 1 It is a flow chart of a method for predicting power load provided in an embodiment of the present application; Figure 2 This is a schematic diagram of a result of power load prediction provided by an embodiment of the present application; Figure 3 It is a schematic diagram of a flow chart of power load residual prediction provided by an embodiment of the present application; Figure 4 It is a flowchart of another power load forecasting method provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of a power load prediction device provided in an embodiment of the present application; Figure 6 It is a structural schematic diagram of a sequence decomposition unit of a second load forecasting unit provided in an embodiment of the present application; Figure 7 is a structural schematic diagram of a residual prediction unit of a second load prediction unit provided in an embodiment of the present application; Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0015] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0016] The following is an explanation of the relevant contents, concepts, meanings, technical issues, technical solutions, beneficial effects, etc. involved in the embodiments of the present application.

[0017] First, some terms involved in this application are explained: User-side resources: User-side resources refer to equipment and devices such as power generation, power consumption and energy storage that are installed on the power consumption side, belong to the user and have the ability to interact with the power grid.

[0018] See also Figure 1 , Figure 1 : is a flow chart of a method for predicting power load provided in an embodiment of the present application, the method includes but is not limited to the following steps: S101. Obtain a historical power load sequence of a power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence.

[0019] In the embodiment of the present application, the power system is an electric energy production and consumption system composed of power generation, transmission, transformation, distribution and power consumption. The electric energy generated by it can be supplied to various user-side resources through transmission, transformation and distribution. The embodiment of the present application mainly analyzes and predicts the power consumption data of user-side resources. Therefore, the power load data of the power system can be obtained for specific analysis.

[0020] The preset time period refers to a pre-set historical time period for power load analysis. The time period is set according to specific application requirements and analysis purposes. For example, if you need to study short-term load fluctuation characteristics, the preset time period can be set to the past few hours or a day to analyze the load variation pattern during the day. If you need to analyze long-term power load trends, the preset time period can be set to the past few years to predict power demand in the next year.

[0021] The historical power load sequence refers to an ordered set of power load data recorded by the power system within a preset time period. It is indexed by time and consists of a series of discrete power load data. The historical power load sequence reflects the change of power load over time within a preset time period, that is, the historical power load sequence has volatility and regularity. Among them, volatility means that the power load will change instantly due to various factors, such as the start and stop of industrial production, changes in residents' electricity consumption habits, sudden changes in weather, etc. Regularity is manifested on different time scales. For example, the daily load curve shows that the load is higher during the peak period of daytime electricity consumption and lower during the valley period at night. The weekly load curve shows that there will be different electricity consumption patterns on weekdays and weekends. The annual load curve shows that the load is higher during summer cooling and winter heating.

[0022] In a specific embodiment, the historical power load sequence of the power system in a preset time period can be obtained through a Supervisory Control And Data Acquisition (SCADA) system, which has the function of real-time monitoring and control of the operating equipment of the power system, and can realize functions such as data acquisition, equipment control, measurement, parameter adjustment, and signal alarm. At the same time, the metering equipment and communication technology in the Advanced Metering Infrastructure (AMI) can be used to accurately and comprehensively collect the user's power usage data to obtain the historical power load sequence of the power system in the preset time period.

[0023] Next, after obtaining the historical power load sequence, it is necessary to preprocess it to obtain the first power load sequence. Since there may be abnormal data in the obtained historical power load sequence, the abnormal data may be caused by equipment failure, communication error, etc., therefore, it is necessary to preprocess the historical power load sequence to correct the abnormal data and ensure the accuracy of the data for power load forecasting.

[0024] Optionally, when preprocessing the historical power load sequence, in order to eliminate the dimensional effects of different factors and limit the data range, so as to facilitate further data processing and model training, the data in the historical power load sequence can also be normalized. For example, Min-Max normalization can be used. Specifically, Min-Max normalization performs linear transformation based on the maximum and minimum values ​​in the historical power load sequence, so that each power load data in the historical power load sequence is mapped to the [0,1] interval. By normalizing the historical power load sequence, the efficiency and stability of model training can be improved, and model training problems caused by data dimensional differences can be effectively reduced.

[0025] Optionally, the historical power load sequence may include n power load data, where n is an integer greater than 1; the above step of preprocessing the historical power load sequence to obtain the first power load sequence may specifically include the following steps: A101, determining the absolute value of the difference between any two adjacent power load data among the n power load data, and obtaining n-1 load difference values; A102. Determine the average value of the n-1 load differences to obtain the load difference average value; A103. Determine an abnormal load threshold value according to a preset correction coefficient and the load difference average value; A104, taking the power load data greater than the abnormal load threshold among the n power load data as abnormal data, and obtaining j abnormal data; j is an integer less than n; A105. Determine the power load data except the j abnormal data among the n power load data to obtain nj power load data, and determine the average value of the nj power load data to obtain the load average value; A106. Replace each of the j abnormal data with the load average value to obtain j corrected data; A107. Determine the first power load sequence based on the j correction data and the nj power load data.

[0026] Among them, the preset correction coefficient refers to a parameter that is pre-set based on actual experience and historical data to adjust the abnormal load threshold. By setting the preset correction coefficient, the judgment criteria for abnormal data can be flexibly adjusted. For example, when the power load data fluctuates greatly, the preset correction coefficient can select a larger value to increase the abnormal load threshold and reduce the situation where normal fluctuation data is misjudged as abnormal. Otherwise, when the power load data fluctuates relatively smoothly, the preset correction coefficient can select a smaller value to reduce the abnormal load threshold so as to more accurately identify abnormal data, improve the quality of power load data, and thus improve the accuracy of power load forecasting.

[0027] The historical power load sequence may include n power load data, where n is an integer greater than 1.

[0028] In a specific embodiment, by determining the absolute value of the difference between any two adjacent power load data among n power load data, n-1 load differences can be obtained, and the load difference can represent the change range between adjacent data to determine the fluctuation of the power load data.

