Power demand prediction method based on time sequence and external environment factors

Abstract

The invention discloses a power demand prediction method based on time sequence and external environment factors, relates to the technical field of data processing and prediction, and solves the problem that power potential cannot be systematically evaluated due to the fact that no system performs data analysis and prediction on a power market in the prior art. Customer basic information, business expansion information, power consumption behaviors and external environment factors are obtained, then a user business expansion influence power consumption demand multi-factor analysis model is constructed according to business expansion business subdivision, and a user business expansion influence power consumption demand multi-factor analysis model is established by combining the industry prosperity, the electric quantity change rate in the power behaviors, the capacity change amount in the customer basic information and other multi-dimensional information. According to the method, a power demand coefficient of a comprehensive evaluation property is obtained, then an ARIMA model is adopted for fitting prediction of the power demand coefficient of each business expansion business type in the future, prediction of the electric quantity potential of cities, industries and enterprises is realized, and a more accurate decision basis is provided for power industry management and enterprise operation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and prediction, and in particular to a method for predicting power demand based on time series and external environmental factors. Background Art

[0002] Against the backdrop of the country's rapid economic development, the balance between demand and supply in the electricity market and the stability and security of the power system are facing more stringent requirements. Grid companies must scientifically use power data to conduct in-depth analysis of power demand and tap into power potential so that they can perceive changes and development trends in power demand in advance. This is an urgent and complex task for grid companies. They need to use precise data-driven methods to conduct detailed analysis of power demand and predict future power consumption patterns, so as to better adapt to changes in power demand brought about by economic development. This forward-looking analytical capability is crucial for grid companies. It can not only help companies optimize the allocation of power resources and improve the efficiency and reliability of power supply, but also ensure that the power system can operate stably in the face of growing power demand to meet the needs of social and economic development.

[0003] The current application of power data and the mining of power potential have the following problems: First, the system data is relatively scattered and contains abnormal noise data, and no scientific means are used to clean the data; second, the analysis is relatively simple and one-sided, lacks a systematic evaluation method, and is limited to internal data, without integrating external influencing factors; third, there is no scientific and reasonable power potential model, multi-dimensional analysis of market confidence, and no systematic evaluation of the power potential of new capacity in various industries and cities.

[0004] In view of this, a power demand forecasting method based on time series and external environmental factors is needed. Summary of the invention

[0005] In view of the problem that there is no systematic data analysis and prediction of the power market in the prior art, which leads to the inability to systematically evaluate the power potential, the present invention provides a power demand prediction method based on time series and external environmental factors, which can integrate the internal data such as the basic customer information, business expansion registration information, and power consumption behavior of the power grid enterprise and the external environmental factor data, introduce the concept of business expansion impact life cycle, use data mining technology, construct a power demand potential model, realize the identification of power demand and development trends, support power supply and resource allocation optimization, provide decision-making basis for the planning and construction of the power system, and promote the steady development of the economy. The specific technical scheme is as follows:

[0006] A method for predicting power demand based on time series and external environmental factors comprises the following steps:

[0007] Obtain basic customer information, business expansion registration information, electricity usage behavior and external environmental factors;

[0008] According to the business segmentation of business expansion, a multi-factor analysis model of the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellations is constructed as follows:

[0009]

[0010] Among them, Q represents the electricity demand coefficient of the industry's new installation, capacity increase, capacity reduction, or user business expansion during the life cycle; x represents the industry's prosperity in the external environmental factors, κ 1 Represents the weight coefficient of industry prosperity; i represents the industry prosperity of user i’s electricity consumption behavior, κ 2 The weight coefficient representing the rate of change of electric quantity; z i represents the change in electricity consumption per unit capacity in the electricity consumption behavior of user i, κ 3 The weight coefficient representing the amount of electricity change caused by unit capacity; ΔC i represents the capacity change in the basic information of user i, κ 4 The weight coefficient representing the capacity change.

