A method for predicting urban electricity demand based on the Logistic model

Abstract

This invention relates to the field of power forecasting technology, specifically to a method for predicting urban power demand based on a Logistic model. The invention analyzes the trends in daily power consumption and load changes to obtain the overall expansion sustainability, sustained high load sustainability, and load decline sustainability of each power supply area, and identifies traditional industrial areas and emerging load areas. It also obtains the number of times power is supplied and the number of times it receives support, and combines this with the overall expansion sustainability of each emerging load area to obtain the comprehensive expansion dynamic impact of each emerging load area. For the latest historical year, it obtains the power saturation capacity influence coefficient, and combines this with the distribution of power load in different historical years to obtain the optimized saturation capacity for predicting urban power demand. This invention improves the accuracy of power demand forecasting by obtaining accurate saturation capacity predicted by the Logistic model.

Description

Technical Field

[0001] This invention relates to the field of power forecasting technology, and specifically to a method for forecasting urban power demand based on a Logistic model. Background Technology

[0002] Urban electricity demand forecasting is crucial for ensuring stable power supply, optimizing energy resource allocation, reducing system operating costs, enhancing environmental sustainability, addressing climate change, supporting smart grid development, and promoting long-term urban development. Electricity demand forecasting not only helps improve power system efficiency but also provides important data for environmental protection and urban infrastructure construction, ensuring that grid expansion keeps pace with urban growth.

[0003] In existing technologies, the Logistic model based on a fixed saturation capacity value is used to predict electricity demand. However, the continuous expansion and upgrading of cities have made the growth of electricity demand highly nonlinear and time-varying. The fixed saturation capacity value fails to reflect dynamic changes, resulting in a deviation between the prediction results and the actual demand, and the electricity demand prediction effect is poor. Summary of the Invention

[0004] To address the technical problem that fixed saturation capacity values ​​fail to reflect dynamic changes and result in poor electricity demand forecasting, this invention aims to provide a method for urban electricity demand forecasting based on a Logistic model. The specific technical solution adopted is as follows:

[0005] This invention proposes a method for predicting urban electricity demand based on a Logistic model, the method comprising:

[0006] Obtain the daily power consumption of different power supply areas within the city, as well as the power load for each time period of the day;

[0007] Based on the daily power consumption distribution of the power supply area in all days of the year, and the power load change trend at the same time of different days, the overall expansion sustainability performance, sustained high load performance, and load decline performance of each power supply area are obtained.

[0008] Based on the daily power consumption changes of the power supply area in all days of different years, traditional industrial areas and new load areas are screened out; the number of times the power supply area is supported and the number of times it is supported are obtained; combined with the overall expansion sustainability of each new load area, the comprehensive expansion dynamic impact of each new load area is obtained.

[0009] For the latest historical year, the power saturation capacity influence coefficient is obtained based on the sustained high load performance of different power supply areas, the load decline performance of all traditional industrial areas, and the comprehensive expansion dynamic impact of all new load areas; the optimized saturation capacity is obtained based on the power saturation capacity influence coefficient and the distribution of electricity load in different years.

[0010] Urban electricity demand is predicted based on the optimized Logistic model with saturated capacity.

[0011] Furthermore, the method for obtaining the overall expansion persistence performance includes:

[0012] Within the neighborhood of the latest historical year, the cumulative daily power consumption of each power supply area for all days of each month is obtained and normalized, serving as the power consumption weight of each power supply area in each month.

[0013] Obtain the difference in power consumption weight between different months and the previous month as the weight difference; assign consecutive positive weight differences to all months to form an expansion and development cycle; calculate the average power consumption weight of all months in each expansion and development cycle as the expansion power consumption weight; calculate the average ratio of the cumulative daily power consumption between different months and the previous month in each expansion and development cycle as the expansion coefficient.

[0014] The expansion power consumption weight is adjusted by gain according to the expansion coefficient of each expansion cycle, which is used as the local expansion sustainability of each expansion cycle; the largest local expansion sustainability value among all expansion cycles is selected as the overall expansion sustainability of each power supply area.

[0015] Furthermore, the method for obtaining the sustained high load performance includes:

[0016] Based on the daily power consumption distribution of each power supply area throughout the year, the annual continuity of power consumption in each power supply area is obtained.

[0017] The power load curves of each power supply area are fitted to the power load of the same time period in different days. The two power load curves with the highest and lowest positions in all time periods are selected. The area difference between the two curves is calculated by definite integral and negative correlation normalization is performed to serve as the multi-time period continuous load degree of each power supply area.

