A method and device for evaluating potential of electric power users

Abstract

The present invention relates to a method and device for evaluating the potential of power users, and belongs to the technical field of power evaluation, including dividing the southern region into multiple target areas according to its winter characteristics; analyzing the power consumption patterns of the daily historical power consumption data of residents in each target area in the past N years, and obtaining the corresponding daily power consumption forecast data; according to each date of the current year, respectively determining the power consumption forecast data corresponding to each relevant date from the daily power consumption forecast data, and obtaining the power consumption forecast data set associated with each date of the current year; wherein, according to the daily average temperature and humidity of each target area in the current year, respectively matching the daily historical average temperature and humidity of each target area in the past N years, and determining multiple relevant dates with the highest matching degree of daily average temperature and humidity; according to the difference between the maximum value and the minimum value in the power consumption forecast data set, determining the responsive power for each date of the current year. The present invention can realize accurate and reliable power consumption potential evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of power evaluation, and in particular to a method and device for evaluating the potential of power users. Background Art

[0002] With the rapid development of industrialization and informatization, the power system plays a vital role in modern society. As the core component of the power system, the power dispatching system covers power grid companies, load aggregators, and various types of power users, including residential and industrial users. Among these users, electricity consumption behavior shows a certain regularity. Especially during peak electricity consumption periods, power grid companies face huge power supply loads, which not only poses a challenge to the safe and stable operation of the power grid, but also puts high demands on ensuring residents' electricity consumption. During the low electricity consumption period, power grid companies often have a greater power supply capacity than users' electricity demand, resulting in serious waste of electricity.

[0003] To alleviate this problem, power grid companies usually adopt a peak-valley time-of-use electricity price strategy, that is, setting higher electricity prices during peak electricity consumption periods and lower electricity prices during valley periods to encourage users to use electricity during off-peak periods. Although this method can improve the load conditions of the power system to a certain extent, due to its lack of fine-grained control measures, users' responses are often disordered and may cause load rebound effects, affecting the smooth power supply of the power grid. To address this problem, load aggregators conduct potential assessment and analysis of power users, attempting to determine the electricity demand patterns of different user groups and predict electricity consumption trends in the future. Then, based on these forecast data, more refined power supply regulation is implemented to improve the efficiency of load management.

[0004] However, in practical applications, due to the great differences in electricity demand among different users, traditional potential assessment methods often fail to provide sufficiently accurate and reliable assessment results. Taking winter and summer as an example, the heating and cooling needs of residents in the north and south are significantly different, and these differences are jointly affected by regional climate, living habits and seasonal changes. Northern regions usually have centralized heating, while southern regions rely more on electric heating, resulting in higher electricity demand in southern residents in winter. A similar situation exists in the use of air conditioners in summer. In particular, for residents in the south, winter heating constitutes the main part of their electricity consumption and has a large electricity response potential. However, the existing assessment methods cannot fully consider the specific electricity consumption pattern of winter heating in the south, resulting in deviations between the assessment results and actual electricity consumption behavior. Summary of the invention

[0005] To this end, the technical problem to be solved by the present invention is to overcome the problem in the prior art that the electricity consumption patterns in different regions are not fully considered, resulting in the inability to provide sufficiently accurate and reliable electricity consumption potential assessment results.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a method for evaluating the potential of power users, which is used to evaluate the potential of power consumption of residents in southern China in winter, comprising:

[0007] According to the temperature and humidity of each province in the southern region in winter, each province is divided into a plurality of target areas;

[0008] Analyze the daily historical electricity consumption data of residents in each target area in the past N years to obtain the daily electricity consumption forecast data corresponding to each target area; wherein N is an integer greater than or equal to 3;

[0009] According to each date of the current year, the electricity consumption forecast data corresponding to each relevant date is determined from the daily electricity consumption forecast data, and the electricity consumption forecast data set associated with each date of the current year is obtained; wherein the method for obtaining the relevant dates is: according to the daily average temperature and daily average humidity of each target area in the current year, the daily historical average temperature and daily historical average humidity of each target area in the past N years are matched respectively, and a plurality of the relevant dates with the highest matching degree of the daily average temperature and the daily average humidity are determined;

[0010] The responsive power quantity for each date in the current year is determined according to the difference between the maximum value and the minimum value in the power consumption forecast data set.

[0011] In one embodiment of the present invention, the method for obtaining the electricity consumption forecast data is:

[0012] The historical power consumption data is analyzed for power consumption data of the first category of electrical appliances and the second category of electrical appliances to obtain dehumidification power consumption data and heating power consumption data respectively;

[0013] Respectively analyzing the dehumidification electricity consumption data and the heating electricity consumption data to obtain corresponding dehumidification electricity consumption prediction data and heating electricity consumption prediction data;

[0014] According to different time periods, the dehumidification electricity consumption forecast data and the heating electricity consumption forecast data are combined to obtain the electricity consumption forecast data.