[0029] Next, determine the average value of n-1 load differences to obtain the load difference average value. Multiply the preset correction coefficient and the load difference average value to obtain an abnormal load threshold. The abnormal load threshold is used to identify abnormal data in the n power load data, and its value can be adjusted by changing the size of the preset correction coefficient.

[0030] By taking the power load data greater than the abnormal load threshold among the n power load data as abnormal data, j abnormal data can be obtained, where j is an integer less than n. By determining the power load data other than the j abnormal data among the n power load data, nj power load data can be obtained, and the average value of the nj power load data is determined to obtain the load average value, which can be used to represent the average level of normal power load data.

[0031] By replacing each of the j abnormal data with the load average value, j corrected data can be obtained, and the first power load sequence can be obtained by recombining the j corrected data with the nj power load data that are not judged as abnormal. By identifying and correcting the abnormal data in the historical power load sequence, the data deviation caused by the abnormal data is avoided, and then the first power load sequence with higher data quality is obtained, which can more accurately reflect the real situation of the power load.

[0032] S102: Perform uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data.

[0033] In an embodiment of the present application, in order to clarify the changing characteristics of the power load data of the user-side resources and identify the uncertain factors that may affect the load changes, uncertainty analysis can be performed on the first power load sequence to obtain uncertainty characteristic data, which can be used for accurate load forecasting.

[0034] The power load of user-side resources is affected by many factors, including but not limited to weather factors, time factors, economic activity factors, and user behavior factors. For example, in summer, the extensive use of refrigeration equipment such as air conditioners will lead to a significant increase in power load. In winter, the operation of heating equipment will also lead to a significant increase in power load.

[0035] By analyzing the relationship between each influencing factor and the power load, the relationship can be specifically used to establish a corresponding mathematical model, such as a regression model, to quantify the impact of the influencing factors on the power load. Based on the analysis results of the relationship between the influencing factors and the power load, the uncertainty characteristic data of the power load is evaluated, where the uncertainty characteristic data can be represented by variance, standard deviation, probability distribution, etc. For example, variance and standard deviation can measure the degree of discreteness of the power load data. The greater the degree of discreteness, the higher the uncertainty of the load. The probability distribution can comprehensively describe the possibility of the power load appearing in different value ranges.

[0036] By performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data, considering the uncertainty characteristic data in power load forecasting can make the forecast result closer to the actual situation and reduce the forecast error. At the same time, the uncertainty characteristic data can be used to formulate more flexible and adaptive strategies to cope with the uncertain changes in power load and ensure the safe and stable operation of the power system.

[0037] Optionally, the above step of performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data may specifically include the following steps: A201. Determine target attribute information corresponding to the first power load sequence; A202. Determine a target application scenario of the power system corresponding to the target attribute information; the target application scenario includes one of the following: a load response scenario that can be reduced, a device charging and discharging scenario, and a temperature-controlled load operation scenario; A203, obtaining operation data of the power system corresponding to the target application scenario in the preset time period; A204. Determine uncertainty factor data according to the operation data; the uncertainty factor data includes at least one of the following: user behavior parameters, device parameters, and environmental parameters; A205. Perform feature extraction on the uncertainty factor data to obtain the uncertainty feature data.

[0038] In a specific embodiment, target attribute information corresponding to the first power load sequence is determined, wherein the target attribute information may include: specific data source information, time stamp information, load magnitude information, load change trend, etc.

[0039] Among them, the specific source information of the data clarifies the source of the first power load sequence data, that is, the specific user-side resources. User-side resources include a variety of equipment and entities, such as various types of production equipment, electric vehicles, energy storage equipment, and residential power equipment of industrial and commercial users. The main user-side resources of the power load data are analyzed through the specific source information of the data to analyze the impact of the power consumption characteristics of different types of users on the power load. For example, when the power load data comes from residential power equipment, the power load may show a pattern related to the change in electricity prices, so as to determine the cause of the change in power load. Time stamp information refers to the specific time corresponding to the recording of power load data, the load magnitude information reflects the size of the power load, and the load change trend shows the change trend of the power load over time.

[0040] According to the target attribute information, the target application scenario of the corresponding power system can be determined, wherein the target application scenario includes one of the following: a reducible load response scenario, an equipment charging and discharging scenario, and a temperature-controlled load operation scenario.

[0041] It should be noted that in the scenario of curtailable load response, the first power load sequence can indicate that the load has large fluctuations in certain time periods, such as when users actively reduce or increase electricity consumption under incentives (such as rising electricity prices). In the equipment charging and discharging scenario, the first power load sequence can indicate that the power load increases and decreases regularly in certain time periods, such as the charging and discharging behavior of electric vehicles and energy storage devices. In the temperature-controlled load operation scenario, the first power load sequence can indicate that there is a correlation between load changes and temperature changes, such as the operation of temperature-controlled equipment such as air conditioners and electric heaters.

[0042] Obtain the operating data of the power system corresponding to the target application scenario in the preset time period, which can be obtained from the power system monitoring system, smart meter records, weather station data, equipment management system, etc. In the scenario of load reduction response, the operating data can be the response time and response amount of the user's participation in load reduction. In the equipment charging and discharging scenario, the operating data can be the charging and discharging power, start and end time, battery capacity and other data of the charging equipment. In the temperature control load operation scenario, the operating data can be the indoor and outdoor temperature, the switch status of the temperature control equipment, the set temperature and other data. The operating data can be used to analyze the uncertainty factors corresponding to the target application scenario to determine the change mechanism of the power load under the target application scenario.