[0018] The gain of the annual power consumption duration is adjusted based on the multi-period continuous load of each power supply area to obtain the continuous high load performance of each power supply area.

[0019] Furthermore, the method for obtaining the annual duration of power consumption includes:

[0020] The daily power consumption of each power supply area is normalized and used as the daily power consumption weight of each power supply area.

[0021] Obtain the fitted curve of the power consumption weight of each power supply area for all days, find the maximum point of the fitted curve, and obtain the cumulative difference of the power consumption weight between different maximum points and the previous maximum point as the annual duration of power consumption of each power supply area.

[0022] Furthermore, the method for obtaining the load decay performance index includes:

[0023] Obtain the average electricity load of each power supply area at all times of the day as the average electricity load level; obtain the minimum point in the curve formed by the average electricity load levels of all days in the year as the load decay point;

[0024] Based on the average power load distribution on both sides of each load decay point, the decay node performance of each load decay point is obtained.

[0025] The load attenuation node with the highest attenuation performance among all load attenuation points is selected, and the attenuation node performance of the corresponding load attenuation point is taken as the load attenuation performance of each power supply area.

[0026] Furthermore, the method for obtaining the attenuation node performance includes:

[0027] The average electricity load level corresponding to the load decay point is taken as the target load. The first decay degree is obtained based on the first difference between the maximum value of the average electricity load level in all days and the target load, and the second difference between the average electricity load levels on the left and right sides of each load decay point. Both the first difference and the second difference are positively correlated with the first decay degree.

[0028] The range of consecutive days in which the average electricity load level on the left is greater than or equal to the target load is obtained as the first time interval; the range of consecutive days in which the average electricity load level on the right is less than or equal to the target load is obtained as the second time interval; based on the first difference and the interval difference between the second time interval and the first time interval, the second decay degree is obtained. The first difference is negatively correlated with the second decay degree, and the interval difference is positively correlated with the second decay degree.

[0029] The sum of the first and second attenuation degrees at each load attenuation point is obtained as the attenuation node performance of each load attenuation point.

[0030] Furthermore, the method for obtaining the traditional industrial area and the new load area includes:

[0031] The sum of the daily power consumption of each power supply area for all days of the year is obtained as the total power consumption of each power supply area for the year.

[0032] Calculate the difference in overall power consumption for each power supply area between the latest historical year and the previous year, as the degree of power consumption decline for each power supply area;

[0033] If the rate of change in power consumption decline in a power supply area is less than or equal to a preset decline threshold, the corresponding power supply area will be designated as a traditional industrial area; otherwise, it will be designated as a new type of load area.

[0034] Furthermore, the method for obtaining the comprehensive expansion dynamic influence degree includes:

[0035] For each power supply area, the ratio between the number of times support was received and the number of times support was provided is used as the power contribution rate.

[0036] The comprehensive expansion dynamic impact of each new load area is obtained by considering the number of times the new load area is supported by its neighboring areas, the number of times the new load area is supported, its power contribution, and its overall expansion sustainability. The number of times the new load area is supported and its power contribution are negatively correlated with the comprehensive expansion dynamic impact, while the number of times the new load area is supported and its overall expansion sustainability are positively correlated with the comprehensive expansion dynamic impact.

[0037] Furthermore, the method for obtaining the power saturation capacity influence coefficient includes:

[0038] The cumulative sum of the sustained high load performance and load decline performance of all traditional industrial areas is obtained as the first performance value;

[0039] The cumulative sum of the sustained high load performance and the comprehensive expansion dynamic impact of all new load areas is obtained as the second performance value;

[0040] The difference between the first performance value and the second performance value is obtained as the power saturation capacity influence coefficient.

[0041] Furthermore, the method for obtaining the optimized saturation capacity includes:

[0042] The maximum value of electricity load in a preset number of historical years is obtained, and the Logistic curve is fitted using the nonlinear least squares method to obtain the initial saturation capacity of the latest historical year.

[0043] The initial saturation capacity is adjusted by gain based on the power saturation capacity influence coefficient to obtain the optimized saturation capacity.