[0015] In one embodiment of the present invention, the parsing of the historical power consumption data of the first category of electrical appliances and the second category of electrical appliances includes parsing the power consumption data of any target date, and the power consumption data parsing method of any target date is:

[0016] Analyze the historical electricity consumption data of the target date to select a target time period that satisfies the conditions at the same time, wherein the conditions include: the electricity consumption in the time period is higher than the electricity consumption threshold, the time for which the electricity consumption in the time period is continuously higher than the electricity consumption threshold is greater than a preset time threshold, and the electricity consumption in the time period fluctuates regularly over time;

[0017] The target time period includes a first target time period and a second target time period; according to the amount of power consumption per unit time, the first target time period belonging to the first type of electrical appliance usage time period and the second target time period belonging to the second type of electrical appliance usage time period are identified;

[0018] The dehumidification power consumption data and the heating power consumption data in the historical power consumption data are obtained according to the first target time period and the second target time period.

[0019] In one embodiment of the present invention, according to the difference between the maximum value and the minimum value in the electricity consumption forecast data set, the method for determining the responsive electricity quantity for each date in the current year includes processing the responsive electricity quantity value for any single target date, and the method for processing the responsive electricity quantity value for any single target date is:

[0020] Determine the relevant date to which the maximum value and the minimum value in the power consumption forecast data set associated with the target date belong, and filter out the power consumption forecast sub-data of the determined relevant date from the power consumption forecast data; wherein the power consumption forecast sub-data includes the estimated power consumption in each time period within the relevant date;

[0021] According to the electricity consumption forecast sub-data, the responsive electricity data corresponding to the target date is calculated; and the responsive electricity data is used as the responsive electricity of the target date; wherein the responsive electricity data includes the responsive electricity values ​​corresponding to each time period under the target date.

[0022] In one embodiment of the present invention, the method of analyzing the electricity consumption patterns of the daily historical electricity consumption data of residents in each target area in the past N years includes: curve fitting or neural network model or point-to-point ratio method.

[0023] In one embodiment of the present invention, the multiple target areas include first-class areas, second-class areas, third-class areas and fourth-class areas, wherein the winter temperatures of the first-class areas and the second-class areas are higher than the winter temperatures of the third-class areas and the fourth-class areas, and the winter humidity of the first-class areas and the third-class areas is higher than the winter humidity of the second-class areas and the fourth-class areas.

[0024] In one embodiment of the present invention, the daily historical electricity consumption data of residents in the first and second types of areas from January to February in the past N years are analyzed for electricity consumption patterns; the daily historical electricity consumption data of residents in the third and fourth types of areas from December to February of the following year in the past N years are analyzed for electricity consumption patterns.

[0025] In a second aspect, in order to solve the above technical problems, the present invention provides a device for evaluating the potential of power users, which is used to evaluate the potential of power consumption of residents in southern China in winter, comprising:

[0026] A region division module is used to divide each province in the southern region into multiple target regions according to the temperature and humidity of each province in winter;

[0027] The electricity consumption prediction module is used to analyze the electricity consumption patterns of the daily historical electricity consumption data of residents in each target area in the past N years, and obtain the daily electricity consumption prediction data corresponding to each target area; wherein N is an integer greater than or equal to 3;

[0028] A data corresponding module is used to determine the electricity consumption forecast data corresponding to each relevant date from the electricity consumption forecast data according to each date of the current year, and obtain the electricity consumption forecast data set associated with each date of the current year; wherein the method for obtaining the relevant dates is: according to the daily average temperature and daily average humidity of each target area in the current year, the daily historical average temperature and daily historical average humidity of each target area in the past N years are matched respectively, and a plurality of relevant dates with the highest matching degree of the daily average temperature and the daily average humidity are determined;

[0029] The potential assessment module is used to determine the responsive power quantity for each date in the current year according to the difference between the maximum value and the minimum value in the power consumption forecast data set.

[0030] In a third aspect, in order to solve the above-mentioned technical problems, the present invention provides an electronic device, including a memory, a processor and a motor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the above-mentioned method for evaluating the potential of electricity users is implemented.

[0031] In a fourth aspect, in order to solve the above-mentioned technical problem, the present invention provides a storage medium storing computer executable instructions, and the computer executable instructions are used to execute the above-mentioned method for evaluating the potential of electricity users when executed by a computer processor.

[0032] The above technical solution of the present invention has the following beneficial effects compared with the prior art:

[0033] (1) The method and device for evaluating the potential of power users described in the present invention divide each province into multiple target areas according to the climate characteristics of each province in the region, fully considering the power consumption patterns of different regions, not only improving the accuracy of power consumption forecasting, but also enhancing the pertinence of power consumption response strategies and optimizing the allocation of power resources.

[0034] (2) The present invention divides different time periods and simulates electricity consumption habits according to the climate characteristics of each province in the region, and then simulates the types of electrical appliances used and electricity consumption behaviors in different climates, thereby achieving a scientific and accurate simulation and evaluation of the actual winter heating electricity consumption of southern residents, obtaining accurate and reliable predicted electricity consumption and predicted responsive electricity consumption, and thus achieving an accurate and reliable quantitative evaluation of the southern residents' electricity consumption potential in winter.

[0035] (3) The present invention analyzes the power usage patterns of the first and second category electrical appliances independently, thereby avoiding mutual interference between the data of the two during the power usage pattern analysis process, thereby improving the reliability and accuracy of the power usage pattern analysis, and also improving the reliability and accuracy of the subsequent power usage potential analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein:

[0037] Figure 1 A flowchart of a method for evaluating the potential of power users in a preferred embodiment of the present invention;

[0038] Figure 2 A structural diagram of an electronic device in a preferred embodiment of the present invention;

[0039] Figure 3 Schematic diagram of computer structure in a preferred embodiment of the present invention.

