A power data analysis method and apparatus thereof

Abstract

The application provides a power data analysis method and device, comprising: obtaining historical power consumption data and related external variable data of a target area; establishing a multiple regression relationship model between power consumption and external variables according to the historical power consumption data and related external variable data; defining a probability distribution function for each external variable; performing Monte Carlo simulation based on the multiple regression relationship model, for each iteration, randomly extracting a value from the probability distribution of each external variable, substituting the extracted external variable value into the multiple regression relationship model, and calculating the corresponding power consumption prediction value; accumulating and storing the power consumption prediction values obtained in each iteration to form a simulation result database; and identifying key external variable combinations and scenarios that cause significant changes in power consumption in the target area according to the simulation result database. The application can improve the accuracy of power consumption prediction and identify key external variable combinations and scenarios.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power data analysis, in particular to a power data analysis method and device. BACKGROUND

[0002] With the development of social economy and population growth, the demand for electricity is rising, and the stable operation of the power system and the rational allocation of power resources become more and more important. In order to improve the operation efficiency of the power system and the management level of the power resources, the power data analysis technology emerges as the times require. The traditional power data analysis method mainly relies on historical data to make simple trend prediction, which often ignores the influence of external environmental factors on power consumption, resulting in inaccurate prediction results. In addition, the existing method rarely considers the interaction between multiple external variables, making it difficult to identify the key factors affecting power consumption. SUMMARY

[0003] The purpose of the present application is to provide a power data analysis method and device to improve the accuracy of power consumption prediction and identify the key external variable combination and situation affecting power consumption.

[0004] To achieve the above purpose, the present application provides a power data analysis method, comprising:

[0005] obtaining historical power consumption data and related external variable data of a target area;

[0006] establishing a multiple regression relationship model between power consumption and external variables according to the historical power consumption data and related external variable data;

[0007] defining a probability distribution function for each external variable;

[0008] performing Monte Carlo simulation based on the multiple regression relationship model, for each iteration, randomly selecting a value from the probability distribution of each external variable, substituting the selected external variable value into the multiple regression relationship model, and calculating the corresponding power consumption prediction value;

[0009] cumulatively storing the power consumption prediction value obtained in each iteration to form a simulation result database;

[0010] According to the simulation result database, identifying the key external variable combination and situation leading to significant changes in the power consumption of the target area.

[0011] Preferably, the external variables include temperature, humidity, precipitation, population density, urbanization rate, GDP and industrial output value of the target area.

[0012] Preferably, the step of establishing a multiple regression relationship model between power consumption and external variables based on the historical power consumption data and related external variable data comprises:

[0013] normalizing the historical power consumption data and related external variable data;

[0014] using multiple linear regression analysis, establishing a multiple regression relationship model with normalized power consumption as dependent variable and external variables as independent variable.

[0015] Preferably, the step of defining a probability distribution function for each external variable comprises:

[0016] obtaining the distribution rule of the external variable by statistical analysis on its historical data, and defining a probability distribution function suitable for describing the distribution of the external variable data according to the distribution rule.

[0017] Preferably, the step of identifying key external variable combinations and scenarios that cause significant changes in power consumption in the target area based on the simulation result database comprises:

[0018] comparing power consumption predictions corresponding to different external variable combinations, and determining key external variable combinations and scenarios that cause significant changes in power consumption in the target area according to the comparison results.

[0019] As the same inventive concept, the present application also provides a power data analysis device, comprising:

[0020] a data collection module for obtaining historical power consumption data and related external variable data of a target area;

[0021] a model establishment module for establishing a multiple regression relationship model between power consumption and external variables based on the historical power consumption data and related external variable data;

[0022] a distribution definition module for defining a probability distribution function for each external variable;

[0023] a prediction module for performing Monte Carlo simulation based on the multiple regression relationship model, for each iteration, randomly drawing a value from the probability distribution of each external variable, substituting the drawn external variable value into the multiple regression relationship model, and calculating the corresponding power consumption prediction value;

[0024] a database module for cumulatively storing power consumption prediction values obtained in each iteration to form a simulation result database;

[0025] a result output module for identifying key external variable combinations and scenarios that cause significant changes in power consumption in the target area based on the simulation result database.