[0043] Uncertainty factor data can be determined based on the operation data, wherein the uncertainty factor data includes at least one of the following: user behavior parameters, equipment parameters, environmental parameters, etc. Among them, the user behavior parameters indicate that in the scenario where the load can be reduced, the user's willingness and degree of response to the load reduction instruction are uncertain, which may be affected by the intensity of incentives, the user's own electricity usage habits, etc., and in the equipment charging and discharging scenario, the user's use time and use method of the equipment are also different, such as the charging time selection of electric vehicle users. There are also uncertainties in equipment parameters, such as the cooling and heating efficiency of temperature control equipment, performance changes caused by the degree of equipment aging, etc., and in the equipment charging and discharging scenario, the battery charging and discharging efficiency, remaining capacity and other parameters are not fixed. At the same time, environmental parameters are also uncertain. In the temperature control load operation scenario, changes in environmental factors such as outdoor temperature and humidity will affect the operating time and power consumption of indoor temperature control equipment, and in the equipment charging and discharging scenario, the ambient temperature also affects the battery performance.

[0044] Next, feature extraction is performed on the uncertainty factor data to obtain uncertainty feature data. For example, for user behavior parameters, the probability distribution of user responses, the mean and variance of response time, and other features can be extracted. For equipment parameters, the range of equipment performance changes, the fluctuation range of key parameters, etc. can be extracted. For environmental parameters, the trend of temperature, humidity and other parameters, the frequency of extreme values, etc. can be extracted. By extracting features from uncertainty factor data, uncertainty feature data can be obtained to intuitively reflect the characteristics and impact of uncertainty factors, providing data support for subsequent power load forecasting.

[0045] S103. Predict the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predict the power load at a target prediction time to obtain a power load prediction value.

[0046] In the embodiment of the present application, the BP neural network model can be used for power load forecasting, and the autoregressive integrated moving average model (ARIMA), long short-term memory network (LSTM) and other models can also be used for power load forecasting. Different models have different adaptability to data. For example, the BP neural network is good at processing complex nonlinear relationships and can learn the implicit patterns in the power load series, while the ARIMA model is suitable for time series with stationary and seasonal characteristics. When selecting a specific model, the model or model combination can be selected according to the characteristics of the data and the prediction accuracy requirements.

[0047] In a specific embodiment, the first power load sequence can be used as input data, and the uncertainty characteristic data can be input into the BP neural network model as auxiliary information, so that the BP neural network model considers the influence of the uncertainty characteristic data on the power load when predicting the power load. The first predicted power load sequence can be obtained by predicting the power load based on the first power load sequence and the uncertainty characteristic data, wherein the first power load sequence and the first predicted power load sequence are the same in time, that is, the first power load sequence indicates the actual data within a period of time, and the first predicted power load sequence indicates the predicted data within the period of time. Then, the power load at the target prediction time can be predicted according to the BP neural network model to obtain the power load prediction value.

[0048] Optionally, the above step of predicting the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence may specifically include the following steps: A301. Obtain a first training data set and a first test data set, and determine an expected output value corresponding to the first test data set to obtain an expected output data set; the first training data set is historical power load data used for model training; the first test data set is historical power load data used for model testing; A302, performing feature fusion on the first training data set and the uncertainty feature data to obtain a second training data set; A303: training a preset neural network model according to the second training data set to obtain a first neural network model; A304, inputting the first test data set into the first neural network model to obtain a target output data set; A305, determining a training error data set according to the expected output data set and the target output data set; A306. Determine a model adjustment parameter corresponding to the first neural network model according to the training error data set; A307. Adjusting the model parameters of the first neural network model according to the model adjustment parameters to obtain a second neural network model; A308. Input the first power load sequence into the second neural network model to obtain the first predicted power load sequence.

[0049] Among them, the preset neural network model refers to the neural network architecture pre-selected before power load forecasting. In the embodiment of the present application, the preset neural network model is a BP neural network model.

[0050] In a specific embodiment, a first training data set and a first test data set are obtained, and an expected output value corresponding to the first test data set is determined to obtain an expected output data set, wherein the first training data set is historical power load data used for model training, and the first test data set is historical power load data used for model testing, and the expected output value is the actual power load value corresponding to the test set data, which is used to compare with the output value of the model to determine the accuracy of the model.

[0051] Next, the first training data set and the uncertainty feature data are subjected to feature fusion to obtain a second training data set, and a preset neural network model is trained according to the second training data set to obtain a first neural network model.

[0052] By inputting the first test data set into the first neural network model, the target output data set can be obtained. The training error data set can be determined based on the expected output data set and the target output data set. The expected output data is the true value, and the target output data is the predicted value. By comparing the true value with the predicted value and calculating the error of each data point, the training error data set can be determined.

[0053] The training error indicates the shortcomings of the first neural network model. By analyzing the training error data set, according to the size and distribution of the error, the parameters that need to be adjusted for the first neural network model can be determined, that is, the model adjustment parameters. The model adjustment parameters can be the model's weight parameters, bias parameters, learning rate, etc.

[0054] The model parameters of the first neural network model are adjusted according to the model adjustment parameters to obtain the second neural network model. Then, the first power load sequence is input into the second neural network model to obtain the first predicted power load sequence. By training the neural network model according to the uncertainty characteristic data and the power load history data, the model can take into account more factors affecting the power load, thereby more accurately capturing the changing law of the power load and improving the accuracy of the prediction.

[0055] See also Figure 2 , Figure 2 This is a schematic diagram of the results of a power load forecast provided by an embodiment of the present application. As shown in the figure, the figure shows the change of the predicted value and the actual value of the power load over time. The horizontal axis represents time in hours (h), from 2 to 24, covering a time range of one day, and the vertical axis represents load demand in megawatts (MW), ranging from 400MW to 1300MW.

[0056] In the figure, the dotted curve represents the predicted value of the power load demand at different times obtained based on the BP neural network model, and the solid curve represents the real value of the power load demand at different times obtained through actual measurement or recording.