[0040] Explanation of the reference numerals in the specification: 6, electronic device; 60, processor; 61, memory; 62, computer program; 70, computer; 71, computer processor; 72, internal memory; 73, button; 74, display; 75, wireless communication module. DETAILED DESCRIPTION

[0041] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0042] Embodiment 1

[0043] Reference Figure 1As shown, the present invention provides a method for evaluating the potential of power users, which is used to evaluate the potential of electricity consumption of residents in southern China in winter, including but not limited to the following steps:

[0044] S101. Divide each province in the southern region into multiple target areas according to the temperature and humidity of each province in winter; the temperature and humidity of different target areas are not completely the same;

[0045] S102, respectively, analyze the daily historical electricity consumption data of residents in each target area in the past N years to obtain daily electricity consumption forecast data corresponding to each target area; wherein N is an integer greater than or equal to 3;

[0046] S103. According to each date of the current year, determine the electricity consumption forecast data corresponding to each relevant date from the daily electricity consumption forecast data, and obtain the electricity consumption forecast data set associated with each date of the current year; wherein the method for obtaining the relevant dates is: according to the daily average temperature and daily average humidity of each target area in the current year, respectively match the daily historical average temperature and daily historical average humidity of each target area in the past N years, and determine multiple relevant dates with the highest matching degree of daily average temperature and daily average humidity;

[0047] S104: Determine the responsive power for each date in the current year according to the difference between the maximum value and the minimum value in the power consumption forecast data set.

[0048] The embodiment of the present invention provides a method for evaluating the potential of power users. According to the temperature and humidity of each province in the southern region in winter, each province is divided into multiple target areas, and more accurate daily power consumption forecast data can be obtained. The method of the present invention not only improves the accuracy of power consumption forecasting, but also enhances the pertinence of power consumption response strategies and optimizes the allocation of power resources. In addition, it also improves user satisfaction, supports the integration of renewable energy, promotes energy conservation and emission reduction, enhances market competitiveness, and provides support for policy formulation.

[0049] Generally, there is a big difference in climate between the north and south. Compared with the north, the temperature and humidity in the south are higher in winter. Therefore, for residents in the south, there is a need for heating in winter and a need for dehumidification. As for heating demand, since centralized heating is widely used in the north and is supplied for a long time in winter, while centralized heating is lacking in the south, electric heating by residents is a very common way of heating in winter. As for dehumidification demand, there is basically no dehumidification demand in the dry winter in the north, but the humidity in the south is still high in winter. Under high humidity, the human body is more likely to feel cold and uncomfortable. Therefore, the dehumidification demand is much higher than that in the north. It can be seen that the winter electricity consumption of residents in the north and south is very different. If the winter electricity consumption potential of residents in the north and south is directly evaluated as a whole without distinction, or if the winter electricity consumption potential of residents in the north is only evaluated, the evaluation results obtained are difficult to adapt to the electricity consumption of residents in the south, which makes the final potential evaluation results less accurate and reliable for residents in the south, and it is difficult to provide reliable reference data for regulation and decision-making for power grid companies in the south such as the China Southern Power Grid. In addition, in addition to geographical factors, seasonal factors will also greatly affect residents' electricity consumption. In view of this, the embodiments of the present invention fully consider regional and seasonal factors.

[0050] Specifically, for step S101, the embodiment of the present invention divides the provinces in the southern region according to the climate characteristics of the southern region in winter, wherein the climate characteristics are preferably temperature and humidity. For the temperature of different provinces, the provinces in the southern region are divided into warm and cold regions. For humidity, the provinces in the southern region are divided into high humidity and medium humidity regions. Based on the division of temperature and humidity, the provinces in the southern region are divided into four categories, and the division criteria are as follows:

[0051] The first category of areas includes: provinces and regions that are both warm and high humidity areas;

[0052] The second type of area includes: provinces and regions that belong to both warm and medium humidity areas;

[0053] The third category of areas includes: provinces and regions that are both cold and high humidity areas;

[0054] The fourth type of area includes provinces and regions that belong to both cold and medium-humidity areas.

[0055] According to the divided areas, it can be concluded that the winter temperature of the first and second types of areas is higher than that of the third and fourth types of areas; the winter humidity of the first and third types of areas is higher than that of the second and fourth types of areas. Among them, the multiple target areas include the first, second, third and fourth types of areas, and the four types of areas can be collectively referred to as target areas.

[0056] The high and low temperatures in winter mainly affect the differences in residents' heating needs, while the high and low humidity in winter mainly affect the differences in residents' dehumidification needs, and the two types of needs are different. At the same time, there are large differences in the influencing factors of temperature and humidity. For example, the humidity difference is related to the degree of proximity to the equator, and it is also related to whether it is coastal and the geography of the province. The influencing factors are more complicated. Therefore, for a single province, its temperature and humidity are not simply positively or negatively correlated, and it is difficult to achieve accurate analysis of the heating and dehumidification electricity demands of all southern provinces at the same time by analyzing only the temperature or humidity. Therefore, the embodiment of the present invention proposes to further subdivide the cities in the southern region based on temperature and humidity to achieve a more detailed and accurate demand division for each province.