[0044] The present invention has the following beneficial effects:

[0045] This invention analyzes the trends of daily power consumption and load changes to obtain the overall expansion sustainability, sustained high load sustainability, and load decline sustainability of each power supply area, reflecting the trend characteristics of regional power consumption changes. Based on the daily power consumption changes of each power supply area across all days in different years, traditional industrial areas and emerging load areas are screened, facilitating targeted analysis by area classification. The number of times each power supply area receives and is supported is obtained. Combining the number of times different power supply areas receive and are supported with the overall expansion sustainability of each emerging load area, the comprehensive expansion dynamic impact of each emerging load area is obtained, assessing the dynamic impact of emerging loads on load expansion. For the latest historical year, based on the sustained high load sustainability of different power supply areas, the load decline sustainability of all traditional industrial areas, and the comprehensive expansion dynamic impact of all emerging load areas, the power saturation capacity influence coefficient is obtained, determining the dynamic impact coefficient of the entire city's power saturation capacity changes. Based on the power saturation capacity influence coefficient and the distribution of power load across different years, the optimized saturation capacity is obtained, more accurately predicting the inflection point of power demand. This invention improves the accuracy of power demand forecasting by obtaining the accurate saturation capacity predicted by the Logistic model. Attached Figure Description

[0046] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating a method for predicting urban electricity demand based on a Logistic model, as provided in an embodiment of the present invention;

[0048] Figure 2 A flowchart illustrating a method for obtaining overall extended sustained performance, as provided in an embodiment of the present invention;

[0049] Figure 3 This is a flowchart illustrating a method for obtaining the attenuation node performance according to an embodiment of the present invention. Detailed Implementation

[0050] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a city electricity demand forecasting method based on a Logistic model proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0052] The following description, in conjunction with the accompanying drawings, details a specific scheme for an urban electricity demand forecasting method based on a Logistic model provided by this invention.

[0053] Please see Figure 1 The diagram illustrates a flowchart of an urban electricity demand forecasting method based on a Logistic model, according to an embodiment of the present invention. The specific method includes:

[0054] Step S1: Obtain the daily power consumption of different power supply areas in the city, as well as the power load of each time period during the day.

[0055] In embodiments of the present invention, in order to accurately predict electricity demand, it is necessary to analyze power consumption and electricity load. First, based on the urban power grid GIS platform, different power supply areas within the city are obtained. Then, the power consumption information collection system and SCADA system are used to obtain the power consumption and electricity load of different areas, thereby obtaining the daily power consumption of different power supply areas within the city and the electricity load of each time period within each day.

[0056] It should be noted that, in the embodiments of the present invention, each hour is considered as a time period.

[0057] Step S2: Based on the daily power consumption distribution of the power supply area for all days of the year, and the power load change trend at the same time of different days, obtain the overall expansion sustainability performance, sustained high load performance, and load decline performance of each power supply area.

[0058] Different power supply areas in a city exhibit varying degrees of power load impact. The more consistently daily power consumption increases, the greater the degree of sustained expansion. The trend of power load changes at the same time of day reflects the convergence of curves across multiple time periods. The closer the power load performance across multiple time periods, the more pronounced the sustained power load performance. If significant changes occur in a power supply area, different power load trends will emerge around a certain point in time, reflecting the degree of load decline. Therefore, based on the distribution of daily power consumption across all days of the year and the trend of power load changes at the same time of day across different days, the overall degree of sustained expansion, sustained high load performance, and load decline performance of each power supply area can be obtained.

[0059] Preferably, in one embodiment of the present invention, the method for obtaining the overall expansion persistence performance is described in [reference needed]. Figure 2 It illustrates a flowchart of a method for obtaining the overall expansion persistence performance, including:

[0060] Step S201: Within the neighborhood of the latest historical year, obtain the cumulative daily power consumption of each power supply area for all days in each month, and normalize it as the power consumption weight of each power supply area in each month.

[0061] It should be noted that, in one embodiment of the present invention, the neighborhood range of the latest historical year is the range formed by the latest historical year and the previous year. In other embodiments of the present invention, the size of the neighborhood range can be set according to specific circumstances, and will not be limited or elaborated here.

[0062] It should be noted that in the embodiments of the present invention, linear normalization or a normalization function is used for normalization. The specific means are well known to those skilled in the art and will not be described in detail here.

[0063] Step S202: Obtain the difference in power consumption weight between different months and the previous month as the weight difference; assign consecutive positive weight differences to all months to form an expansion and development cycle; calculate the average power consumption weight of all months in each expansion and development cycle as the expansion power consumption weight; calculate the average ratio of the cumulative daily power consumption between different months and the previous month in each expansion and development cycle as the expansion coefficient.