[0057] Analysis of the power load forecast results shows that both curves show a trend of rising first and then falling within a day, that is, at 2 a.m., the load demand is at a relatively low level, and then begins to rise gradually. After reaching a peak in the evening and night, it gradually falls back. For example, in the peak stage, that is, around 18:00 to 22:00, the load demand reaches the peak area of ​​the day. At this time, it may be due to the fact that residents go home from get off work, various electrical equipment are used in large quantities, and commercial and industrial activities are also in an active state, resulting in a concentrated increase in electricity demand. In the declining stage, that is, around 22:00 to 24:00, after the peak, the load demand begins to gradually decline. As the night time progresses, most electricity consumption activities decrease, and the load demand gradually falls back to a lower level, close to the initial load demand state in the early morning.

[0058] It can be seen that the predicted value curve and the true value curve do not completely overlap, and there is a certain degree of deviation. In some time periods, the predicted value is higher than the true value, while in other time periods, the predicted value is lower than the true value. This shows that although the prediction model can roughly capture the changing trend of power load demand, there are certain errors in the specific values ​​due to some uncertain factors. If the predicted value continues to be higher than the true value, it may cause excessive power generation in the power system, resulting in energy waste and increased costs. If the predicted value continues to be lower than the true value, it may cause insufficient power supply, affect the normal power consumption of users, and even cause unstable operation of the power grid. Therefore, this prediction error caused by uncertainty can be further predicted to improve the accuracy of power load prediction.

[0059] S104. Determine a power load residual sequence according to the first power load sequence and the first predicted power load sequence.

[0060] In an embodiment of the present application, the first power load sequence is an actually recorded power load data sequence, which reflects the actual situation of the power load in the past preset time period, and the first predicted power load sequence is a data sequence obtained by predicting the power load in the preset time period using a prediction model.

[0061] In a specific embodiment, the power load residual sequence can be determined according to the first power load sequence and the first predicted power load sequence, that is, the power load residual sequence can be obtained by subtracting the value of the first power load sequence from the value of the first predicted power load sequence at the corresponding time point.

[0062] The power load residual sequence can intuitively reflect the difference between the predicted value and the actual value. The smaller the value of the power load residual sequence and the more uniform the distribution, the higher the prediction accuracy of the prediction model. Otherwise, if the power load residual sequence fluctuates greatly and the value is dispersed, it means that the prediction model has a large prediction error.

[0063] S105. Predicting the power load residual according to the power load residual sequence to obtain a power load residual prediction value.

[0064] In the embodiment of the present application, since the prediction result of the prediction model still has a certain error relative to the true value, after obtaining the power load residual sequence, the power load residual sequence can be further predicted to reduce the prediction error. The power load residual sequence can be predicted using time series analysis methods, machine learning algorithms, etc.

[0065] Optionally, the above step of predicting the power load residual according to the power load residual sequence to obtain the power load residual prediction value may specifically include the following steps: A501. Performing modal decomposition on the power load residual sequence by using a preset modal decomposition model to obtain a plurality of inherent modal components and a residual component; A502. Predicting the multiple inherent modal components and the residual components by using a preset power load prediction model to obtain multiple first power load residuals and one second power load residual; A503. Determine the power load residual prediction value based on the multiple first power load residuals and the one second power load residual.

[0066] The preset modal decomposition model refers to the preset Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) model. The ICEEMDAN model can decompose the signal into multiple intrinsic modal components and residual components. It is improved based on the ensemble empirical mode decomposition (EEMD) and effectively solves the modal aliasing problem by adding adaptive white noise.

[0067] Among them, the preset power load forecasting model refers to the preset Autoregressive Integrated Moving Average (ARIMA) model. The ARIMA model combines the characteristics of the autoregressive (AR) and moving average (MA) models, and also converts the non-stationary time series into a stationary series through differential operation (I) for analysis.

[0068] In a specific embodiment, the modal decomposition of the power load residual sequence is performed through a preset modal decomposition model, and multiple inherent modal components and a residual component can be obtained. Specifically, by determining the local maximum and minimum values ​​in the residual sequence, fitting the upper and lower envelopes, and calculating the average values ​​of the upper and lower envelopes, the inherent modal components that meet the preset component conditions are continuously iterated and screened out until the remaining components can no longer be further decomposed to obtain the residual components, wherein the preset component conditions refer to the conditions satisfied by the intrinsic mode function.

[0069] The power load residual sequence includes components of various frequencies and characteristics, and it is difficult to predict them directly. However, modal decomposition can decompose complex sequences into relatively simple components. Each inherent modal component represents the fluctuation characteristics of the power load residual sequence in a certain frequency band, and the residual component is the long-term trend of the power load residual sequence or other difficult-to-decompose components. Therefore, by decomposing the power load residual sequence, it is easier to select appropriate prediction methods according to the characteristics of different components and improve the accuracy of the prediction.

[0070] A plurality of inherent modal components and residual components are predicted by a preset power load prediction model, and each inherent modal component and residual component is input into the preset power load prediction model in turn. The model predicts each component according to its own algorithm and learning of historical data, thereby obtaining a plurality of first power load residual prediction values ​​corresponding to the inherent modal components and a second power load residual prediction value corresponding to the residual component. Specifically, the ARIMA model will first perform stationarity processing and white noise test on the data, determine the model parameters (such as p, d, q values) according to the characteristics of the data, and then make predictions, that is, the model parameters of the ARIMA model corresponding to each component are different.

[0071] The power load residual prediction value is determined according to the multiple first power load residuals and one second power load residual, that is, the power load residual prediction value can be obtained by linearly superimposing the multiple first power load residuals and one second power load residual.

[0072] By decomposing the complex power load residual sequence into multiple simple components through modal decomposition and then making separate predictions for each component, the changing characteristics of the residual sequence can be captured more accurately. Compared with directly predicting the power load residual sequence, the accuracy of the prediction is improved.

[0073] See also Figure 3 , Figure 3This is a flow chart of a power load residual prediction provided by an embodiment of the present application. As shown in the figure, by inputting a power load residual sequence, the power load residual sequence is decomposed based on the ICEEMDAN (adaptive noise complete ensemble empirical mode decomposition) model to decompose the power load residual sequence into multiple intrinsic mode components (IMF1, IMF2, ..., IMFn) with different frequency characteristics and a residual component (Rn), wherein IMF1 represents the first intrinsic mode component, IMFn represents the nth intrinsic mode component, each intrinsic mode component represents the fluctuation characteristics of the residual sequence in a certain frequency band, and the residual component reflects the long-term trend of the sequence or the part that is difficult to decompose.

