Industrial power consumption demand prediction method and system considering energy consumption characteristics

Abstract

The invention relates to the technical field of power consumption demand prediction, and discloses an industrial power consumption demand prediction method and system considering energy consumption characteristics, and the system comprises a data collection unit, a power consumption evaluation unit, a factor adjustment unit, and a correlation analysis unit. Rated power, operation duration, historical power consumption data and production scheduling plans of various types of production equipment in the industry are covered, a solid foundation is laid for subsequent prediction, and the actual power consumption of the industry is comprehensively reflected; the accuracy is improved through multi-link fine consideration, single-unit and overall theoretical electricity consumption is calculated in the electricity consumption demand evaluation link of the equipment, and the electricity consumption scale is determined; the time factor adjusting link analyzes a historical electricity utilization time rule, and adjusts the total amount according to date types to adapt to electricity utilization changes in different time periods; in the yield correlation analysis link, equipment and yield correlation is established, the power consumption increment is determined by combining the scheduling yield, and the influence of the yield on power consumption is accurately reflected.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity demand forecasting, and in particular to a method and system for forecasting industrial electricity demand taking energy consumption characteristics into consideration. Background Art

[0002] In today's society, with the vigorous development of various industries, energy consumption, especially electricity consumption, has become a key component of industrial operating costs. Due to differences in production processes, equipment types, and production schedules, different industries have complex and changeable electricity demand.

[0003] On the one hand, traditional electricity demand forecasting methods are often too general. Most of them are based on simple trend extrapolation based on historical electricity data, and fail to deeply analyze the actual operation of production equipment within the industry. For example, in the manufacturing industry, various types of processing equipment have different rated powers, and the operating hours will also vary from day to day due to order tasks and shift arrangements. Simply relying on past electricity consumption to estimate future demand ignores the differences at the equipment level, which can easily lead to large forecast deviations and fail to accurately meet the actual electricity planning needs of the industry.

[0004] On the other hand, time factors have a significant impact on industrial electricity consumption. The production activity of the industry is very different on weekdays, weekends, and holidays, and the electricity load fluctuates significantly. In addition, there are differences in electricity consumption characteristics during different periods of the day, such as peak, flat, and valley. For example, the chemical industry has a large increase in electricity consumption during the peak production period during the day, and the electricity consumption drops sharply during the valley period at night when some equipment is shut down. If the electricity consumption patterns of these time dimensions cannot be accurately grasped, it will be difficult for enterprises to reasonably arrange peak electricity consumption, which may cause power shortages and insufficient power supply during peak periods to affect production, and it is easy to waste electricity resources during valley periods, increasing unnecessary electricity costs.

[0005] Furthermore, as a common dynamic factor in industrial operations, changes in production are closely linked to electricity demand. When an enterprise receives an urgent order and needs to increase production, the equipment combination and operating hours involved in production will be adjusted accordingly, which will directly affect electricity demand. Previous forecasting methods rarely incorporate production correlations in detail, making it impossible to follow up and adjust electricity demand forecasts in a timely manner in scenarios where production changes occur, and cannot provide a reliable basis for enterprise production scheduling and power resource allocation, hindering efficient operation and cost control of enterprises.

[0006] In summary, in view of the many shortcomings of existing electricity demand forecasting methods in considering industrial energy consumption characteristics, there is an urgent need for a new electricity demand forecasting method and system that can comprehensively consider the status of production equipment, time factors and output correlation within the industry, so as to meet the actual needs of accurate industrial electricity management, optimize power resource allocation, and reduce electricity costs. Summary of the invention

[0007] The purpose of the present invention is to provide an industrial electricity demand forecasting method and system taking energy consumption characteristics into consideration, thereby solving the technical problems raised in the background technology.

[0008] The purpose of the present invention can be achieved through the following technical solutions: A method for predicting industrial electricity demand considering energy consumption characteristics, comprising: Step 1: Industry data collection Collect basic data in the target industry, including: rated power of various types of production equipment in the industry, daily operating hours of production equipment, historical electricity consumption data of the industry, and production scheduling plans of the industry; Step 2: Equipment power demand assessment Based on the collected basic data, calculate the theoretical daily power consumption of a single device, and summarize the theoretical daily power consumption of all devices in the industry to determine the total daily theoretical power consumption; Step 3: Time factor adjustment Step D1: Analyze the time distribution of historical electricity consumption data: Step D2: Adjust the theoretical total daily electricity consumption according to the time type of the current date: Step 4: Yield Correlation Analysis Step G1: Establish the relationship between equipment power consumption and output: Step G2: Combined with the estimated output in the production schedule, determine the power consumption increment corresponding to the output change: Step G3: Add the electricity consumption increment to the adjusted daily electricity consumption estimate to obtain the daily electricity demand forecast value.