[0064] The greater the increase in electricity load, the more it exhibits expansion. Therefore, we analyze the expansion cycle by assigning positive values ​​to continuous weight differences across all months. By averaging the values, we quantify the expansion weight of electricity consumption within the expansion cycle, reflecting the overall level of electricity consumption weight within the expansion cycle. The greater the cumulative daily electricity consumption of the following month compared to the previous month, the greater the increase in electricity load and the larger the expansion coefficient.

[0065] Step S203: Adjust the gain of the expansion power consumption weight according to the expansion coefficient of each expansion cycle, and use it as the local expansion sustainability performance of each expansion cycle; select the largest value of the local expansion sustainability performance among all expansion cycles as the overall expansion sustainability performance of each power supply area.

[0066] It should be noted that the larger the expansion coefficient, the greater the expansion power consumption weight, the greater the increase in power load, and the greater the local expansion persistence. The gain adjustment method is as follows: obtain the sum of the positive integer 1 and the expansion coefficient as the expansion adjustment coefficient; calculate the product of the expansion adjustment coefficient and the expansion power consumption weight as the local expansion persistence.

[0067] Preferably, in one embodiment of the present invention, the method for obtaining sustained high load performance includes:

[0068] Based on the daily power consumption distribution of each power supply area throughout the year, the annual continuity of power consumption in each power supply area is obtained.

[0069] Preferably, in one embodiment of the present invention, the method for obtaining the annual duration of power consumption includes:

[0070] The daily power consumption of each power supply area is normalized and used as the daily power consumption weight of each power supply area.

[0071] Obtain the fitted curve of the power consumption weight of each power supply area for all days, find the maximum point of the fitted curve, and obtain the cumulative difference of the power consumption weight between different maximum points and the previous maximum point as the annual duration of power consumption of each power supply area.

[0072] It should be noted that, in the embodiments of the present invention, linear normalization or a normalization function is used for normalization, and least squares method or polynomial fitting is used to obtain the fitting curve. The specific means are well known to those skilled in the art and will not be described in detail here.

[0073] The power load curves of each power supply area are fitted to the power load of the same time period in different days. The two power load curves with the highest and lowest positions in all time periods are selected. The area difference between the two curves is calculated by definite integral and negative correlation normalization is performed to serve as the multi-time period continuous load degree of each power supply area.

[0074] The gain of the annual power consumption duration is adjusted based on the multi-period continuous load of each power supply area to obtain the continuous high load performance of each power supply area.

[0075] It should be noted that the annual power consumption duration reflects the continuity of the power supply area in the power consumption state throughout the year. The greater the annual power consumption duration, the more continuous the load performance. In one embodiment of the present invention, the sum of the positive integer 1 and the multi-period continuous load degree of each power supply area is obtained as the multi-period continuous load regulation degree. The product between the multi-period continuous load regulation degree and the annual power consumption duration is calculated and normalized to obtain the continuous high load performance degree of each power supply area.

[0076] It should be noted that, in one embodiment of the present invention, negative correlation normalization can be performed by taking the reciprocal of the area difference and normalizing it. In other embodiments of the present invention, negative correlation normalization can also be performed by a function. The specific means are well known to those skilled in the art and will not be described in detail here.

[0077] Preferably, in one embodiment of the present invention, the method for obtaining load decay performance includes:

[0078] Obtain the average electricity load of each power supply area at all times of the day as the average electricity load level; obtain the minimum point in the curve formed by the average electricity load levels of all days in the year as the load decay point;

[0079] Based on the average power load distribution on both sides of each load decay point, the decay node performance of each load decay point is obtained.

[0080] It should be noted that, in one embodiment of the present invention, the method for obtaining the attenuation node performance is described in the following reference: Figure 3 It illustrates a flowchart of a method for obtaining the performance of decaying nodes, including:

[0081] Step S301: Take the average electricity load level corresponding to the load decay point as the target load. Based on the first difference between the maximum value of the average electricity load level over all days and the target load, and the second difference between the average electricity load levels on the left and right sides of each load decay point, obtain the first decay degree. Both the first difference and the second difference are positively correlated with the first decay degree.