[0074] For the multiple intrinsic modal components and residual components obtained by decomposition, the ARIMA (autoregressive integrated moving average) model corresponding to the component can be used for prediction, that is, the ARIMA model can determine the appropriate model parameters according to the historical data of each component, so as to perform power load forecasting based on the corresponding ARIMA model, and obtain the IMF1 prediction results, IMF2 prediction results, ..., IMFn prediction results and Rn prediction results respectively.

[0075] By summarizing and calculating the prediction results of each component, the power load residual prediction value can be finally obtained. The power load residual prediction value reflects the deviation from the power load prediction value and can be used to correct the power load prediction value to improve the accuracy of the power load prediction.

[0076] S106. Determine a target power load prediction result according to the power load prediction value and the power load residual prediction value.

[0077] In the embodiment of the present application, the power load prediction value is the predicted value of the power load corresponding to the target prediction time obtained by processing the first power load sequence and uncertainty characteristic data and predicting through a neural network model, and the power load residual prediction value is the value obtained by synthesizing the power load residual sequence after modal decomposition and prediction of each component, and the power load residual prediction value reflects the deviation of the power load prediction value.

[0078] In a specific embodiment, the target power load prediction result can be obtained by adding the power load prediction value and the power load residual prediction value. The power load prediction value may have certain errors due to the influence of various uncertain factors, and the power load residual prediction value reflects the possible situations of these errors. Therefore, by combining the power load prediction value with the power load residual prediction value, the power load prediction value can be corrected, so that the target power load prediction result is closer to the actual power load, thereby improving the accuracy of the prediction.

[0079] See also Figure 4 , Figure 4It is a flow chart of another power load forecasting method provided by an embodiment of the present application. As shown in the figure, the flow chart uses the historical power load sequence as the initial input data, generates a predicted power load sequence and a power load forecast value through BP neural network processing, compares the predicted power load sequence with the real power load sequence, calculates the difference between the two, and obtains the power load residual sequence, wherein the real power load sequence is the actual recorded power load data, and the power load residual sequence reflects the deviation between the BP neural network prediction result and the actual value. By predicting and processing the power load residual sequence, the power load residual value corresponding to the power load residual sequence can be obtained.

[0080] By summarizing and calculating the power load forecast value and the power load residual value, we can finally get the power load forecast result. The power load forecast result comprehensively considers the preliminary forecast and residual correction, and can more accurately reflect the actual situation of future power load.

[0081] Optionally, the following steps may also be included: A601. Establish a corresponding target state model according to the target application scenario; the target state model includes one of the following: a user responsiveness model, a device operation state model, and a temperature control load operation state model; A602. Determine the load expectation result corresponding to the target prediction time based on the first predicted power load sequence and the target state model; A603, determining the deviation between the target power load prediction result and the load expected result, and obtaining a target deviation; A604, determining a target correction factor according to the target deviation; A605. Correct the target power load forecast result according to the correction factor to obtain the corrected target power load forecast result.

[0082] In a specific embodiment, a corresponding target state model is established according to the target application scenario, wherein the target state model includes one of the following: a user responsiveness model, a device operation state model, and a temperature control load operation state model. For example, a user responsiveness model can be established according to a reducible load response scenario, and the model is used to describe the user's response degree to reducing the power load under different electricity prices, incentives, etc., and a device operation state model can be constructed according to a device charging and discharging scenario, and the model reflects the charging and discharging state and law of the charging device under different conditions. A temperature control load operation state model can be established according to a temperature control load operation scenario, and the model reflects the operation state of the temperature control device with factors such as ambient temperature and set temperature.

[0083] The first predicted power load sequence is used as basic data and analyzed in combination with the established target state model. The target state model can adjust and calculate the first predicted power load sequence according to its own rules and parameters, thereby obtaining the load expectation result corresponding to the target prediction time. For example, in the user responsiveness model, the load that the user may reduce at the target prediction time is predicted based on the first predicted power load sequence and the user's response to the electricity price, thereby obtaining the load expectation result.

[0084] The target deviation is obtained based on the deviation between the target power load forecast result and the expected load result. The target power load forecast result is the forecast value obtained by comprehensively considering multiple factors, while the expected load result is the expected value further revised based on the target application scenario. The target deviation reflects the difference between the forecast result and the expected result based on a specific scenario.

[0085] The target correction factor is determined according to the target deviation. Specifically, a proportional coefficient related to the target deviation can be set based on experience. For example, when the target deviation is positive, the target correction factor can be set to 1-k×target deviation / reference value, wherein k is a pre-set empirical coefficient with a value range between 0 and 1. The reference value can represent the average value of the first predicted power load sequence. When the target deviation is negative, the target correction factor can be 1+k×|target deviation| / reference value.

[0086] The target power load forecast result is multiplied by the target correction factor to obtain the corrected target power load forecast result. By establishing a target state model and considering the special factors in the target application scenario, the forecast result is corrected to make the final forecast result more consistent with the actual situation and reduce the forecast error.

[0087] Optionally, when the target application scenario is the load-reducible response scenario, the above step A601, establishing a corresponding target state model according to the target application scenario, may specifically include the following steps: B601. Acquire the user's electricity consumption behavior data in the load reduction response scenario; B602. Analyze the user response behavior at each time scale in multiple time scales according to the user power consumption behavior data to obtain multiple power consumption behavior change characteristics; the multiple time scales include: short-term time scale, medium-term time scale and long-term time scale; B603. Determine the target key factors corresponding to the load reduction response scenario according to the multiple power consumption behavior change characteristics; the target key factors include at least one of the following: a reduction potential index, a load transfer rate, and a power equipment parameter; B604. Construct the target state model according to the target key factors.