[0026] Preferably, the external variables include temperature, humidity, precipitation, population density, urbanization rate, GDP and industrial output value of the target region.

[0027] Preferably, the model establishing module is configured to:

[0028] normalizing the historical power consumption data and the related external variable data;

[0029] establishing a multiple regression relationship model by using multiple linear regression analysis, taking the normalized power consumption as the dependent variable and the external variables as the independent variables.

[0030] Preferably, the distribution defining module is configured to:

[0031] defining a probability distribution function suitable for describing the distribution of the external variable data by statistically analyzing the historical data of the external variable to obtain the distribution rule thereof.

[0032] Preferably, the result output module is configured to:

[0033] comparing the power consumption predictions corresponding to different combinations of external variables, and determining the key combination of external variables and the situation causing significant changes in the power consumption of the target region according to the comparison result.

[0034] The present application has the following beneficial effects:

[0035] Traditional power consumption prediction methods often fail to fully consider the influence of external environmental factors on power consumption, resulting in large errors in the prediction results. The present application can more accurately predict power consumption by establishing a multiple regression relationship model between power consumption and external variables and introducing Monte Carlo simulation.

[0036] In a complex power system, multiple external variables may act on power consumption at the same time, and the interaction between different variables may cause significant changes in power consumption. The present application can effectively identify the key combination of external variables causing significant changes in power consumption by simulating the situation of different combinations of external variables, thereby providing decision support for the optimal dispatching of the power system. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0038] Figure 1 A flowchart of a power data analysis method in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The detailed description of the drawings is intended as an illustration of the current embodiments of the application, and is not intended to represent the only form in which the present application can be practiced. It is understood that the functions can be performed by different embodiments and that similar or equivalent functions can be performed by similar digital or analog components.

[0040] Referring to Figure 1 The embodiments of the present application provide a power data analysis method, comprising the following steps:

[0041] Step S10, obtaining historical power consumption data and related external variable data of a target region.

[0042] Specifically, the target region can be a city, and the related external variable data can be data that can have a relationship with the power consumption of the target region, such as weather conditions, population flow, etc.

[0043] Step S20, establishing a multiple regression relationship model between power consumption and external variables according to the historical power consumption data and the related external variable data.

[0044] Specifically, the multiple regression relationship model can be expressed as:

[0045] text{power consumption} = beta_0 + beta_1 * text{variable 1} + beta_2 * text{variable 2} +... + beta_n * text{variable n} + epsilon;

[0046] Where beta_0 is the intercept term, beta_1, beta_2,..., beta_n are the regression coefficients of each external variable, and epsilon is the error term.

[0047] Step S30, defining a probability distribution function for each external variable.

[0048] Step S40, performing Monte Carlo simulation based on the multiple regression relationship model, for each iteration, randomly sampling a value from the probability distribution of each external variable, substituting the sampled external variable value into the multiple regression relationship model, and calculating the corresponding power consumption prediction value.

[0049] Specifically, Monte Carlo simulation is a numerical calculation method based on probability and statistics theory, which simulates the probability distribution of one or more random variables through random sampling to estimate the possible results. In power data analysis, Monte Carlo simulation can be used to predict power consumption under the influence of different external variables.

[0050] At each iteration of the Monte Carlo simulation, we need to generate a random value for each external variable, which is drawn from the probability distribution function defined earlier (step S30). For example, if an external variable follows a normal distribution, we would randomly draw a value from that normal distribution.

[0051] The drawn external variable values are plugged into the multiple regression relationship model. This means we use these randomly generated values as inputs to the model to calculate the corresponding power consumption prediction.

[0052] Through the regression model, we obtain a prediction of power consumption. This process is repeated at each iteration, using different randomly drawn external variable values.

[0053] The specific steps are as follows:

[0054] Start the iteration, set the number of iterations (for example, 1000 or more, depending on the required accuracy and computing resources);

[0055] In each iteration, perform the following operations for each external variable:

[0056] Randomly draw a value according to the probability distribution function of that external variable;

[0057] Plug all drawn external variable values into the multiple regression model;

[0058] Calculate the model output, i.e. the prediction of power consumption;

[0059] Record the prediction value of this iteration;

[0060] Repeat the above process until all iterations are completed;

[0061] Finally, through a large number of iterations, we can obtain a distribution of prediction values, which helps us understand the possible range and probability distribution of power consumption under different combinations of external variables.