[0082] It should be noted that the first difference between the maximum value of the average electricity load level over all days and the target load reflects the change in peak and valley load. The greater the change, the larger the first difference, and the more attention needs to be paid to the load change. The second difference between the average electricity load levels on the left and right sides of each load decline point reflects the load decline. The larger the second difference, the greater the decline, that is, the greater the first attenuation. Both the first and second differences are positively correlated with the first attenuation.

[0083] It should be noted that in other embodiments of the present invention, the difference between data can also be reflected by analyzing the ratio. The larger the ratio, the greater the difference between the previous data and the next data. The specific means are well known to those skilled in the art and will not be described in detail here.

[0084] In one embodiment of the present invention, the product of a first difference and a second difference is obtained and normalized to obtain a first attenuation degree. Therefore, based on the above basic mathematical operations, a correlation is constructed between the first difference, the second difference, and the first attenuation degree; that is, the larger the first difference, the greater the attention to load changes, and the larger the second difference, the greater the first attenuation degree.

[0085] Step S302: Obtain the range of consecutive days in which the average electricity load level on the left side is greater than or equal to the target load, as the first time interval; obtain the range of consecutive days in which the average electricity load level on the right side is less than or equal to the target load, as the second time interval; obtain the second decay degree based on the first difference and the interval difference between the second time interval and the first time interval, wherein the first difference is negatively correlated with the second decay degree and the interval difference is positively correlated with the second decay degree;

[0086] It should be noted that the smaller the first difference between the maximum value of the average electricity load level and the target load, the less obvious the trend of load data change, the more attention is paid to the time-dependent decay trend, and the greater the reliability of the interval difference. The interval difference between the second time interval and the first time interval reflects the impact of the load transition time trend. The larger the interval difference, the larger the second time interval, the smaller the time corresponding to the load decay point, the longer the subsequent decay, and the greater the second decay degree. The first difference is negatively correlated with the second decay degree, and the interval difference is positively correlated with the second decay degree.

[0087] In one embodiment of the present invention, the difference between the positive integer 1 and the first difference is obtained, and the product between the difference result and the interval difference is calculated as the second attenuation degree. Based on the above basic mathematical operations, the correlation between the first difference, the interval difference and the second attenuation degree is constructed, that is, the smaller the first difference, the less attention is paid to load changes and the greater attention is paid to time decay; the larger the interval difference, the greater the second attenuation degree.

[0088] Step S303: Obtain the sum of the first attenuation degree and the second attenuation degree for each load attenuation point, as the attenuation node performance degree for each load attenuation point.

[0089] The load attenuation node with the highest attenuation performance among all load attenuation points is selected, and the attenuation node performance of the corresponding load attenuation point is taken as the load attenuation performance of each power supply area.

[0090] Step S3: Based on the changes in daily power consumption of the power supply area in all days of different years, filter out traditional industrial areas and new load areas; obtain the number of times the power supply area is supported and the number of times it is supported, and combine the overall expansion sustainability of each new load area to obtain the comprehensive expansion dynamic impact of each new load area.

[0091] Traditional industrial areas typically maintain relatively stable electricity demand over this long period, with little change in electricity load within the overall power system, maintaining a relatively stable load state.

[0092] As cities develop, the electricity consumption of traditional industrial areas may decline, while new load areas are emerging and consuming more electricity. Therefore, based on the changes in daily electricity consumption of power supply areas over all days in different years, traditional industrial areas and new load areas are selected.

[0093] Preferably, in one embodiment of the present invention, the method for obtaining traditional industrial areas and new load areas includes:

[0094] The sum of the daily power consumption of each power supply area for all days of the year is obtained as the total power consumption of each power supply area for the year.

[0095] Calculate the difference in overall power consumption for each power supply area between the latest historical year and the previous year, as the degree of power consumption decline for each power supply area;

[0096] If the rate of change in power consumption decline in a power supply area is less than or equal to a preset decline threshold, the corresponding power supply area will be designated as a traditional industrial area; otherwise, it will be designated as a new type of load area.

[0097] It should be noted that, in one embodiment of the present invention, the preset decay threshold is 0.65; in other embodiments of the present invention, the preset decay threshold can be set according to specific circumstances, and will not be limited or elaborated here.