[0088] Among them, when the target application scenario is a load-reducible response scenario, a corresponding target state model can be established according to the load-reducible response scenario.

[0089] In a specific embodiment, the electricity usage behavior data of users in load reduction response scenarios are collected, wherein the electricity usage behavior data may include the user's electricity usage at different times, the user's electricity usage habits, historical payment records, and the user's electricity usage data when faced with load reduction measures.

[0090] The time scale is divided into short-term, medium-term and long-term, where short-term refers to the time range of one day to one week, medium-term refers to the time range of one month to one quarter, and long-term refers to the time span of one year or more. At each time scale, the user's electricity consumption behavior data is analyzed. For example, at the short-term time scale, by analyzing the changes in the user's electricity consumption within a few hours after receiving the load reduction notice, it is analyzed whether the user can respond quickly and reduce the load. At the medium-term time scale, the user's response to different electricity prices within a month is analyzed to determine whether the user will adjust the electricity consumption time to avoid the high electricity price period. At the long-term time scale, by analyzing the overall change trend of the user's electricity consumption habits, the user's electricity consumption pattern changes are determined. By analyzing the user's response behavior at each time scale in multiple time scales, multiple characteristics of electricity consumption behavior changes can be obtained, such as the timeliness of load reduction and the magnitude of load adjustment.

[0091] A comprehensive analysis is conducted on the changing characteristics of multiple electricity consumption behaviors to screen out target key factors that have an important impact on the load reduction response scenarios. The target key factors include at least one of the following: a reduction potential index, a load transfer rate, and power equipment parameters. The reduction potential index indicates the maximum load that a user can reduce under different circumstances, which can be determined by analyzing the user's load reduction capabilities under different time scales. The load transfer rate indicates the proportion of a user's electricity consumption time transferred from a high-load period to a low-load period. The power equipment parameters can be determined based on the type and characteristics of the equipment used by the user.

[0092] Based on the target key factors, use appropriate mathematical methods or model structures, such as regression models, machine learning models, etc. to build a target state model. For example, based on the load transfer rate, build a user responsiveness model, which represents the electricity consumption relationship based on different electricity price signals.

[0093] By analyzing user electricity consumption behavior data, determining target key factors and building corresponding target state models, we can more accurately predict user load changes in load-reducible response scenarios to correct the predicted power load results.

[0094] In summary, by implementing the embodiments of the present application, the historical power load sequence of the power system in a preset time period is obtained, and the historical power load sequence is preprocessed to obtain a first power load sequence; uncertainty analysis is performed on the first power load sequence to obtain uncertainty characteristic data; the power load is predicted based on the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and the power load at the target prediction time is predicted to obtain a power load prediction value; the power load residual sequence is determined based on the first power load sequence and the first predicted power load sequence; the power load residual is predicted based on the power load residual sequence to obtain a power load residual prediction value; the target power load prediction result is determined based on the power load prediction value and the power load residual prediction value. It can be seen that by performing uncertainty analysis on the historical power load sequence, predicting the power load based on the uncertainty analysis results, and predicting and error correcting the power load residual, the prediction error is effectively reduced and the accuracy of power load prediction is improved.

[0095] See also Figure 5 , Figure 5 is a structural diagram of a power load prediction device provided in an embodiment of the present application, wherein the power load prediction device 500 comprises: a data acquisition unit 501, an uncertainty analysis unit 502, a first load prediction unit 503, a data processing unit 504, and a second load prediction unit 505, wherein: The data acquisition unit 501 is used to obtain a historical power load sequence of the power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence; The uncertainty analysis unit 502 is used to perform uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; The first load prediction unit 503 is used to predict the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predict the power load at a target prediction time to obtain a power load prediction value; The data processing unit 504 is used to determine a power load residual sequence according to the first power load sequence and the first predicted power load sequence; The second load prediction unit 505 is used to predict the power load residual according to the power load residual sequence to obtain a power load residual prediction value; The data processing unit 504 is further configured to determine a target power load prediction result according to the power load prediction value and the power load residual prediction value.

[0096] Optionally, the historical power load sequence includes n power load data, where n is an integer greater than 1; in the aspect of preprocessing the historical power load sequence to obtain the first power load sequence, the data acquisition unit 501 is further specifically used for: Determine the absolute value of the difference between any two adjacent power load data among the n power load data to obtain n-1 load difference values; Determine the average value of the n-1 load differences to obtain a load difference average value; Determine an abnormal load threshold value according to a preset correction coefficient and the load difference average value; The power load data greater than the abnormal load threshold value among the n power load data are taken as abnormal data to obtain j abnormal data; j is an integer less than n; Determine the power load data except the j abnormal data among the n power load data to obtain nj power load data, and determine the average value of the nj power load data to obtain the load average value; Replace each of the j abnormal data with the load average value to obtain j corrected data; The first electric power load sequence is determined according to the j correction data and the nj electric power load data.

[0097] Optionally, in the aspect of performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data, the uncertainty analysis unit 502 is further specifically used for: Determining target attribute information corresponding to the first power load sequence; Determine a target application scenario of the power system corresponding to the target attribute information; the target application scenario includes one of the following: a load response scenario that can be reduced, an equipment charging and discharging scenario, and a temperature-controlled load operation scenario; Acquire operation data of the power system corresponding to the target application scenario in the preset time period; Determine uncertainty factor data according to the operation data; the uncertainty factor data includes at least one of the following: user behavior parameters, device parameters, and environmental parameters; Feature extraction is performed on the uncertainty factor data to obtain the uncertainty feature data.