[0057] For example, based on the average temperature from November to March of the following year in the provinces in the southern region, the provinces in the southern region are divided into two categories: warm areas and cold areas, wherein the average temperature from November to March of the following year in the provinces in the warm areas is higher than the average temperature from November to March of the following year in the provinces in the cold areas. Based on the average winter humidity in the provinces in the southern region, the provinces in the southern region are divided into two categories: warm areas and cold areas, wherein the average winter temperature in the provinces in the warm areas is higher than the average winter temperature in the provinces in the cold areas.

[0058] In practical applications, the winter duration of various provinces in the southern region varies greatly. For example, provinces close to or at the equator, such as Hainan, Guangdong and Guangxi, have the shortest winter, generally 1-2 months, mainly concentrated between December of each year and February of the following year. On the contrary, the closer to the equator, the farther away from the equator and closer to the north, such as Jiangsu, Hubei and Anhui, have the longest winter, generally 3-4 months, mainly concentrated between November of each year and March of the following year. Therefore, in order to achieve accurate temperature and humidity classification of provinces in the southern region, the embodiment of the present invention sets the time range of temperature and humidity analysis to November to March of the following year, so that the winter data of all provinces in the southern region can be fully counted to the greatest extent, ensuring the integrity of the temperature and humidity sample data. Among them, the temperature and humidity data of specific provinces come from the local meteorological bureau. That is, in the embodiment of the present invention, the specific months included in winter may be different according to the actual situation, for example, in S101, it can be November to March of the following year, and in some subsequent embodiments, winter includes January to February or December to February of the following year, so it is specifically determined according to the specific situation of the embodiment in which it is located.

[0059] For example, after obtaining the local temperature and humidity data of each province in the southern region from November to March of the following year, the corresponding specific temperature and humidity data with certain statistical significance can be calculated, such as average temperature, average humidity, minimum temperature, maximum humidity, etc. Then, based on the calculated specific temperature and humidity data, each province is classified, and the provinces with lower specific temperature data are classified into cold areas, while the provinces with higher specific temperature data are classified into warm areas; the provinces with lower specific humidity data are classified into medium humidity areas, while the provinces with higher specific humidity data are classified into high humidity areas. Among them, the embodiment of the present invention does not make too many restrictions on the specific temperature and humidity classification method, which can be determined according to actual conditions. For example, in some optional embodiments, some classification models based on machine learning can be used for self-learning data analysis and classification, and in other optional embodiments, the temperature and humidity data can also be divided by setting temperature thresholds and humidity thresholds.

[0060] Exemplarily, taking the average temperature and average humidity as specific temperature and humidity data, we can further calculate the average temperature and average humidity of all provinces in the southern region based on the average temperature and average humidity of each province, and then classify the provinces whose average temperature is higher than the overall average temperature into warm areas, and classify the provinces whose average temperature is lower than the overall average temperature into cold areas; classify the provinces whose average humidity is higher than the overall average humidity into high humidity areas, and classify the provinces whose average humidity is lower than the overall average humidity into medium humidity areas.

[0061] Exemplarily, taking the average temperature and average humidity as specific temperature and humidity data for illustration, a fixed temperature threshold and humidity threshold can be pre-set. For example, the temperature threshold can be set to 10°, and the humidity threshold can be set to 75%. On this basis, provinces with average temperatures higher than the temperature threshold are classified as warm areas, while provinces with average temperatures lower than the temperature threshold are classified as cold areas; provinces with their own average humidity higher than the humidity threshold are classified as high humidity areas, while provinces with their own average humidity lower than the humidity threshold are classified as medium humidity areas.

[0062] Furthermore, for step S102, the electricity consumption analysis strategies used in each type of area are not exactly the same. Daily historical electricity consumption data include: historical electricity consumption corresponding to each time period of each day, rather than simply daily historical total electricity consumption. The winter electricity consumption forecast data for each type of area includes: for this type of area, the estimated electricity consumption of residents in each time period every day in winter. It should be understood that the result at this time is a forecast result, and the date of the corresponding winter electricity consumption forecast data only has a month and day mark but does not have a specific year. For example, assuming that winter includes January and February, the winter electricity consumption forecast data now includes the estimated electricity consumption in each time period of each day in January and February, but there is no specific year.

[0063] Specifically, the historical data range of the first type of regional power consumption law analysis specifically includes the daily historical power consumption data of residents from January to February every winter in the last N years; the historical data range of the second type of regional power consumption law analysis specifically includes the daily historical power consumption data of residents from January to February every winter in the last N years; the historical data range of the third type of regional power consumption law analysis specifically includes: the daily historical power consumption data of residents from December every winter to February of the following year in the last N years; the historical data range of the fourth type of regional power consumption law analysis specifically includes: the daily historical power consumption data of residents from December every winter to February of the following year in the last N years. That is, in the embodiment of the present invention, if there is no special explanation, the default of historical years refers to the last N years, where N is an integer greater than or equal to 3.