[0009] As a further solution of the present invention: wherein the rated power of various production equipment in the industry is recorded as P i , where i represents the number of different production equipment, i=1, 2, ... n, n represents the number of different production equipment; The daily operating time of the production equipment is recorded as T i，j , j represents the date, j=1, 2, ...m, m represents the number of multiple dates in the observation period; The historical electricity consumption data recorded in the form of time series is recorded as L k , k represents the power consumption period, k=1, 2, ... p, p represents the number of power consumption periods in the specified observation period, L k represents the power consumption in the kth power consumption period; The production schedule of the industry specifies the equipment combination and expected output during different shift periods, and records the expected output as Q r，t, r represents the product line, that is, the combination of equipment involved in production, r=1, 2, ...u, u represents the number of product lines, t represents the scheduling period, t=1, 2, ...v, v represents the number of scheduling periods.

[0010] As a further solution of the present invention: the calculation method of the theoretical daily power consumption of a single device is as follows: pass:

[0011] Calculate the daily theoretical power consumption E1 of each device during the observation period i，j .

[0012] As a further solution of the present invention: the total theoretical daily electricity consumption is determined as follows: Then pass:

[0013] Calculate the theoretical total electricity consumption E2 for each date during the observation period j .

[0014] As a further solution of the present invention: in step D1, the time distribution law analysis method is as follows: The power consumption time period within the specified observation period is divided into a plurality of different types of power consumption time periods according to the pre-set time period type, and is marked as g, where g=1, 2, ... q, and q represents the number of types of different types of power consumption time periods; Select a type of electricity usage time period; Then through:

[0015] Calculate the average electricity consumption ratio R of different types of electricity consumption time periods g ; In the formula, Indicates the total electricity consumption of a type during the electricity consumption period.

[0016] As a further solution of the present invention: wherein the time period types include weekdays, weekends, holidays, and daily peak, off-peak, and valley periods.

[0017] As a further solution of the present invention: in step D2, the daily theoretical total electricity consumption is adjusted as follows: pass:

[0018] Calculate the adjusted daily electricity consumption estimate E3 for each date during the observation period j .

[0019] As a further solution of the present invention: the association relationship in step G1 is established as follows: In the production scheduling plan, select a product line; Then, the power consumption of each power-consuming device on the product line in multiple corresponding shift periods is obtained and recorded as E4 i，t ; At the same time, extract the expected output Q of the product line in multiple corresponding scheduling periods r，t ; Then pass:

[0020] Calculate the equipment power consumption coefficient C of the product line corresponding to the expected output r ; As a further solution of the present invention: in step G2, the calculation method of the power consumption increment is as follows: pass:

[0021] Calculate the increase in electricity consumption ZE caused by changes in output r，k ; As a further solution of the present invention: in step G3, the calculation formula of the daily electricity demand forecast value is as follows:

[0022] In the formula, EY j It is the daily electricity demand forecast value.

[0023] A system for predicting industrial electricity demand considering energy consumption characteristics, the system is used to implement a method for predicting industrial electricity demand considering energy consumption characteristics, the system comprising: Data collection unit, used to collect basic data in the target industry; The electricity consumption evaluation unit is used to determine the total theoretical daily electricity consumption based on the collected basic data; The factor adjustment unit is used to analyze the time distribution of historical electricity consumption data and adjust the daily theoretical total electricity consumption according to the time type of the current date: The correlation analysis unit is used to establish the correlation between equipment electricity consumption and output, and determine the electricity consumption increment corresponding to the output change based on the corresponding correlation relationship and the estimated output in the production scheduling plan, and then add the electricity consumption increment to the adjusted daily electricity consumption estimate to obtain the daily electricity demand forecast value.

[0024] Beneficial effects of the present invention: Comprehensive and practical data utilization: Through the industrial data collection steps, basic data covering various aspects of the industry's production equipment, such as rated power, daily operating hours, historical power consumption data, and production scheduling plans, is collected. Key factors such as the equipment's own attributes, actual operating conditions, past power consumption performance, and production arrangements related to industrial power consumption are fully considered, laying a comprehensive and practical foundation for subsequent accurate power demand forecasts, avoiding inaccurate forecasts due to missing or one-sided data.