[0098] Optionally, in predicting the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, the first load prediction unit 503 is further specifically used to: Obtain a first training data set and a first test data set, and determine an expected output value corresponding to the first test data set to obtain an expected output data set; the first training data set is historical power load data used for model training; the first test data set is historical power load data used for model testing; Performing feature fusion on the first training data set and the uncertainty feature data to obtain a second training data set; Training a preset neural network model according to the second training data set to obtain a first neural network model; Inputting the first test data set into the first neural network model to obtain a target output data set; Determine a training error data set according to the expected output data set and the target output data set; Determining a model adjustment parameter corresponding to the first neural network model according to the training error data set; Adjusting the model parameters of the first neural network model according to the model adjustment parameters to obtain a second neural network model; The first power load sequence is input into the second neural network model to obtain the first predicted power load sequence.

[0099] Optionally, in the aspect of predicting the power load residual according to the power load residual sequence to obtain the power load residual prediction value, the second load prediction unit 505 is further specifically used for: Performing modal decomposition on the power load residual sequence by using a preset modal decomposition model to obtain a plurality of inherent modal components and a residual component; Predicting the plurality of inherent modal components and the residual components by using a preset power load prediction model to obtain a plurality of first power load residuals and a second power load residual; The power load residual prediction value is determined based on the plurality of first power load residuals and the one second power load residual.

[0100] See also Figure 6 , Figure 6It is a structural schematic diagram of a sequence decomposition unit of a second load forecasting unit provided by an embodiment of the present application. As shown in the figure, the sequence decomposition unit 60 includes: an EMD decomposition module 601, a local mean module 602, an intrinsic modal component calculation module 603, and a residual component calculation module 604, wherein the empirical mode decomposition (EMD) can decompose a complex signal into multiple intrinsic modal components and one residual component. Therefore, the power load residual sequence can be decomposed into multiple intrinsic modal components and one residual component through the EMD decomposition module 601. The local mean module 602 receives the signal data processed by the EMD decomposition module 601 and calculates the local mean of the signal. By analyzing and calculating the local extreme points of the signal, the local average trend information of the signal at different scales is obtained. The intrinsic modal component calculation module 603 can use information such as the local mean to calculate the intrinsic modal component, which represents the fluctuation characteristics of the original sequence in a certain specific frequency band. After obtaining each intrinsic modal component, the residual component calculation module 604 calculates the difference between the original sequence and the extracted intrinsic modal component to obtain the residual component, which represents the low-frequency trend or other difficult-to-decompose part in the sequence that is not fully represented by the intrinsic modal component.

[0101] See also Figure 7 , Figure 7 It is a structural schematic diagram of a residual prediction unit of a second load prediction unit provided in an embodiment of the present application. As shown in the figure, the residual prediction unit 70 includes: an ARIMA model-based prediction module 701 and a linear superposition module 702, wherein ARIMA (autoregressive integrated moving average model) is a time series prediction model, which is suitable for analyzing time series data with certain trends and seasonality. The ARIMA model-based prediction module 701 uses the ARIMA model to model and predict multiple intrinsic modal components and residual components obtained by decomposing the power load residual sequence, determines the model parameters of different components, and then predicts the residual according to the corresponding model. The linear superposition module 702 can perform linear superposition processing on each residual prediction value obtained by the ARIMA model prediction module to obtain the final residual prediction result.

[0102] Optionally, the power load prediction device 500 is further specifically used for: Establish a corresponding target state model according to the target application scenario; the target state model includes one of the following: a user responsiveness model, a device operation state model, and a temperature control load operation state model; Determining the load expectation result corresponding to the target prediction time based on the first predicted power load sequence and the target state model; Determine the deviation between the target power load prediction result and the load expected result to obtain a target deviation; determining a target correction factor according to the target deviation; The target power load forecast result is corrected according to the correction factor to obtain the corrected target power load forecast result.

[0103] Optionally, when the target application scenario is the load-reducible response scenario, in terms of establishing a corresponding target state model according to the target application scenario, the power load prediction device 500 is further specifically used to: Acquiring user electricity consumption behavior data in the load curtailment response scenario; Analyze the user response behavior at each time scale in multiple time scales according to the user power consumption behavior data to obtain multiple power consumption behavior change characteristics; the multiple time scales include: short-term time scale, medium-term time scale and long-term time scale; Determine the target key factors corresponding to the load reduction response scenario according to the multiple power consumption behavior change characteristics; the target key factors include at least one of the following: a reduction potential index, a load transfer rate, and a power equipment parameter; The target state model is constructed according to the target key factors.

[0104] The power load prediction device 500 described in the present application can obtain the historical power load sequence of the power system in a preset time period, and pre-process the historical power load sequence to obtain a first power load sequence; perform uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; predict the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predict the power load at the target prediction time to obtain a power load prediction value; determine the power load residual sequence according to the first power load sequence and the first predicted power load sequence; predict the power load residual according to the power load residual sequence to obtain a power load residual prediction value; determine the target power load prediction result according to the power load prediction value and the power load residual prediction value. It can be seen that by performing uncertainty analysis on the historical power load sequence, predicting the power load based on the uncertainty analysis results, and predicting and correcting the power load residual, the prediction error is effectively reduced and the accuracy of power load prediction is improved.

[0105] See also Figure 8 , Figure 8: is a structural diagram of an electronic device provided in an embodiment of the present application, the electronic device may include a processor, a memory, a communication interface and one or more programs, the processor, the memory and the communication interface may be interconnected through a bus; the one or more programs are stored in the memory and configured to be executed by the processor; in the embodiment of the present application, the program includes instructions for executing the following steps: Acquire a historical power load sequence of the power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence; performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; Predicting the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predicting the power load at a target prediction time to obtain a power load prediction value; Determine an electric load residual sequence according to the first electric load sequence and the first predicted electric load sequence; Predicting the power load residual according to the power load residual sequence to obtain a power load residual prediction value; A target power load prediction result is determined according to the power load prediction value and the power load residual prediction value.