[0064] The range of the years can be set according to actual needs, for example, it can be the past 3 years, 5 years, 10 years or 15 years, etc. The winter temperature and humidity data of the current year can be defined as the temperature and humidity data of November of the current year, December of the current year, January of the next year, February of the next year and March of the next year. For example, for 2020, the winter temperature and humidity data of the current year include: the temperature and humidity data of November 2020, December 2020, January 2021, February 2021 and March 2021.

[0065] In order to make the final potential assessment result more valuable for actual reference, the embodiment of the present invention also distinguishes the main peak months of heating and dehumidification power consumption for different types of regions.

[0066] Specifically, for the first and second category areas with high temperatures, only the data from January to February each winter are analyzed and a series of operations such as subsequent prediction are performed. The reason is that in the relatively warm first and second category areas, due to the short winter time, the main cold period is concentrated in January each year. Combined with the characteristics that the humidity in the southern region will increase significantly in late winter and early spring, the time range of the analysis is determined to be January-February, that is, this period is the peak demand period for heating and dehumidification for southern residents in this region, and the responsiveness is the largest. Therefore, the value of the sample is the greatest for the evaluation of electricity consumption potential. Although in theory, a larger range of sample data can be introduced for analysis and prediction operations, more noise will be introduced as the sample data increases, and in the process of analysis and prediction, the impact on the analysis of the peak demand period is also greater, which will be detrimental to the accuracy of the analysis of the responsiveness of the peak demand period. For this reason, the embodiment of the present invention preferably uses the data from January to February each winter as the sample range here.

[0067] For the third and fourth types of areas with low temperatures, only the data from December to February of the following year are analyzed and a series of subsequent operations such as prediction are performed. The reason is that the winter is long and the main cold period is concentrated from December to January of the following year. Combined with the characteristics of a significant increase in humidity in late winter and early spring in the southern region, the time range of the analysis is determined to be from December to February of the following year, that is, this period is the peak demand period for heating and dehumidification for southern residents in this region, and the responsiveness is the largest. Therefore, the sample has the greatest value for the assessment of electricity consumption potential. Based on the same reasons mentioned above, the data from December to February of the following year in each winter can be used as the sample range to accurately divide the actual heating and dehumidification demand range of the third and fourth types of areas in winter with the greatest accuracy, making the subsequent data analysis more accurate and effective, and thus making the final responsiveness analysis results more accurate and reliable.

[0068] Furthermore, based on the distinction between regions and months, and combined with the characteristics of heating and dehumidification electricity demand in the four types of regions, appropriate electricity consumption analysis and forecasting strategies are designed respectively.

[0069] Specifically, for the first type of regions: taking into account the simultaneous needs of heating and dehumidification, when analyzing the electricity consumption data of southern residents from January to February of previous years, we distinguish and identify the electricity consumption data containing the first type of electrical appliances and the second type of electrical appliances, and at the same time combine the daily electricity consumption, electricity consumption time period, daily average temperature and daily average humidity data from January to February of previous years to conduct a detailed potential assessment, so as to obtain the electricity consumption forecast for the region from January to February in the next winter.

[0070] For the second type of regions: Considering that their demand is mainly concentrated on heating, when analyzing the electricity consumption data of southern residents from January to February of previous years, we do not distinguish between the first and second types of appliances. Instead, we directly identify the data related to the second type of appliances from the electricity consumption data, and at the same time combine the daily electricity consumption, electricity consumption time period, daily average temperature and daily average humidity data from January to February of previous years to conduct a detailed potential assessment, so as to obtain the electricity consumption forecast for the region from January to February in the next winter.

[0071] For the third type of area: Taking into account its strong demand for heating and dehumidification, when analyzing the electricity consumption data of southern residents from December to February of the following year, we distinguish and identify the electricity consumption data of the first type of electrical appliances and the second type of electrical appliances, and at the same time combine the daily electricity consumption, electricity consumption time period, daily average temperature and daily average humidity data from December to February of the following year to conduct a detailed potential assessment, so as to obtain the electricity consumption forecast for the region from December to February of the following year in the next winter.

[0072] For the fourth type of region: Considering that its demand is mainly concentrated on heating, when analyzing the electricity consumption data of southern residents from December to February of the following year, we do not distinguish between the first and second types of electrical appliances. Instead, we directly identify the data related to the second type of electrical appliances from the electricity consumption data, and at the same time combine the daily electricity consumption, electricity consumption time period, daily average temperature and daily average humidity data from December to February of the following year to conduct a detailed potential assessment, so as to obtain the electricity consumption forecast for the region from December to February of the following year in the next winter.

[0073] The embodiment of the present invention accurately distinguishes the climate characteristics of various provinces in the southern region to divide the winter time periods and simulate electricity consumption habits. Combined with the types of electrical appliances used in winter and the simulation of electricity consumption behavior, it can achieve scientific and accurate simulation and evaluation of the actual southern residents' winter heating electricity consumption, obtain accurate and reliable predicted electricity consumption and predicted responsive electricity consumption, and achieve accurate and reliable quantitative evaluation of the southern residents' winter electricity consumption potential. Among them, the method for obtaining electricity consumption prediction data is:

[0074] S201, analyzing the historical electricity consumption data of the first category of electrical appliances and the second category of electrical appliances to obtain dehumidification electricity consumption data and heating electricity consumption data respectively;

[0075] S202, respectively analyzing the dehumidification electricity consumption data and the heating electricity consumption data to obtain corresponding dehumidification electricity consumption prediction data and heating electricity consumption prediction data;

[0076] S203. According to different time periods, the dehumidification electricity consumption prediction data and the heating electricity consumption prediction data are combined to obtain the electricity consumption prediction data.