[0011] Preferably, the calculation formula for the industry prosperity x in the external environmental factors is as follows:

[0012]

[0013] Among them, M is the total number of months that have passed in a year up to the statistical time, and R 1m is the industry electricity consumption in the mth month of the current year, R 2m It is the industry electricity consumption in the mth month of the previous year.

[0014] Preferably, the rate of change of electricity consumption in the electricity consumption behavior of user i is i The calculation is as follows:

[0015]

[0016] Among them, R 业扩后 The power consumption after business expansion, R 业扩前 is the power consumption before business expansion, Δt 业扩 The time it takes for a business expansion to be completed from inception to completion.

[0017] Preferably, the amount of electricity change z caused by the unit capacity in the electricity consumption behavior of user i i It is the ratio of the power consumption to the capacity change when the business expansion impact cycle reaches stability when the industry to which user i belongs handles the same business expansion business, expressed as follows:

[0018]

[0019] Among them, R 业扩后 The power consumption after business expansion, C 业扩后 is the capacity after business expansion, C 业扩前 This is the capacity before business expansion.

[0020] Preferably, the capacity change ΔC in the basic customer information of user i i It is the capacity change that an enterprise applies for when expanding its business.

[0021] Preferably, in constructing the multi-factor prediction model for the impact of business expansion on electricity demand of new installation, capacity increase, capacity reduction, and account cancellation users in the next month, the influence factor of extreme weather is added, and the calculation formula is as follows:

[0022]

[0023] Here, ∝ represents the temperature of the external environment.

[0024] Preferably, the method further comprises the following steps:

[0025] Set an observation period and performance period to collect data from users who have applied for business expansion services, including power consumption, capacity and temperature at different times;

[0026] Capture the electricity consumption and capacity before and after different business expansion types, calculate the electricity demand during the life cycle of new installation, capacity increase, capacity reduction or account cancellation business expansion based on the multi-factor analysis model of business expansion of new installation, capacity increase, capacity reduction or account cancellation business users, and obtain the electricity demand coefficient of each business expansion type in each month of the cycle;

[0027] Based on the electricity demand coefficient of each business expansion type in each month within the cycle, the ARIMA model is used to fit and predict the electricity demand coefficient of each business expansion type in the future.

[0028] Preferably, fitting and predicting the power demand coefficient of each business expansion service type at a future moment using the ARIMA model includes the following steps:

[0029] Determine the ARIMA model parameters: Draw the autocorrelation function and partial autocorrelation function graphs to determine the parameters of the ARIMA model, namely the autoregressive term p, the difference order d, and the moving average term q; use the grid search method to traverse different combinations of p, d, and q to find the optimal model parameters;

[0030] Model building and training: Define the ARIMA model based on the determined parameters; fit the model using the training data set;

[0031] Model evaluation: Check whether the residual is white noise to evaluate the model fitting effect and calculate the prediction error;

[0032] Model prediction: Use the fitted model to predict future data and obtain the electricity demand coefficient for each type of business expansion service at future moments.

[0033] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the intelligent detection construction method as described above.

[0034] A processor is used to run a program, wherein the program executes the intelligent detection construction method as described above when running.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. The present invention obtains basic customer information, business expansion application information, electricity consumption behavior and external environmental factors, and then constructs a multi-factor analysis model of the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellation services, based on the business expansion business segmentation. Then, combined with multi-dimensional information such as industry prosperity, the rate of change of electricity in electricity behavior, the amount of electricity change brought about by unit capacity in electricity behavior, and the amount of capacity change in basic customer information, a comprehensive evaluation of electricity demand coefficient is obtained, which further reflects the changes in electricity demand under the influence of business expansion for new installations, capacity increases, capacity reductions, and account cancellation services. Pushing these quantitative data to the marketing business system can monitor the electricity potential of cities, industries, and enterprises, and provide more accurate decision-making basis for power industry management and business operations.

[0037] 2. The present invention also considers the influence of extreme factors on the electricity demand coefficient in the process of constructing a multi-factor analysis model of the impact of business expansion on electricity demand of new installations, capacity increases, capacity reductions, and account cancellation services according to the business expansion business segmentation. In addition to considering the influencing factors such as industry prosperity, the rate of change of electricity volume in electricity behavior, the change in electricity volume brought by unit capacity in electricity behavior, and the capacity change in customer basic information, it also considers the influence of extreme factors on the electricity demand coefficient, further broadens the influence dimension, and makes the calculation of the electricity demand coefficient more accurate.