[0025] Equipment power demand assessment: Based on the rich basic data collected, the daily theoretical power consumption of a single device can be calculated scientifically and reasonably, and the total daily theoretical power consumption of all equipment in the industry can be further summarized, clearly defining the theoretical scale of power consumption of the industry as a whole under normal conditions. This helps to grasp the approximate level of industrial power consumption from a basic level, provides an important reference for subsequent more detailed adjustments and analysis, and improves the basic accuracy of power demand forecasts.

[0026] Time factor adjustment: On the one hand, the time distribution pattern of historical electricity consumption data is carefully analyzed, and the electricity consumption time periods are divided into various time period types such as weekdays, weekends, holidays, and daily peak, off-peak and low-peak periods. The average electricity consumption ratio of each type of electricity consumption period is calculated to accurately capture the differences in electricity consumption under different time characteristics; on the other hand, the theoretical total daily electricity consumption is adjusted accordingly according to the time type of the current date, so that the prediction results can fully adapt to the changing characteristics of electricity demand under different time scenarios, effectively improving the accuracy and rationality of the prediction when facing the influence of time factors.

[0027] Output correlation analysis: First, establish the correlation between equipment power consumption and output. Determine the equipment power consumption coefficient by analyzing the power consumption of equipment on the product line and the expected output. Then, accurately determine the power consumption increment corresponding to the output change based on the expected output in the production schedule. Add the increment to the corresponding value to derive the final daily power demand forecast. Fully consider the direct impact of the key variable of production output on power demand, ensure that the power demand forecast under different production plans can fit the actual production situation, and further enhance the accuracy of the overall forecast.

[0028] System architecture facilitates efficient implementation: A specially designed industrial electricity demand forecasting system that takes energy consumption characteristics into consideration includes a data collection unit, an electricity consumption assessment unit, a factor adjustment unit, and a correlation analysis unit. Each unit has a clear division of labor and cooperates with each other. They are responsible for data collection in the corresponding links, determination of theoretical total electricity consumption, adjustment of time factors, and output correlation analysis, etc., which realizes efficient and orderly operation of the entire forecasting method, facilitates its implementation in actual industrial applications, improves the efficiency and quality of industrial electricity demand forecasting, and helps industries better plan electricity arrangements, rationally allocate power resources, and effectively control electricity costs.

[0029] In summary, the present invention can provide the industry with accurate, reliable and practical electricity demand forecasts by integrating multiple factors, multi-link detailed analysis and the design of supporting system architecture, which plays a positive and important role in the scientific electricity management of the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The present invention will be further described below in conjunction with the accompanying drawings.

[0031] Figure 1 The system block diagram of an industrial electricity demand forecasting system taking energy consumption characteristics into consideration according to the present invention.

[0032] Figure 2 It is a flow chart of an industrial electricity demand forecasting method taking energy consumption characteristics into consideration according to the present invention. DETAILED DESCRIPTION

[0033] 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 only 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. Example

[0034] See also Figure 1 and Figure 2 As shown, the present invention is a method for predicting industrial electricity demand taking into account energy consumption characteristics, comprising: Step 1: Industry data collection For the target industry, collect the following basic data: The rated power of various production equipment in the industry is recorded as P i , where i represents the number of different production equipment, i=1, 2, ... n, n represents the number of different production equipment, and the rated power is obtained from the equipment nameplate or product manual, and its unit is kilowatt; The daily operating time of the production equipment is recorded as T i，j, j represents the date, j=1, 2, ...m, m represents the number of multiple dates in the observation period, and the daily operation time is recorded by the operation monitoring device pre-installed on the equipment, in hours; The historical electricity consumption data of the industry is recorded in the form of time series and is denoted as L k , k represents the power consumption period, k=1, 2, ... p, p represents the number of power consumption periods in the specified observation period, L k represents the power consumption of the kth power consumption period, in kilowatt-hours, and the historical power consumption data is obtained from the electric meter records of the power department or the enterprise. In this embodiment, each hour is regarded as a power consumption period for recording the power consumption data; The production schedule of the industry specifies the equipment combination and expected output during different shift periods, and records the expected output as Q r，t , r represents the product line, that is, the combination of equipment involved in production, r=1, 2, ...u, u represents the number of product lines, t represents the shift period, t=1, 2, ...v, v represents the number of shift periods, and the unit corresponding to the expected output is determined according to the characteristics of the industrial products, such as tons or pieces; Step 2: Equipment power demand assessment Based on the collected basic data, calculate the theoretical daily power consumption of a single device, and summarize the theoretical daily power consumption of all devices in the industry to determine the total daily theoretical power consumption; The method is as follows: First pass:

[0035] Calculate the daily theoretical power consumption E1 of each device during the observation period i，j ; Then pass:

[0036] Calculate the theoretical total electricity consumption E2 for each date during the observation period j ; Step 3: Time factor adjustment Step D1: Analyze the time distribution of historical electricity consumption data: The method is as follows: The power consumption time period within the specified observation period is divided into a plurality of different types of power consumption time periods according to the pre-set time period type, and is marked as g, where g=1, 2, ... q, and q represents the number of types of different types of power consumption time periods; In this embodiment, the time period types include weekdays, weekends, holidays, and daily peak, off-peak, and valley periods; Select a type of electricity usage time period; Then through:

[0037] Calculate the average electricity consumption ratio R of different types of electricity consumption time periods g ; In the formula, It represents the total power consumption of a type in the power application period; Step D2: Adjust the total theoretical daily electricity consumption of the industry according to the time type of the current date: The method is as follows: pass:

[0038] Calculate the adjusted daily electricity consumption estimate E3 for each date during the observation period j ; Step 4: Yield Correlation Analysis Step G1: Establish the relationship between equipment power consumption and output: The method is as follows: In the production scheduling plan, select a product line; Then, the power consumption of each power-consuming device on the product line in multiple corresponding shift periods is obtained and recorded as E4 i，t ; At the same time, extract the expected output Q of the product line in multiple corresponding scheduling periods r，t ; Then pass:

[0039] Calculate the equipment power consumption coefficient C of the product line corresponding to the expected output r ; Step G2: Combined with the estimated output in the production schedule, determine the power consumption increment corresponding to the output change: The method is as follows: pass:

[0040] Calculate the increase in electricity consumption ZE caused by changes in output r，k ; Step G3: Set the power consumption increment ZE r，k The increment is added to the adjusted daily electricity consumption estimate E3 j On the above, the daily electricity demand forecast value is obtained; The formula is as follows:

[0041] In the formula, EY j It is the daily electricity demand forecast value.

[0042] This embodiment provides comprehensive and detailed information support for subsequent accurate electricity demand forecasting by collecting multi-dimensional basic data such as the rated power, daily operating hours, historical electricity consumption data of various types of production equipment in the industry, and production scheduling plans. It covers multiple aspects such as the equipment's own characteristics, actual operating conditions, past electricity consumption, and production arrangements, so that the forecast can be based on reality and fit the actual operation of the industry; based on the collected data, the daily theoretical electricity consumption of a single device and the total daily theoretical electricity consumption of all equipment can be scientifically calculated, which clarifies the theoretical electricity consumption scale of the industry under normal circumstances and helps to grasp the basic electricity consumption level; analyzing historical usage The time distribution pattern of electricity data is distinguished, different types of electricity consumption time periods are distinguished and the corresponding average electricity consumption ratio is calculated, and then the theoretical total electricity consumption is adjusted according to the time type to which the current date belongs, fully considering the impact of time factors on electricity demand, so that the prediction results are more in line with the actual changes in electricity consumption in different time scenarios; the correlation between equipment electricity consumption and output is established, and the equipment electricity consumption coefficient is determined by analyzing the equipment electricity consumption and expected output on the product line, and the electricity demand is corrected according to the expected output in the production scheduling plan, taking into account the direct correlation between production output changes and electricity demand, which improves the accuracy of electricity demand forecasts when facing different production plans. Example

[0043] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of the present embodiment is different from the first embodiment only in that the present embodiment also includes dynamic feedback adjustment, and the method is as follows: During the daily production process, the actual daily electricity consumption data is collected in real time and marked as Y j ; Then through:

[0044] Calculate the error rate W between the actual daily electricity consumption data and the corresponding daily electricity demand forecast value j ; Then the error rate W j Compare with the pre-determined error threshold WY: If W j >WY, first check the equipment operation status monitoring system to check whether there is any sudden equipment failure or shutdown; If it is found that the power-consuming equipment is shut down, the power-consuming equipment number is located, and the downtime node is obtained at the same time, and then the originally expected power demand for the remaining operating time of the equipment is calculated. At this time, this part of the power demand is calculated as 0 to correct the subsequent prediction; At the same time, communicate with the production scheduling department to confirm whether emergency production tasks have been temporarily added; If there are any urgent production tasks that are added temporarily, learn in detail about the equipment involved in the task, the output requirements, and the estimated time required, so as to re-evaluate the increase in electricity consumption; Afterwards, the affected parts will be recalculated based on the retrospective investigation results; If it is caused by equipment failure, recalculate the theoretical total power consumption of the remaining normal operating equipment in the subsequent unfinished period; And according to the method of the second step, the theoretical power consumption of a single device in the remaining period is calculated based on the remaining operating time and rated power, and then the new theoretical total power consumption of the industry in the remaining period is obtained; Then, the third step is repeated, and the time factor is adjusted according to the time type of the current remaining time period and the recalculated theoretical total electricity consumption to obtain an adjusted electricity consumption estimate.

[0045] Finally, as in step 4, changes in yield associations are considered; If the emergency production task changes the production layout, recalculate the equipment power consumption coefficient per unit of production, and then calculate the power consumption increment caused by the change in production, add it to the adjusted power consumption estimate, and get the updated daily power demand forecast value to guide the subsequent production power consumption arrangement; This embodiment collects actual power consumption data in real time during the daily production process, and compares it with the predicted value to calculate the error rate. The subsequent retrospective investigation mechanism is triggered by comparing the error rate with the preset error threshold. When a large error occurs, it can specifically investigate influencing factors such as sudden equipment failure and shutdown and temporary increase of emergency production tasks. This real-time dynamic feedback adjustment mechanism can promptly discover the reasons why the prediction is inconsistent with the actual situation, and enhance the adaptability and accuracy of the prediction method in practical applications. If it is found that the equipment is shut down due to a fault, the equipment number can be located, the shutdown time node can be obtained, the originally expected power demand can be calculated and corrected to 0, and the theoretical total power consumption of the remaining normal operating equipment in the subsequent time period can be recalculated, and then the time factor adjustment and output correlation analysis processes are repeated according to the steps of Example 1 to ensure that the subsequent prediction can still reflect the actual power demand more accurately in the case of a sudden equipment failure, thereby reducing the problem of unreasonable power arrangement caused by equipment failure; if there is a temporary emergency production task, the power increment can be re-evaluated by understanding the information related to the relevant task in detail, and the equipment power coefficient per unit output can be recalculated when necessary, so as to obtain an updated daily power demand forecast value, so that the forecast value can adapt to the changes in production layout caused by temporary production tasks, and better guide the subsequent production power arrangement, and avoid power shortage or waste due to temporary tasks. Example

[0046] As the third embodiment of the present invention, when the present application is specifically implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments mentioned above for implementation.

[0047] This embodiment combines the solutions of embodiment one and embodiment two, and combines the advantages of the comprehensive multi-factor prediction method of embodiment one and the real-time dynamic feedback adjustment mechanism of embodiment two. It can accurately predict electricity demand based on comprehensive analysis of multiple factors under normal production conditions, and can timely correct the prediction results through dynamic feedback when actual production changes such as equipment failures and temporary emergency production tasks occur, so that it can always fit the actual electricity consumption situation, and maximize the accuracy and adaptability of electricity demand prediction and its effective guidance on the arrangement of industrial production electricity consumption, and comprehensively help the industry to use electricity rationally, arrange power resources scientifically, and effectively control electricity costs.

[0048] See also Figure 1 and Figure 2 As shown, the present invention also provides an industrial electricity demand forecasting system considering energy consumption characteristics, the system is used to implement an industrial electricity demand forecasting method considering energy consumption characteristics, the system comprising: Data collection unit, used to collect basic data in the target industry; The electricity consumption evaluation unit is used to determine the total theoretical daily electricity consumption based on the collected basic data; The factor adjustment unit is used to analyze the time distribution of historical electricity consumption data and adjust the daily theoretical total electricity consumption according to the time type of the current date: The correlation analysis unit is used to establish the correlation between equipment electricity consumption and output, and determine the electricity consumption increment corresponding to the output change based on the corresponding correlation relationship and the estimated output in the production scheduling plan, and then add the electricity consumption increment to the adjusted daily electricity consumption estimate to obtain the daily electricity demand forecast value.