[0077] Among them, the first category of electrical appliances mainly refers to electrical equipment with dehumidification function, such as dehumidifiers (also known as dehumidifiers, dryers, dehumidifiers, etc.). The second category of electrical appliances mainly refers to electrical equipment with heating function, such as air conditioners, electric heaters (such as electric floor heating, oil heaters, etc.), electric water heaters, electric blankets, etc. It should be noted that considering that air conditioners also have dehumidification functions in actual applications, in theory, air conditioners can be classified as both the first and second categories of electrical appliances. However, under normal circumstances, the dehumidification power consumption of air conditioners will be much less than the heating power consumption. Therefore, when analyzing and predicting the power consumption of electrical appliances, there will be obvious differences in power consumption between the two.

[0078] After obtaining the dehumidification power forecast data and the heating power forecast data, the embodiment of the present invention will perform independent power consumption law analysis on the two data to obtain their respective forecast data. The advantage is that the power consumption of the first type of electrical appliances and the second type of electrical appliances is quite different, and there is no necessary correlation between the use time, that is, there is no strong correlation in terms of time and power consumption, and it is even foreseeable that there will be large differences. In the case of high dehumidification demand, the proportion of the first type of electrical appliances to the residential power load is also relatively high compared with other common electrical appliances, that is, the dehumidification power data also has a greater impact on the entire residential power data. Under these backgrounds, if the power consumption data of the first type of electrical appliances and the second type of electrical appliances are directly analyzed as a whole data, it will inevitably lead to the mutual influence of the two. And because the use demand of the first type of electrical appliances in the first type of area with high humidity is high, the power consumption law of the power consumption data of the second type of electrical appliances will also be higher, which makes the final analysis of the power consumption law of the first type of electrical appliances and the second type of electrical appliances inaccurate and unreliable. Therefore, the embodiment of the present invention analyzes the power consumption patterns of the two independently, avoiding mutual interference between the data of the two during the power consumption pattern analysis process, thereby greatly improving the reliability and accuracy of the power consumption pattern analysis, and also improving the reliability and accuracy of the subsequent power consumption potential analysis.

[0079] Furthermore, in step S201, the power consumption data of the first and second electrical appliances are parsed for the historical power consumption data, including parsing any target date. It should be noted that the target date means any date that needs to be processed among all dates in the current winter. The target date is described as being distinguished from other dates, but its essence can be any date among all dates in the current winter. The method for parsing the power consumption data of any target date is as follows:

[0080] S301, analyzing the historical electricity consumption data of the target date, and selecting the target time period that meets the conditions at the same time, wherein the conditions include: the electricity consumption in the time period is higher than the electricity consumption threshold, the time for which the electricity consumption in the time period is continuously higher than the electricity consumption threshold is greater than a preset time threshold, and the electricity consumption in the time period fluctuates regularly with time;

[0081] S302, according to the amount of power consumption in a unit time, identifying a first target time period belonging to the first type of electrical appliance use time period and a second target time period belonging to the second type of electrical appliance use time period; wherein the target time period includes the first target time period and the second target time period;

[0082] S303. Obtain dehumidification power consumption data and heating power consumption data in the historical power consumption data according to the first target period and the second target period.

[0083] Further, in step S301, compared with some commonly used electrical appliances (such as refrigerators, washing machines, computers, televisions, microwave ovens, etc.), both the first and second types of electrical appliances have the significant characteristics of high power, long single continuous use time, and obvious periodicity in power change. For example, for dehumidifiers, the power is generally concentrated in 200 watts-700 watts, and the time of each use is generally more than 2 hours. In the process of operation, the overall power change is first stabilized for a long period of time, and then periodically decreases and increases. The reason for the power change rule is that dehumidification is first performed at high power, and the power is reduced and the humidity is dynamically adjusted after the humidity reaches a certain value, that is, the power is increased when the humidity increases. Similarly, when the air conditioner is heating, the power is generally more than 1000 watts, and the time of each use is basically several hours. In the process of operation, the overall power change is first stabilized for a long period of time, and then periodically decreases and increases. The reason is similar to that of the dehumidifier, mainly because high power heating is performed first, and then the temperature is dynamically adjusted to keep the temperature relatively stable. Therefore, the embodiment of the present invention analyzes the power consumption data of each time period in the historical power consumption data, and selects the time periods that simultaneously meet the following conditions: large power consumption (greater than a preset power consumption threshold), long maintenance time (power consumption continues to be greater than the power consumption threshold for a longer time than the preset time threshold), and power consumption fluctuates regularly over time. For example, within a period of time, the power consumption changes multiple times, and the time interval and amplitude of each change are within a preset range (such as the difference between each time interval is less than a preset time difference threshold, such as the difference between each amplitude is less than a preset amplitude difference threshold), that is, there will be regular changes in time and power consumption. In this way, the target time period containing power consumption data of the first category of electrical appliances and the second category of electrical appliances can be selected from the historical power consumption data.