[0038] 3. The present invention also sets an observation period and a performance period, calculates the electricity demand coefficient based on the collected historical data, and then uses the ARIMA model to fit and predict the electricity demand coefficient of each type of business expansion service at future moments, thereby realizing the prediction of the electricity potential of cities, industries, and enterprises, and providing more accurate decision-making basis for power industry management and business operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0040] Figure 1 is a flow chart of the method of the present invention;

[0041] Figure 2 The present invention is a flowchart of the steps of fitting and predicting the ARIMA model. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0044] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0045] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0046] In one embodiment of the present invention, a method for predicting electricity demand based on time series and external environmental factors is provided. The method is based on the business expansion power consumption data and external environmental factor data in the marketing system and the collection system, introduces the business expansion impact life cycle theory, and constructs a multivariate regression model within the business expansion impact life cycle to predict and perceive the electricity demand and development trend of different cities and industries in advance.

[0047] like Figure 1 As shown, the following steps are included:

[0048] Step 1: Data acquisition: Extract the power transmission data and power consumption data after power transmission for new high-voltage installation, capacity increase, account cancellation, suspension, capacity reduction, and suspension and restoration of business expansion from 2016 to date from the marketing system and collection system, obtain weather data such as temperature from the production management system, and obtain economic indicator data from external channels;

[0049] Step 2: Data cleaning and derivation, including:

[0050] (1) Eliminate data that is obviously unreasonable in terms of business. Eliminate data that is obviously unreasonable if the power connection capacity or application capacity is 0.

[0051] (2) Identify and eliminate noise data. For example, due to accidental factors such as the epidemic, electricity demand has fluctuated significantly, which needs to be eliminated and corrected. Specifically: analyze the monthly electricity demand trends of various industries, use the Grubbs model to identify abnormal values ​​of electricity demand, and use the moving average sequence algorithm to correct the anomalies.

[0052] (3) Seasonal adjustment by STL decomposition: Affected by holidays, temperature, production cycle, etc., the electricity demand of various industries shows seasonal trend changes. Therefore, the STL method is used to decompose the monthly electricity demand data into long-term periodic trend, season, and residual items to obtain electricity demand data that excludes seasonal influences. The specific method is as follows: According to the time series characteristics of electricity demand in various industries, the multiplication decomposition method is used to extract the sequence trend and periodic items and eliminate the seasonal items. Since STL provides a method for processing additive decomposition, in order to obtain multiplication decomposition: first take the logarithm of the electricity demand data, then perform a reverse transformation on each component, perform a Box-Cox transformation on the data with λ=0 to obtain multiplication decomposition, and finally eliminate the seasonal item and residual item, retain the trend and periodic item, that is, obtain the seasonally adjusted electricity demand time series, which more accurately reflects the basic development trend of electricity demand.

[0053] (4) Extraction of information on the life cycle of business expansion: There is a strong correlation between the change in user electricity demand after power supply and the change in capacity. After the business expansion service is processed, the user's electricity demand will first fluctuate for a period of time before stabilizing. It is necessary to identify the time it takes for the change in electricity demand to stabilize after the business expansion service is processed and the change in electricity volume caused by the change in unit capacity, in order to prepare for the subsequent accurate prediction of changes in electricity demand caused by capacity changes.

[0054] The specific approach is as follows: citing the life cycle theory, when the electricity demand reaches a stable stage, the impact of business expansion has reached a mature stage. The trend of electricity changes in this process presents an S-shaped curve. The logistic regression model is used to fit the trend of electricity changes. The analysis obtains the time required for the electricity demand to reach stability after the enterprise's industry handles similar business expansion businesses (new installation, capacity increase, capacity reduction, and account cancellation), the stable electricity value affected by the business expansion, and the rate of change of electricity during the period when the stable electricity consumption state is not reached.