[0062] Step S50, accumulate and store the power consumption prediction values obtained at each iteration to form a simulation result database.

[0063] Specifically, in each iteration of the Monte Carlo simulation, a predicted value of electricity consumption is generated; these predicted values are possible outcomes of random variables under different scenarios; to analyze these outcomes, they need to be stored; the simulation results database should have a clear structure to facilitate data storage and retrieval; the database contains the following fields: iteration number, external variable values for each iteration, corresponding electricity consumption prediction, etc.; after each iteration is completed, the iteration number, extracted external variable values, and calculated electricity consumption prediction are stored as a record in the database; this process is repeated until all iterations are completed; the database can be a relational database (such as MySQL, PostgreSQL) or a non-relational database (such as MongoDB, Cassandra), the specific choice depends on the data volume, query requirements and system environment.

[0064] The specific operation steps are as follows:

[0065] Create an empty database or data table to store simulation results.

[0066] After each Monte Carlo simulation iteration, insert the following information as a record into the database: iteration identifier (e.g., iteration number or unique identifier), extracted value of each external variable in this iteration, calculated electricity consumption prediction in this iteration;

[0067] Ensure that the database can handle a large number of insert operations and perform performance optimization when necessary to avoid bottlenecks in data storage processes.

[0068] After all iterations are completed, the database will contain a complete set of simulation results, which can be used for further analysis.

[0069] In this way, the simulation results database becomes a valuable data resource, not only containing a large amount of prediction data, but also retaining the context information (i.e., specific values of external variables) of each prediction. This allows analysts to conduct in-depth data mining, such as identifying potential patterns of electricity consumption, assessing risks, predicting extreme situations, etc.

[0070] Step S60, according to the simulation results database, identify the key external variable combination and scenario that causes significant changes in electricity consumption in the target area.

[0071] In particular, step S60 is the analysis phase in the electricity data analysis method, which aims to extract valuable information from the simulation results database to identify which combinations of external variables and contexts lead to significant changes in electricity consumption in the target region. Interpretation of the identified key external variable combinations and contexts, understanding how they affect electricity consumption, can combine these findings with actual situations such as seasonal changes, market trends, policy impacts, etc. to provide deeper insights. The analysis results are organized into reports and key findings are displayed through visualization tools such as charts, heat maps, scatter plots, etc. to facilitate understanding by decision makers and stakeholders.

[0072] Through step S60, electricity companies and policymakers can better understand the impact of external factors on electricity consumption, so as to take appropriate measures to optimize the allocation of electricity resources, improve the efficiency and stability of the power grid, and respond to possible electricity demand peaks or troughs.

[0073] Further, the external variables include the temperature, humidity, precipitation, population density, urbanization rate, GDP and industrial output value of the target region.

[0074] In particular, in the electricity data analysis method, considering external variables is crucial to improve prediction accuracy, and the following describes how the mentioned external variables are further refined and applied in step S60.

[0075] Temperature: Analyze the impact of temperature changes on electricity consumption, especially in extreme temperature conditions (such as high or low temperatures), identify the nonlinear relationship between temperature and electricity consumption, such as the use of air conditioning and heating equipment.

[0076] Humidity: Examine the potential impact of humidity on electricity consumption, especially in high humidity environments on air conditioning energy consumption, analyze the interaction between humidity and other variables, such as increased electricity consumption under high temperature and high humidity conditions.

[0077] Precipitation: Study the short-term and long-term effects of precipitation on electricity consumption, for example, the cooling effect of rainfall may reduce air conditioning use, analyze the relationship between precipitation and hydropower generation.

[0078] Population density: Explore the direct impact of population density on electricity consumption, typically higher population density areas have higher electricity demand, analyze the long-term impact of population density trends on electricity consumption.

[0079] Urbanization rate: Examine the impact of urbanization on electricity consumption patterns, typically higher urbanization rates are associated with increased electricity demand, analyze the relationship between urbanization rates and electricity infrastructure investment and energy efficiency improvements.

[0080] GDP: Study the correlation between GDP growth and electricity consumption, as GDP growth often leads to increased electricity demand. Analyze the relationship between the contribution of different industries to GDP and electricity consumption.