[0084] Further, in step S302, after determining the time period that satisfies the three conditions at the same time, identify whether each target time period belongs to the use time period of the first category of electrical appliances or the use time period of the second category of electrical appliances according to the amount of electricity consumption in the unit time; the electricity consumption data associated with the use time period of the first category of electrical appliances in the historical electricity consumption data is used as the dehumidification electricity consumption data corresponding to the first category of electrical appliances, and the electricity consumption data associated with the use time period of the second category of electrical appliances in the historical electricity consumption data is used as the heating electricity consumption data corresponding to the second category of electrical appliances. Specifically, the first category of electrical appliances and the second category of electrical appliances are further distinguished according to the amount of electricity consumption (i.e., power consumption) in the unit time. Since the power difference between the first category of electrical appliances and the second category of electrical appliances is large, the power consumption threshold that can distinguish the first category of electrical appliances and the second category of electrical appliances can be determined by pre-research and calibration, and the target time period is further subdivided based on this, so as to determine the first target time period containing the power consumption data of the first category of electrical appliances and the corresponding power consumption data, and at the same time determine the second target time period containing the power consumption data of the second category of electrical appliances and the corresponding power consumption data. Therefore, the dehumidification power consumption data corresponding to the first type of electrical appliances (recording the first target period and the corresponding power consumption data) and the heating power consumption data corresponding to the second type of electrical appliances (recording the second target period and the corresponding power consumption data) can be obtained respectively every day.

[0085] In order to more clearly illustrate steps S201 to S203, the following example is given:

[0086] Example 1, using the first historical electricity consumption data of each province in the first category area in January-February of the past N years. For the first category of warm and humid areas, not only heating is an important need of residents in winter, but dehumidification is also an important need of residents in winter. Therefore, the use of the first category of electrical appliances for dehumidification is as important as the use of the second category of electrical appliances for heating. Based on this, the embodiment of the present invention performs data analysis on the first historical electricity consumption data, and parses out the electricity consumption data of the first category of electrical appliances and the electricity consumption data of the second category of electrical appliances in different time periods, that is, the first dehumidification electricity consumption data and the first heating electricity consumption data. Exemplarily, the first dehumidification electricity consumption data and the first heating electricity consumption data of each province in the first category area in January-February of the past N years are analyzed respectively to obtain the corresponding first dehumidification electricity consumption forecast data and the first heating electricity consumption forecast data. The electricity consumption data of the first dehumidification electricity consumption forecast data and the first heating electricity consumption forecast data are merged according to the time period to obtain the first electricity consumption forecast data corresponding to the first category area. After obtaining the independent first dehumidification electricity consumption forecast data and the first heating electricity consumption forecast data, the electricity consumption data of the two are merged according to the time period coordinates, so as to obtain the first electricity consumption forecast data that is complete for the first category of areas and contains accurate electricity consumption forecast data for the first category of electrical appliances and the second category of electrical appliances.

[0087] Example 2, using the second historical electricity consumption data of each province in the second category area in the past N years from January to February every day; parsing the electricity consumption data of the second category of electrical appliances on the second historical electricity consumption data every day, and obtaining the second heating electricity consumption data corresponding to the second category of electrical appliances every day; analyzing the second heating electricity consumption data of each province in the second category area in the past N years from January to February every day, and obtaining the corresponding second winter electricity consumption forecast data (also referred to as the second heating electricity consumption forecast data). The basic principles, implementation details and beneficial effects of Example 2 are basically the same as those of the first category area analysis strategy implementation example shown in Example 1. Therefore, the same parts are not repeated here. The difference is that since the humidity in each province in the second category area is not particularly high, the residents' dehumidification demand is relatively low. Based on this, the demand for the use of the first category of electrical appliances is much lower than that of the first category of areas, and the actual survey also confirms this point. The use of the first category of electrical appliances in the second category of areas is less, and the difference is very large relative to the electricity consumption of the second category of electrical appliances. Therefore, in this example, there is no need to parse and analyze the electricity consumption data of the first category of electrical appliances separately. However, since heating demand is still an extremely important demand in the second-category area in winter, it is still necessary to analyze the electricity consumption data of the second-category appliances separately and conduct targeted regularity analysis to avoid excessive influence of the electricity consumption data of other appliances on the regularity analysis of the electricity consumption data of the second-category appliances. At the same time, by eliminating the electricity consumption data of non-second-category appliances, the cleanliness of the sample data for subsequent responsive power analysis can also be ensured to avoid analyzing the non-target heating and dehumidification demand potential. This can effectively improve the reliability and accuracy of the potential assessment of the final power users.

[0088] Example three, using the third historical electricity consumption data of each province in the third category area from December to February of the following year in the past N years; parsing the electricity consumption data of the first category of electrical appliances and the third heating electricity consumption data of the second category of electrical appliances in the third historical electricity consumption data of each day, respectively obtaining the third dehumidification electricity consumption data corresponding to the first category of electrical appliances and the third heating electricity consumption data corresponding to the second category of electrical appliances on a daily basis. Analyze the third dehumidification electricity consumption data and the third heating electricity consumption data of each province in the first category area from December to February of the following year in the past N years, respectively, to obtain the corresponding third dehumidification electricity forecast data and third heating electricity forecast data. Merge the electricity consumption data of the third dehumidification electricity forecast data and the third heating electricity forecast data according to the time period, and obtain the third winter electricity forecast data corresponding to the third category area. The basic principles, implementation details, and beneficial effects of this example are basically the same as those of the first category area analysis strategy implementation example shown in Example 1. Therefore, the same parts will not be repeated here. The difference is that this example specifically expands the winter analysis coverage months and includes December, a month with low temperatures, into the analysis sample in view of the long winters in the southern cold regions. Therefore, this example can better adapt to the analysis and prediction of the heating and dehumidification electricity consumption potential of residents in the southern cold regions.