[0055] (5) Index normalization: Enterprise electricity demand is affected by factors such as temperature, economic conditions, and the Spring Festival holiday. The dimensional differences between various influencing indicators are large. The deviation normalization method is used to eliminate the dimensional influence between indicators.

[0056] Step 3: According to the business segmentation of business expansion, a multi-factor analysis model of the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellations is constructed, as follows:

[0057]

[0058] Among them, Q represents the electricity demand coefficient during the life cycle of new installations, capacity increases, capacity decreases, or user business expansions;

[0059] x represents the industry prosperity in the external environment factors, which is the comparison of the electricity consumption of the industry to which the enterprise belongs this year and the same period last year. The more prosperous the industry, the greater the impact of the enterprise's business expansion on electricity consumption next month, κ 1 The weight coefficient representing the industry's prosperity; the calculation formula is as follows:

[0060]

[0061] Among them, M is the total number of months that have passed in a year up to the statistical time, and R 1m is the industry electricity consumption in the mth month of the current year, R 2m It is the industry electricity consumption in the mth month of the previous year.

[0062] y i Represents the industry prosperity in the electricity consumption behavior of user i. By studying the life cycle of the industry expansion impact of the enterprise, the production electricity consumption curve of the industry after handling the same type of business expansion business is obtained. The larger the value, the greater the impact of the enterprise's business expansion business on the electricity consumption in the next month. 2 The weight coefficient representing the rate of change of electric quantity; the calculation is as follows:

[0063]

[0064] Among them, R 业扩后 The power consumption after business expansion, R 业扩前 is the power consumption before business expansion, Δt 业扩 The time it takes for a business expansion to be completed from inception to completion.

[0065] z i Represents the change in electricity volume caused by unit capacity in the electricity consumption behavior of user i. It is the ratio of electricity volume to capacity change when the expansion impact cycle reaches stability when the enterprise's industry handles the same type of expansion business. The larger the value, the greater the impact of the enterprise's expansion business on electricity volume. 3 The weight coefficient representing the amount of electricity change caused by unit capacity is expressed as follows:

[0066]

[0067] Among them, R 业扩后 The power consumption after business expansion, C 业扩后 is the capacity after business expansion, C 业扩前 This is the capacity before business expansion.

[0068] ΔC i Represents the capacity change in the basic information of user i. It is the capacity change applied for change when the enterprise handles business expansion. The larger the value, the greater the impact of the enterprise's business expansion on electricity consumption. 4 The weight coefficient representing the capacity change.

[0069] In one embodiment of the present invention, in constructing the multi-factor prediction model of the impact of business expansion on electricity demand of new installation, capacity increase, capacity reduction and account cancellation users in the next month, the influence factor of extreme weather is added, and the calculation formula is as follows:

[0070]

[0071] Here, ∝ represents the temperature of the external environment.

[0072] Step 4: Set the observation period and performance period, and collect data from users who have applied for business expansion services, including power consumption, capacity, and temperature at different times;

[0073] Step 5: Capture the power consumption and capacity before and after different business expansion types, and calculate the power demand of new installation, capacity increase, capacity reduction, or account cancellation business expansion users within the life cycle based on the multi-factor analysis model of business expansion of new installation, capacity increase, capacity reduction, and account cancellation users, and obtain the power demand coefficient of each business expansion type in each month of the cycle;

[0074] Step 6: Based on the electricity demand coefficient of each business expansion type in each month within the cycle, the ARIMA model is used to fit and predict the electricity demand coefficient of each business expansion type in the future.

[0075] Among them, fitting and predicting the electricity demand coefficient of each business expansion service type at the future moment using the ARIMA model includes the following steps:

[0076] In order to save production electricity costs, the electricity capacity applied for by enterprises will be adjusted accordingly according to the production electricity demand: if the production electricity demand is expected to increase, new installation and capacity increase will be carried out; if the production electricity demand is expected to decrease, capacity reduction, suspension and account cancellation will be carried out. Taking into account the seasonality and trend of the monthly production electricity consumption of enterprise users due to climate, changes in production demand, social and economic development and other reasons, the trend of changes in the applied electricity capacity also has the same characteristics. In order to achieve accurate prediction of the next period of electricity consumption, the ARIMA model with good short-term prediction effect and accurate capture of the trend, seasonality and random fluctuation characteristics in the time series is used for fitting and prediction.