[0098] In the case of expansion of new load areas, when the power supply area may experience overload, the reserve capacity of adjacent power supply areas will be prioritized to meet the power demand. Based on the urban power dispatch management system, the dispatch event logs will be obtained, which will be reflected as the number of times the area is supported or supported. The overall expansion sustainability of each new load area reflects the continuous growth of the area's power load. The greater the continuous growth, the more expansion-oriented the load. By measuring the number of times different power supply areas are supported and supported, as well as the overall expansion sustainability of each new load area, the comprehensive expansion dynamic impact is quantified, reflecting the degree of impact of load expansion on power system stability. The comprehensive expansion dynamic impact of each new load area is obtained by combining the number of times different power supply areas are supported and supported with the overall expansion sustainability of each new load area.

[0099] Preferably, in one embodiment of the present invention, the method for obtaining the comprehensive expansion dynamic influence degree includes:

[0100] For each power supply area, the ratio between the number of times support was received and the number of times support was provided is used as the power contribution rate.

[0101] The comprehensive expansion dynamic impact of each new load area is obtained by considering the number of times the new load area is supported by its neighboring areas, the number of times the new load area is supported, its power contribution, and its overall expansion sustainability. The number of times the new load area is supported and its power contribution are negatively correlated with the comprehensive expansion dynamic impact, while the number of times the new load area is supported and its overall expansion sustainability are positively correlated with the comprehensive expansion dynamic impact.

[0102] It should be noted that the number of times adjacent regions support a new load area reflects the number of times the new load area is supported by other nearby power supply areas. The closer to the number of times the new load area is supported, the greater the number of times adjacent regions support the new load area relative to the number of times it is supported. This increases the likelihood of nearby power supply support during power shortages and reduces the impact of expansion. The power contribution reflects the new load area's ability to support the balance of power supply and demand. The greater the number of times it is supported, the greater the power contribution, indicating that the power supply in the new load area is relatively abundant and the impact of expansion is smaller. The overall expansion sustainability reflects the sustainability of load expansion. The greater the expansion sustainability, the greater the expansion impact. Therefore, the number of times the new load area is supported and the power contribution are negatively correlated with the overall expansion dynamic impact, while the number of times the new load area is supported and the overall expansion sustainability are positively correlated with the overall expansion dynamic impact.

[0103] In one embodiment of the present invention, the ratio of the number of times a new load area is supported by neighboring regions to the number of times the new load area is supported is obtained as the feasibility of near-distance power supply support; the product of power contribution and near-distance power supply support feasibility is obtained and normalized as the contribution-near-distance support linkage coefficient; the difference between the positive integer 1 and the contribution-near-distance support linkage coefficient is obtained, and the product of the difference result and the expansion duration limit is calculated as the comprehensive expansion dynamic impact of each new load area. Therefore, based on the above basic mathematical operations, a correlation is constructed between the number of times a new load area is supported, the power contribution, the number of times a new load area is supported, the overall expansion duration performance, and the comprehensive expansion dynamic impact. That is, the smaller the number of times a new load area is supported, the smaller the power contribution, the larger the number of times a new load area is supported, and the larger the overall expansion duration performance, the larger the comprehensive expansion dynamic impact.

[0104] Step S4: For the latest historical year, obtain the power saturation capacity influence coefficient based on the sustained high load performance of different power supply areas, the load decline performance of all traditional industrial areas, and the comprehensive expansion dynamic influence of all new load areas; obtain the optimized saturation capacity based on the power saturation capacity influence coefficient and the distribution of electricity load in different years.

[0105] Considering that the impact of emerging load areas on power saturation capacity is increasing, while the impact of traditional industrial areas is decreasing, it is crucial to focus on the impact of sustained high load demand on overall power demand, using sustained high load performance as a weight. Influenced by various factors, traditional industrial areas exhibit declining trends, leading to significant fluctuations in power load. Emerging load areas, on the other hand, experience substantial increases in power load, exhibiting an expansionary trend. Therefore, this study analyzes the sustained high load performance of different power supply areas, the load decline performance of all traditional industrial areas, and the comprehensive expansion dynamic impact of all emerging load areas. For the latest historical year, the power saturation capacity impact coefficient is obtained based on the sustained high load performance of different power supply areas, the load decline performance of all traditional industrial areas, and the comprehensive expansion dynamic impact of all emerging load areas.

[0106] Preferably, in one embodiment of the present invention, the method for obtaining the power saturation capacity influence coefficient includes:

[0107] The cumulative sum of the sustained high load performance and load decline performance of all traditional industrial areas is obtained as the first performance value;

[0108] The cumulative sum of the sustained high load performance and the comprehensive expansion dynamic impact of all new load areas is obtained as the second performance value;

[0109] The difference between the first performance value and the second performance value is obtained as the power saturation capacity influence coefficient.