[0049] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0050] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting industrial electricity demand considering energy consumption characteristics, characterized in that: The following steps are involved: Step 1: Industry data collection Collect basic data in the target industry, including: rated power of various types of production equipment in the industry, daily operating hours of production equipment, historical electricity consumption data of the industry, and production scheduling plans of the industry; Step 2: Equipment power demand assessment Based on the collected basic data, calculate the theoretical daily power consumption of a single device, and summarize the theoretical daily power consumption of all devices in the industry to determine the total daily theoretical power consumption; Step 3: Time factor adjustment Step D1: Analyze the time distribution of historical electricity consumption data: Step D2: Adjust the theoretical total daily electricity consumption according to the time type of the current date: Step 4: Yield Correlation Analysis Step G1: Establish the relationship between equipment power consumption and output: Step G2: Combined with the estimated output in the production schedule, determine the power consumption increment corresponding to the output change: Step G3: Add the electricity consumption increment to the adjusted daily electricity consumption estimate to obtain the daily electricity demand forecast value.

2. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 1, characterized in that: in, The rated power of various production equipment in the industry is recorded as P i , where i represents the number of different production equipment, i=1, 2, ... n, n represents the number of different production equipment; The daily operating time of the production equipment is recorded as T i，j , j represents the date, j=1, 2, ...m, m represents the number of multiple dates in the observation period; The historical electricity consumption data recorded in the form of time series is recorded as L k , k represents the power consumption period, k=1, 2, ... p, p represents the number of power consumption periods in the specified observation period, L k represents the power consumption in the kth power consumption period; The production schedule of the industry specifies the equipment combination and expected output during different shift periods, and records the expected output as Q r，t , r represents the product line, that is, the combination of equipment involved in production, r=1, 2, ...u, u represents the number of product lines, t represents the scheduling period, t=1, 2, ...v, v represents the number of scheduling periods.

3. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 2, characterized in that: The calculation method for the theoretical daily power consumption of a single device is as follows: pass: Calculate the daily theoretical power consumption E1 of each device during the observation period i，j .

4. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 3, characterized in that: The total theoretical daily electricity consumption is determined as follows: Then pass: Calculate the theoretical total electricity consumption E2 for each date during the observation period j .

5. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 4, characterized in that: In step D1, the time distribution law analysis method is as follows: The power consumption time period within the specified observation period is divided into a plurality of different types of power consumption time periods according to the pre-set time period type, and is marked as g, where g=1, 2, ... q, and q represents the number of types of different types of power consumption time periods; Select a type of electricity usage time period; Then through: Calculate the average electricity consumption ratio R of different types of electricity consumption time periods g ; In the formula, Indicates the total power consumption of a type during the power consumption period.

6. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 5, characterized in that: In step D2, the daily theoretical total electricity consumption is adjusted as follows: pass: Calculate the adjusted daily electricity consumption estimate E3 for each date during the observation period j .

7. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 6, characterized in that: The association relationship in step G1 is established as follows: In the production scheduling plan, select a product line; Then, the power consumption of each power-consuming device on the product line in multiple corresponding shift periods is obtained and recorded as E4 i，t ; At the same time, extract the expected output Q of the product line in multiple corresponding scheduling periods r，t ; Then pass: Calculate the equipment power consumption coefficient C of the product line corresponding to the expected output r .

8. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 7, characterized in that: In step G2, the calculation method of the power consumption increment is as follows: pass: Calculate the increase in electricity consumption ZE caused by changes in output r，k .

9. The method for predicting industrial electricity demand considering energy consumption characteristics according to claim 8, characterized in that: In step G3, the calculation formula for the daily electricity demand forecast value is as follows: In the formula, EY j It is the daily electricity demand forecast value.

10. An industrial electricity demand forecasting system considering energy consumption characteristics, the system being used to implement an industrial electricity demand forecasting method considering energy consumption characteristics as claimed in any one of claims 1 to 9, characterized in that: The system includes: Data collection unit, used to collect basic data in the target industry; The electricity consumption evaluation unit is used to determine the total theoretical daily electricity consumption based on the collected basic data; The factor adjustment unit is used to analyze the time distribution of historical electricity consumption data and adjust the daily theoretical total electricity consumption according to the time type of the current date: The correlation analysis unit is used to establish the correlation between equipment electricity consumption and output, and determine the electricity consumption increment corresponding to the output change based on the corresponding correlation relationship and the estimated output in the production scheduling plan, and then add the electricity consumption increment to the adjusted daily electricity consumption estimate to obtain the daily electricity demand forecast value.

Images