[0077] Generally, in order to save production electricity costs, the electricity capacity applied for by enterprises will be adjusted accordingly according to production electricity demand: if the production electricity demand is expected to increase, new installations and capacity increases will be carried out; if the production electricity demand is expected to decrease, capacity reduction, suspension and account cancellation will be carried out. Taking into account the seasonality and trend of monthly production electricity consumption of enterprise users due to climate, changes in production demand, social and economic development and other reasons, the trend of changes in the applied electricity demand coefficient also has the same characteristics. In order to achieve accurate prediction of the next period's electricity consumption, the ARIMA model with good short-term prediction effect and the ability to accurately capture the characteristics of trends, seasonality and random fluctuations in time series is used for fitting and prediction. Figure 2 As shown, the specific steps are as follows:

[0078] Step 1: Stationarity test and white noise test. Use drawing or statistical test (such as ADF test) to determine whether the historical data of power consumption capacity is stationary. Non-stationary series need to be differentiated until the series is stable and meets the modeling requirements.

[0079] Step 2: Moving average or logarithmic processing. For some industries and some business types, the time series data test results are white noise data, which cannot be modeled. The original data needs to be processed by moving average or logarithmic processing to make the data relatively smooth before subsequent differential processing, testing and other steps.

[0080] Step 3: Model identification and sequence order determination. Determine the model parameters based on the trend of the historical data of power consumption: by observing the autocorrelation diagram (ACF) and partial autocorrelation diagram (PACF) of the stationary series, determine the order p (number of autoregressive terms), d (number of differences, which has been determined in the difference processing), and q (number of moving average terms) of the ARIMA model.

[0081] Step 4: Model building and residual test. Build the model, that is, fit the data trend, and use the residual to check the completeness of information extraction, and constantly adjust the model. If the residual sequence of the model is white noise, the model information has been completely extracted.

[0082] Step 5: Model prediction: Directly predict the next period of power consumption data based on the fitted model.

[0083] In summary, the present invention obtains basic customer information, business expansion application information, electricity consumption behavior and external environmental factors, and then constructs a multi-factor analysis model of the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellation services, based on the business expansion business segmentation. Then, combined with multi-dimensional information such as industry prosperity, the rate of change of electricity in electricity behavior, the amount of electricity change brought about by unit capacity in electricity behavior, and the amount of capacity change in the basic information of customers, a comprehensive evaluation of the nature of the power demand coefficient is obtained, which further reflects the changes in electricity demand under the influence of business expansion for new installations, capacity increases, capacity reductions, and account cancellation services. Pushing these quantitative data to the marketing business system can realize the monitoring of the electricity potential of cities, industries, and enterprises, and provide a more accurate decision-making basis for power industry management and business operations. Moreover, in the process of constructing a multi-factor analysis model of the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellation services, the present invention also considers the impact of extreme factors on the electricity demand coefficient, further broadens the impact dimension, and makes the calculation of the electricity demand coefficient more accurate. In addition, the present invention also sets an observation period and a performance period, calculates the electricity demand coefficient based on the collected historical data, and then uses the ARIMA model to fit and predict the electricity demand coefficient of each type of business expansion service at future moments, so as to realize the prediction of the electricity potential of cities, industries, and enterprises, and provide a more accurate decision-making basis for power industry management and business operations.