[0081] Industrial output: Evaluate the impact of industrial output on electricity consumption, particularly for heavy industries and high-energy-consuming sectors. Analyze the short-term and long-term effects of changes in industrial output on electricity consumption.

[0082] In step S60, the analysis of these external variables can include the following aspects:

[0083] Variable importance ranking: Determine which external variables have the most significant impact on electricity consumption.

[0084] Scenario modeling: Construct different combinations of external variables and simulate electricity consumption under these scenarios.

[0085] Key scenario identification: Identify key scenarios that lead to significant changes in electricity consumption by comparing the predicted values under different scenarios.

[0086] Risk analysis: Assess the impact of specific external variable combinations on the electricity supply, such as extreme weather events or economic fluctuations on the power system.

[0087] Through these analyses, we can better understand how external variables individually or collectively affect electricity consumption and provide scientific basis for the planning, operation, and risk management of the power system.

[0088] Further, the step S20 includes:

[0089] Step S201, normalizing the historical electricity consumption data and related external variable data;

[0090] Specifically, normalization is an important step in data processing, aiming to scale data to a small specific range, usually [0, 1] or [-1, 1], to facilitate comparison and calculation.

[0091] Here are the specific steps for normalization:

[0092] Calculate the maximum and minimum values: For each external variable and electricity consumption data, calculate the maximum and minimum values in its historical data.

[0093] Apply normalization formula: Use the following formula to normalize the data:

[0094] For 0-1 normalization: text{normalized value} = {text{original value} - text{minimum value}} / {text{maximum value} - text{minimum value}};

[0095] For normalization from -1 to 1: normalized value = 2 * (original value - minimum value) / (maximum value - minimum value) - 1;

[0096] Ensure all data undergo the same normalization process to maintain consistency in multiple regression analysis.

[0097] Step S202: Using multiple linear regression analysis, normalized electricity consumption is used as the dependent variable and external variables are used as independent variables to establish a multiple regression relationship model.

[0098] Specifically, multiple linear regression is a statistical technique used to model the linear relationship between a dependent variable (electricity consumption in this case) and multiple independent variables (external variables).

[0099] The following are the steps to build a model:

[0100] Choose the model type: Determine whether to use a multiple linear regression model to describe the relationship between electricity consumption and external variables.

[0101] Define the dependent and independent variables: use the normalized electricity consumption data as the dependent variable (Y), and use the normalized external variable data (temperature, humidity, precipitation, population density, urbanization rate, GDP and industrial output) as the independent variables (X1,X2,...,Xn).

[0102] Fitting the model: Use least squares or other optimization algorithms to estimate regression coefficients, which represent the relative impact of each external variable on power consumption.

[0103] Model validation: The accuracy, stability, and reliability of the model are verified through methods such as cross-validation and residual analysis.

[0104] Model output: The resulting multiple regression model typically has the following form:

[0105] Y=beta_0+beta_1X_1+beta_2X_2+...+beta_nX_n+ε;

[0106] Where Y is the predicted power consumption, X1, X2, ..., Xn are external variables, β0 is the intercept, β1, β2, ..., βn are regression coefficients, and ε is the error term.

[0107] These steps allow us to build a multiple regression model for predicting electricity consumption, which takes into account the combined effects of multiple external variables.

[0108] Further, step S30 includes:

[0109] The distribution rule of the external variable is obtained by statistical analysis of the historical data of the external variable, and a probability distribution function suitable for describing the data distribution of the external variable is defined according to the distribution rule.

[0110] Specifically, descriptive statistical analysis is performed on each external variable, including calculating mean, median, standard deviation, minimum value, maximum value, skewness and kurtosis, etc. By drawing histograms, density curves, box plots, etc., the distribution characteristics of the data are observed, such as whether it is symmetric, whether there are outliers, the shape of the distribution, etc. Based on the descriptive statistics and distribution characteristics, determine the most suitable distribution type for each external variable. Common distribution types include normal distribution, lognormal distribution, uniform distribution, exponential distribution, Weibull distribution, etc. If the data conforms to a certain specific distribution, the parameters of the distribution need to be estimated, such as the mean and standard deviation of the normal distribution.

[0111] According to the determined distribution type and parameters, define the probability distribution function of each external variable. The probability distribution function can be a probability density function (PDF) or a cumulative distribution function (CDF).