[0110] Saturation capacity reflects the maximum load limit that a power system in a certain area can carry. It reveals the growth characteristics of urban power load through the distribution of electricity load. However, relying solely on historical growth trends may overestimate the actual achievable capacity. The power saturation capacity influence coefficient integrates power changes and trend changes to correct the saturation capacity. Based on the power saturation capacity influence coefficient and the distribution of electricity load in different years, the optimized saturation capacity is obtained.

[0111] Preferably, in one embodiment of the present invention, the method for obtaining the optimized saturation capacity includes:

[0112] The maximum value of electricity load in a preset number of historical years is obtained, and the Logistic curve is fitted using the nonlinear least squares method to obtain the initial saturation capacity for the latest historical year.

[0113] The initial saturation capacity is adjusted by gain based on the power saturation capacity influence coefficient to obtain the optimized saturation capacity.

[0114] It should be noted that the specific nonlinear least squares method for fitting the Logistic curve is a technique well-known to those skilled in the art, and will not be elaborated upon here.

[0115] It should be noted that, in one embodiment of the present invention, a preset number of historical years are selected, including the latest historical year and adjacent historical years, and the preset number is 5. In other embodiments of the present invention, the preset number can be set according to specific circumstances, and will not be limited or elaborated here.

[0116] In one embodiment of the present invention, the sum of the positive integer 1 and the power saturation capacity influence coefficient is obtained as the influence weight;

[0117] The product of the initial saturation capacity and the influence weights is obtained as the optimized saturation capacity.

[0118] Step S5: Predict urban electricity demand based on the optimized Logistic model with saturated capacity.

[0119] By optimizing the saturation capacity parameter of the traditional Logistic model, a more realistic urban electricity demand forecast curve can be generated, improving the effectiveness of electricity demand forecasting and facilitating urban development planning.

[0120] In summary, this invention analyzes the trends in daily power consumption and load changes to obtain the overall expansion sustainability, sustained high load sustainability, and load decline sustainability of each power supply area, and identifies traditional industrial areas and emerging load areas. It also obtains the number of times power is supplied and the number of times it receives support, and combines this with the overall expansion sustainability of each emerging load area to obtain its comprehensive expansion dynamic impact. For the latest historical year, it obtains the power saturation capacity influence coefficient, and combines this with the distribution of power load in different historical years to obtain the optimized saturation capacity for predicting urban power demand. This invention improves the accuracy of power demand forecasting by obtaining the accurate saturation capacity predicted by the Logistic model.

[0121] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for predicting urban electricity demand based on a Logistic model, characterized in that, The method includes: This study obtains the daily electricity consumption and daily load of different power supply areas within a city. Based on the distribution of daily electricity consumption across all days of the year and the load trends during the same time period across different days, it obtains the overall expansion sustainability, sustained high load sustainability, and load decline sustainability of each power supply area. Traditional industrial areas and emerging load areas are identified based on the daily electricity consumption changes across all days of different years. The number of times different power supply areas receive and are supported is obtained, and combined with the overall expansion sustainability of each emerging load area, the comprehensive expansion dynamic impact of each emerging load area is obtained. For the latest historical year, the power saturation capacity impact coefficient is obtained based on the sustained high load sustainability of different power supply areas, the load decline sustainability of all traditional industrial areas, and the comprehensive expansion dynamic impact of all emerging load areas. The optimized saturation capacity is obtained based on the power saturation capacity impact coefficient and the load distribution across different years. The city's electricity demand is then predicted using a Logistic model based on the optimized saturation capacity.

2. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The method for obtaining the overall expansion persistence performance includes: Within the neighborhood of the latest historical year, the cumulative daily power consumption of each power supply area for all days of each month is obtained and normalized, serving as the power consumption weight of each power supply area in each month. Obtain the difference in power consumption weight between different months and the previous month as the weight difference; assign consecutive positive weight differences to all months to form an expansion and development cycle; calculate the average power consumption weight of all months in each expansion and development cycle as the expansion power consumption weight; calculate the average ratio of the cumulative daily power consumption between different months and the previous month in each expansion and development cycle as the expansion coefficient. The expansion power consumption weight is adjusted by gain according to the expansion coefficient of each expansion cycle, which is used as the local expansion sustainability of each expansion cycle; the largest local expansion sustainability value among all expansion cycles is selected as the overall expansion sustainability of each power supply area.

3. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The method for obtaining the sustained high load performance includes: Based on the daily power consumption distribution of each power supply area throughout the year, the annual continuity of power consumption in each power supply area is obtained. The power load curves of each power supply area are fitted to the power load of the same time period in different days. The two power load curves with the highest and lowest positions in all time periods are selected. The area difference between the two curves is calculated by definite integral and negative correlation normalization is performed to serve as the multi-time period continuous load degree of each power supply area. The gain of the annual power consumption duration is adjusted based on the multi-period continuous load of each power supply area to obtain the continuous high load performance of each power supply area.

4. The urban electricity demand forecasting method based on the Logistic model according to claim 3, characterized in that, The method for obtaining the annual duration of power consumption includes: The daily power consumption of each power supply area is normalized and used as the daily power consumption weight of each power supply area. Obtain the fitted curve of the power consumption weight of each power supply area for all days, find the maximum point of the fitted curve, and obtain the cumulative difference of the power consumption weight between different maximum points and the previous maximum point as the annual duration of power consumption of each power supply area.

5. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The method for obtaining the load decay performance index includes: Obtain the average electricity load of each power supply area at all times of the day as the average electricity load level; obtain the minimum point in the curve formed by the average electricity load levels of all days in the year as the load decay point; Based on the average power load distribution on both sides of each load decay point, the decay node performance of each load decay point is obtained. The load attenuation node with the highest attenuation performance among all load attenuation points is selected, and the attenuation node performance of the corresponding load attenuation point is taken as the load attenuation performance of each power supply area.

6. The urban electricity demand forecasting method based on the Logistic model according to claim 5, characterized in that, The method for obtaining the attenuation node performance includes: The average electricity load level corresponding to the load decay point is taken as the target load. The first decay degree is obtained based on the first difference between the maximum value of the average electricity load level in all days and the target load, and the second difference between the average electricity load levels on the left and right sides of each load decay point. Both the first difference and the second difference are positively correlated with the first decay degree. The range of consecutive days in which the average electricity load level on the left is greater than or equal to the target load is obtained as the first time interval; the range of consecutive days in which the average electricity load level on the right is less than or equal to the target load is obtained as the second time interval; based on the first difference and the interval difference between the second time interval and the first time interval, the second decay degree is obtained. The first difference is negatively correlated with the second decay degree, and the interval difference is positively correlated with the second decay degree. The sum of the first and second attenuation degrees at each load attenuation point is obtained as the attenuation node performance of each load attenuation point.

7. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The methods for obtaining the traditional industrial area and the new load area include: The sum of the daily power consumption of each power supply area for all days of the year is obtained as the total power consumption of each power supply area for the year. Calculate the difference in overall power consumption for each power supply area between the latest historical year and the previous year, as the degree of power consumption decline for each power supply area; If the rate of change in power consumption decline in a power supply area is less than or equal to a preset decline threshold, the corresponding power supply area will be designated as a traditional industrial area; otherwise, it will be designated as a new type of load area.

8. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The method for obtaining the dynamic impact of the comprehensive expansion includes: For each power supply area, the ratio between the number of times support was received and the number of times support was provided is used as the power contribution rate. The comprehensive expansion dynamic impact of each new load area is obtained by considering the number of times the new load area is supported by its neighboring areas, the number of times the new load area is supported, its power contribution, and its overall expansion sustainability. The number of times the new load area is supported and its power contribution are negatively correlated with the comprehensive expansion dynamic impact, while the number of times the new load area is supported and its overall expansion sustainability are positively correlated with the comprehensive expansion dynamic impact.

9. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The method for obtaining the power saturation capacity influence coefficient includes: The cumulative sum of the sustained high load performance and load decline performance of all traditional industrial areas is obtained as the first performance value; The cumulative sum of the sustained high load performance and the comprehensive expansion dynamic impact of all new load areas is obtained as the second performance value; The difference between the first performance value and the second performance value is obtained as the power saturation capacity influence coefficient.

10. The urban electricity demand forecasting method based on the Logistic model according to claim 1, characterized in that, The method for obtaining the optimized saturation capacity includes: The maximum value of electricity load in a preset number of historical years is obtained, and the Logistic curve is fitted using the nonlinear least squares method to obtain the initial saturation capacity of the latest historical year. The initial saturation capacity is adjusted by gain based on the power saturation capacity influence coefficient to obtain the optimized saturation capacity.

Images