[0106] The electronic device described in the present application can obtain the historical power load sequence of the power system in a preset time period, and pre-process the historical power load sequence to obtain a first power load sequence; perform uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; predict the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predict the power load at the target prediction time to obtain a power load prediction value; determine the power load residual sequence according to the first power load sequence and the first predicted power load sequence; predict the power load residual according to the power load residual sequence to obtain a power load residual prediction value; determine the target power load prediction result according to the power load prediction value and the power load residual prediction value. It can be seen that by performing uncertainty analysis on the historical power load sequence, predicting the power load based on the uncertainty analysis results, and predicting and correcting the power load residual, the prediction error is effectively reduced and the accuracy of power load prediction is improved.

[0107] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0108] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0109] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0110] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also exist in a terminal device or a management device as discrete components.

[0111] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0112] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. It is implemented in the form of a software program that runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0113] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A method for predicting power load, characterized in that: The method comprises: Acquire a historical power load sequence of the power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence; performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; Predicting the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predicting the power load at a target prediction time to obtain a power load prediction value; Determine an electric load residual sequence according to the first electric load sequence and the first predicted electric load sequence; Predicting the power load residual according to the power load residual sequence to obtain a power load residual prediction value; A target power load prediction result is determined according to the power load prediction value and the power load residual prediction value.

2. The method according to claim 1, characterized in that The historical power load sequence includes n power load data, where n is an integer greater than 1; the preprocessing of the historical power load sequence to obtain a first power load sequence includes: Determine the absolute value of the difference between any two adjacent power load data among the n power load data to obtain n-1 load difference values; Determine the average value of the n-1 load differences to obtain a load difference average value; Determine an abnormal load threshold value according to a preset correction coefficient and the load difference average value; The power load data greater than the abnormal load threshold value among the n power load data are taken as abnormal data to obtain j abnormal data; j is an integer less than n; Determine the power load data except the j abnormal data among the n power load data to obtain nj power load data, and determine the average value of the nj power load data to obtain the load average value; Replace each of the j abnormal data with the load average value to obtain j corrected data; The first electric power load sequence is determined according to the j correction data and the nj electric power load data.

3. The method according to claim 1, characterized in that The performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data includes: Determining target attribute information corresponding to the first power load sequence; Determine a target application scenario of the power system corresponding to the target attribute information; the target application scenario includes one of the following: a load response scenario that can be reduced, an equipment charging and discharging scenario, and a temperature-controlled load operation scenario; Acquire operation data of the power system corresponding to the target application scenario in the preset time period; Determine uncertainty factor data according to the operation data; the uncertainty factor data includes at least one of the following: user behavior parameters, device parameters, and environmental parameters; Feature extraction is performed on the uncertainty factor data to obtain the uncertainty feature data.

4. The method according to any one of claims 1 to 3, characterized in that: The step of predicting the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence includes: Obtain a first training data set and a first test data set, and determine an expected output value corresponding to the first test data set to obtain an expected output data set; the first training data set is historical power load data used for model training; the first test data set is historical power load data used for model testing; Performing feature fusion on the first training data set and the uncertainty feature data to obtain a second training data set; Training a preset neural network model according to the second training data set to obtain a first neural network model; Inputting the first test data set into the first neural network model to obtain a target output data set; Determine a training error data set according to the expected output data set and the target output data set; Determining a model adjustment parameter corresponding to the first neural network model according to the training error data set; Adjusting the model parameters of the first neural network model according to the model adjustment parameters to obtain a second neural network model; The first power load sequence is input into the second neural network model to obtain the first predicted power load sequence.

5. The method according to claim 1, characterized in that The step of predicting the power load residual according to the power load residual sequence to obtain a power load residual prediction value comprises: Performing modal decomposition on the power load residual sequence by using a preset modal decomposition model to obtain a plurality of inherent modal components and a residual component; Predicting the plurality of inherent modal components and the residual components by using a preset power load prediction model to obtain a plurality of first power load residuals and a second power load residual; The power load residual prediction value is determined based on the plurality of first power load residuals and the one second power load residual.

6. The method according to claim 3, characterized in that The method further comprises: Establish a corresponding target state model according to the target application scenario; the target state model includes one of the following: a user responsiveness model, a device operation state model, and a temperature control load operation state model; Determining the load expectation result corresponding to the target prediction time based on the first predicted power load sequence and the target state model; Determine the deviation between the target power load prediction result and the load expected result to obtain a target deviation; determining a target correction factor according to the target deviation; The target power load forecast result is corrected according to the correction factor to obtain the corrected target power load forecast result.

7. The method according to claim 6, characterized in that When the target application scenario is the load-reducible response scenario, the step of establishing a corresponding target state model according to the target application scenario includes: Acquiring user electricity consumption behavior data in the load curtailment response scenario; Analyze the user response behavior at each time scale in multiple time scales according to the user power consumption behavior data to obtain multiple power consumption behavior change characteristics; the multiple time scales include: short-term time scale, medium-term time scale and long-term time scale; Determine the target key factors corresponding to the load reduction response scenario according to the multiple power consumption behavior change characteristics; the target key factors include at least one of the following: a reduction potential index, a load transfer rate, and a power equipment parameter; The target state model is constructed according to the target key factors.

8. A power load forecasting device, characterized in that: The power load prediction device comprises: a data acquisition unit, an uncertainty analysis unit, a first load prediction unit, a data processing unit, and a second load prediction unit, wherein: The data acquisition unit is used to obtain a historical power load sequence of the power system in a preset time period, and preprocess the historical power load sequence to obtain a first power load sequence; The uncertainty analysis unit is used to perform uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; The first load prediction unit is used to predict the power load according to the first power load sequence and the uncertainty characteristic data to obtain a first predicted power load sequence, and predict the power load at a target prediction time to obtain a power load prediction value; The data processing unit is used to determine a power load residual sequence according to the first power load sequence and the first predicted power load sequence; The second load prediction unit is used to predict the power load residual according to the power load residual sequence to obtain a power load residual prediction value; The data processing unit is further used to determine a target power load prediction result according to the power load prediction value and the power load residual prediction value.

9. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images