[0112] Probability density function (PDF): describes the probability density of a random variable near a certain value.

[0113] Cumulative distribution function (CDF): describes the probability that a random variable is less than or equal to a certain value.

[0114] The following is an example of defining a probability distribution function:

[0115] For normal distribution: If the data is normally distributed, its probability density function is:

[0116]

[0117] Where μ is the mean and σ is the standard deviation.

[0118] For other distributions: According to the determined distribution type, use the corresponding formula to define the PDF or CDF.

[0119] Through these steps, a probability distribution function can be defined for each external variable. These functions will be used in Monte Carlo simulation to randomly generate values of external variables, simulating different scenarios. This helps to more accurately predict changes in power consumption under different external conditions.

[0120] Further, according to the simulation result database, identify the key combination of external variables and scenarios that cause significant changes in power consumption in the target area, including:

[0121] Compare the electricity consumption predictions corresponding to different external variable combinations, and determine the key external variable combinations and scenarios that lead to significant changes in electricity consumption in the target area based on the comparison results.

[0122] Specifically, in step S60, identifying the key external variable combinations and scenarios that lead to significant changes in electricity consumption in the target area is an analysis process that involves in-depth mining and comparison of the simulation result database. The following is a detailed explanation of this step:

[0123] Compare the electricity consumption predictions corresponding to different external variable combinations: Extract the electricity consumption prediction values under different external variable combinations from the simulation result database. These prediction values are obtained through Monte Carlo simulation in step S40. Compare the prediction results of different external variable combinations. This can be achieved by calculating various statistical indicators (such as mean, median, standard deviation, etc.), or by visualizing tools (such as scatter plots, heat maps, etc.) to visually display.

[0124] Determine the key external variable combinations and scenarios: Perform significance tests such as t-test or ANOVA on the electricity consumption prediction values of each external variable combination to determine which combinations have a significant impact on electricity consumption. Analyze the differences in electricity consumption prediction values between different combinations to find those that lead to significant increases or decreases in electricity consumption.

[0125] Scenario identification: Define the variable combinations with significant impact as "key scenarios", which may include specific weather conditions (such as high temperature and humidity), economic activities (such as significant growth in industrial output), or other external events (such as temporary population density increase caused by large-scale activities).

[0126] The following is an example:

[0127] Step 1: Filter the high and low value intervals of electricity consumption prediction values from the database;

[0128] Step 2: For each high and low value interval, view the corresponding external variable combination;

[0129] Step 3: Analyze the common characteristics of these combinations and identify which changes in external variables are associated with significant changes in electricity consumption;

[0130] Step 4: Determine the scenarios corresponding to these key external variable combinations, for example, "during the summer high temperature period, when the temperature exceeds 30℃ and the humidity exceeds 70%, the electricity consumption increases significantly";

[0131] Step 5: Verify the universality and reproducibility of these key scenarios to ensure they are not just individual anomalies.

[0132] Through this process, the combination of external variables and the situation that have a significant impact on power consumption can be identified, thereby providing a scientific basis for the planning, scheduling and risk management of the power system.

[0133] Another embodiment of the present application also provides a power data analysis device, comprising:

[0134] a data collection module configured to obtain historical power consumption data and related external variable data of a target region;

[0135] a model establishment module configured to establish a multiple regression relationship model between power consumption and external variables based on the historical power consumption data and related external variable data;

[0136] a distribution definition module configured to define a probability distribution function for each external variable;

[0137] a prediction module configured to perform Monte Carlo simulation based on the multiple regression relationship model, for each iteration, randomly select a value from the probability distribution of each external variable, substitute the selected external variable value into the multiple regression relationship model, and calculate a corresponding power consumption prediction value;

[0138] a database module configured to accumulate and store the power consumption prediction value obtained in each iteration to form a simulation result database;

[0139] a result output module configured to identify, based on the simulation result database, a combination of key external variables and a situation that cause significant changes in power consumption of the target region.

[0140] Further, the external variables include temperature, humidity, precipitation, population density, urbanization rate, GDP and industrial output value of the target region.

[0141] Further, the model establishment module is configured to:

[0142] normalize the historical power consumption data and related external variable data;

[0143] use multiple linear regression analysis to establish a multiple regression relationship model, with the normalized power consumption as the dependent variable and the external variables as the independent variables.