[0084] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0085] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0086] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0087] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for predicting power demand based on time series and external environmental factors, characterized in that: The following steps are involved: Obtain basic customer information, business expansion registration information, electricity usage behavior and external environmental factors; According to the business segmentation of business expansion, a multi-factor analysis model of the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellations is constructed as follows: Among them, Q represents the electricity demand coefficient of the industry's new installation, capacity increase, capacity reduction, or user business expansion during the life cycle; x represents the industry's prosperity in the external environmental factors, κ1 represents the weight coefficient of the industry's prosperity; y i represents the industry prosperity in the electricity consumption behavior of user i, κ2 represents the weight coefficient of the rate of change of electricity consumption; z i represents the change in electricity volume per unit capacity in the electricity consumption behavior of user i, and κ3 represents the weight coefficient of the change in electricity volume per unit capacity; ΔC i represents the capacity change in the basic information of user i, and κ4 represents the weight coefficient of the capacity change.

2. The method for predicting power demand based on time series and external environmental factors according to claim 1, characterized in that: The calculation formula for the industry prosperity x, which represents the external environmental factors, is as follows: Among them, M is the total number of months that have passed in a year up to the statistical time, and R 1m is the industry electricity consumption in the mth month of the current year, R 2m It is the industry electricity consumption in the mth month of the previous year.

3. The method for predicting power demand based on time series and external environmental factors according to claim 1, characterized in that: The rate of change of electricity consumption in the electricity consumption behavior of user i y i The calculation is as follows: Among them, R 业扩后 The power consumption after business expansion, R 业扩前 is the power consumption before business expansion, Δt 业扩 The time it takes for a business expansion to be completed from inception to completion.

4. The method for predicting power demand based on time series and external environmental factors according to claim 1, characterized in that: The amount of electricity change z caused by unit capacity in the electricity consumption behavior of user i i It is the ratio of the power consumption to the capacity change when the business expansion impact cycle reaches stability when the industry to which user i belongs handles the same business expansion business, expressed as follows: Among them, R 业扩后 The power consumption after business expansion, C 业扩后 is the capacity after business expansion, C 业扩前 This is the capacity before business expansion.

5. The method for predicting power demand based on time series and external environmental factors according to claim 1, characterized in that: The capacity change ΔC in the basic customer information of user i i It is the capacity change that an enterprise applies for when expanding its business.

6. A method for predicting power demand based on time series and external environmental factors according to any one of claims 1 to 5, characterized in that: In constructing the multi-factor prediction model for the impact of business expansion on electricity demand for new installations, capacity increases, capacity reductions, and account cancellations next month, the influence factor of extreme weather is added, and the calculation formula is as follows: Here, ∝ represents the temperature of the external environment.

7. The method for predicting power demand based on time series and external environmental factors according to claim 1, characterized in that: The following steps are also included: Set an observation period and performance period to collect data from users who have applied for business expansion services, including power consumption, capacity and temperature at different times; Capture the electricity consumption and capacity before and after different business expansion types, calculate the electricity demand during the life cycle of new installation, capacity increase, capacity reduction or account cancellation business expansion based on the multi-factor analysis model of business expansion of new installation, capacity increase, capacity reduction or account cancellation business users, and obtain the electricity demand coefficient of each business expansion type in each month of the cycle; Based on the electricity demand coefficient of each business expansion type in each month within the cycle, the ARIMA model is used to fit and predict the electricity demand coefficient of each business expansion type in the future.

8. The method for predicting power demand based on time series and external environmental factors according to claim 7, characterized in that: The ARIMA model is used to fit and predict the electricity demand coefficient of each business expansion service type at the future moment, including the following steps: Determine the ARIMA model parameters: Draw the autocorrelation function and partial autocorrelation function graphs to determine the parameters of the ARIMA model, namely the autoregressive term p, the difference order d, and the moving average term q; use the grid search method to traverse different combinations of p, d, and q to find the optimal model parameters; Model building and training: Define the ARIMA model based on the determined parameters; fit the model using the training data set; Model evaluation: Check whether the residual is white noise to evaluate the model fitting effect and calculate the prediction error; Model prediction: Use the fitted model to predict future data and obtain the electricity demand coefficient for each type of business expansion service at future moments.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for predicting power demand based on timing and external environmental factors as described in any one of claims 1 to 5.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the method for predicting power demand based on timing and external environmental factors as described in any one of claims 1 to 5.

Images