[0144] Further, the distribution definition module is configured to:

[0145] obtain the distribution rule of the external variable by statistical analysis of its historical data, and define a probability distribution function suitable for describing the distribution of the external variable data based on the distribution rule.

[0146] Further, the result output module is configured to:

[0147] The power consumption predictions corresponding to different combinations of external variables are compared, and a key combination of external variables and a scenario that leads to a significant change in power consumption in the target area is determined according to the comparison result.

[0148] The device of the present embodiment corresponds to the method of the above embodiment, and thus, the contents not described in detail in the device of the present embodiment can be obtained by referring to the contents of the method of the above embodiment, which will not be described herein.

[0149] The above has described the embodiments of the present application, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, practical application, or technical improvement in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A power data analysis method, characterized in that, include: Obtain historical electricity consumption data and relevant external variable data for the target region; A multiple regression model for the relationship between electricity consumption and external variables is established based on the historical electricity consumption data and relevant external variable data. Define a probability distribution function for each external variable; Monte Carlo simulation is performed based on the multivariate regression model. For each iteration, a value is randomly selected from the probability distribution of each external variable, and the selected external variable value is substituted into the multivariate regression model to calculate the corresponding predicted power consumption value. The predicted power consumption values ​​obtained from each iteration are accumulated and stored to form a simulation results database; Based on the simulation results database, key combinations of external variables and scenarios that lead to significant changes in electricity consumption in the target region are identified.

2. The method according to claim 1, characterized in that, The external variables include the target region's temperature, humidity, precipitation, population density, urbanization rate, GDP, and industrial output.

3. The method according to claim 2, characterized in that, The step of establishing a multiple regression model between electricity consumption and external variables based on the historical electricity consumption data and relevant external variable data includes: The historical power consumption data and related external variable data are normalized; Using multiple linear regression analysis, normalized electricity consumption was used as the dependent variable and external variables were used as independent variables to establish a multiple regression model.

4. The method according to claim 3, characterized in that, The definition of a probability distribution function for each external variable includes: By statistically analyzing the historical data of external variables, we can obtain their distribution patterns and then define a probability distribution function that describes the data distribution of the external variable based on these patterns.

5. The method according to claim 4, characterized in that, The step of identifying key combinations of external variables and scenarios that lead to significant changes in electricity consumption in the target region based on the simulation results database includes: Compare the electricity consumption forecasts corresponding to different combinations of external variables, and determine the key combinations of external variables and scenarios that lead to significant changes in electricity consumption in the target region based on the comparison results.

6. A power data analysis device, characterized in that, include: The data collection module is used to acquire historical electricity consumption data and related external variable data for the target area; The model building module is used to build a multiple regression model between electricity consumption and external variables based on the historical electricity consumption data and relevant external variable data. The distribution definition module is used to define the probability distribution function for each external variable; The prediction module is used to perform Monte Carlo simulation based on the multiple regression relationship model. For each iteration, a value is randomly selected from the probability distribution of each external variable, and the selected external variable value is substituted into the multiple regression relationship model to calculate the corresponding predicted power consumption value. The database module is used to accumulate and store the predicted power consumption values ​​obtained from each iteration, forming a simulation results database; The results output module is used to identify key combinations of external variables and scenarios that lead to significant changes in power consumption in the target area, based on the simulation results database.

7. The apparatus according to claim 6, characterized in that, The external variables include the target region's temperature, humidity, precipitation, population density, urbanization rate, GDP, and industrial output.

8. The apparatus according to claim 7, characterized in that, The model building module is used for: The historical power consumption data and related external variable data are normalized; Using multiple linear regression analysis, normalized electricity consumption was used as the dependent variable and external variables were used as independent variables to establish a multiple regression model.

9. The apparatus according to claim 8, characterized in that, The distribution definition module is used for: By statistically analyzing the historical data of external variables, we can obtain their distribution patterns and then define a probability distribution function that describes the data distribution of the external variable based on these patterns.

10. The apparatus according to claim 9, characterized in that, The result output module is used for: Compare the electricity consumption forecasts corresponding to different combinations of external variables, and determine the key combinations of external variables and scenarios that lead to significant changes in electricity consumption in the target region based on the comparison results.

Images