[0089] Example 4, using the fourth historical electricity consumption data of each province in the fourth category area from December to February of the following year in the past N years; parsing the electricity consumption data of the second category of electrical appliances on the fourth historical electricity consumption data every day, and obtaining the fourth heating electricity consumption data corresponding to the second category of electrical appliances every day. Analyze the fourth heating electricity consumption data of each province in the fourth category area from December to February of the following year in the past N years, and obtain the corresponding fourth winter electricity consumption forecast data (also referred to as the fourth heating electricity consumption forecast data). The basic principles, implementation details and beneficial effects of this example are basically the same as those of the second category regional analysis strategy implementation example shown in Example 2, so the same parts are not repeated here. The difference is that this example specifically expands the coverage months of winter analysis in view of the long winter in low temperature and cold areas in the south, and includes December with low temperature in the analysis sample. To this end, this example can better adapt to the analysis and prediction of the heating electricity potential of residents in low temperature and cold areas in the south in winter.

[0090] It can be understood that the first historical electricity consumption data in Example 1, the second historical electricity consumption data in Example 2, the third historical electricity consumption data in Example 3, and the fourth historical electricity consumption data in Example 4 are essentially historical electricity consumption data, and only the regions to which they belong are different, so they are named differently. The union of the four historical electricity consumption data is the historical electricity consumption data for the entire southern region. Similarly, the first winter electricity consumption forecast data, the second winter electricity consumption forecast data, the third winter electricity consumption forecast data, and the fourth winter electricity consumption forecast data are essentially winter electricity consumption forecast data, and only the regions to which they belong are different, so they are named differently. The union of the four electricity consumption forecast data is the winter electricity consumption forecast data for the entire southern region.

[0091] Among them, the embodiments of the present invention do not impose too many restrictions on the specific electricity consumption pattern analysis strategy used, and can be set according to actual needs. For example, in some optional embodiments, a curve fitting method can be used to perform curve fitting on the first dehumidification electricity consumption data and the first heating electricity consumption data of each day in January and February of the past N years, respectively, to establish a first-category electrical appliance load curve and a second-category electrical appliance load curve. Based on the fitted curve, the power consumption forecast values ​​of the first-category electrical appliances and the second-category electrical appliances in each time period are determined, thereby obtaining the required first dehumidification electricity consumption forecast data and the first heating electricity consumption forecast data. In other optional embodiments, the first dehumidification electricity consumption data and the first heating electricity consumption data of each day in January and February of the past N years can also be analyzed based on a pre-trained neural network model, thereby determining the power consumption forecast values ​​of the first-category electrical appliances and the second-category electrical appliances in each time period, thereby obtaining the required first dehumidification electricity consumption forecast data and the first heating electricity consumption forecast data. In some other optional embodiments, the point-to-point ratio method can also be combined to analyze the daily first dehumidification power consumption data and the first heating power consumption data in January and February of the past N years, and predict and determine the power consumption forecast values ​​of the first and second category electrical appliances in each time period, and then obtain the required first dehumidification power consumption forecast data and first heating power consumption forecast data. At the same time, by eliminating the power consumption data of non-first category electrical appliances and non-second category electrical appliances, the cleanliness of the sample data that can respond to the subsequent power analysis can also be ensured, avoiding the analysis of non-target heating and dehumidification demand potential.

[0092] After completing the electricity consumption forecast data for heating and dehumidification of residents in each area based on their respective potential assessment strategies, we then match these data with the weather on each winter date of that year, determine multiple forecast data that best match each day of that winter, and determine the two daily electricity consumption data with the largest and smallest electricity consumption. This way, we can obtain extremely detailed potential conditions for southern residents in different southern provinces and in different winter months.

[0093] Specifically, for step S103, the daily historical average temperature and daily historical average humidity of each province in the first, second, third and fourth categories of regions in the winter of previous years are obtained, and the daily average temperature and daily average humidity of each province in the first, second, third and fourth categories of regions in the winter of the current year are obtained, and based on the daily average temperature and daily average humidity, the daily historical average temperature and daily historical average humidity of the previous years in the own region are matched with the daily historical average temperature and daily historical average humidity on a daily basis, and multiple relevant dates with the highest matching degree with the daily weather in the winter of the current year are determined. Among them, the current year refers to the current year, that is, the real-time year when the embodiment of the present invention is executed.

[0094] It can be understood that the range of months included in the winter corresponding to each type of area in S103 is consistent with that in the above S102 and related examples, so as to ensure the consistency of the time range of the previous and subsequent data, and thus ensure the effectiveness of the subsequent potential analysis. Specifically, for the first and second types of areas, the winter of the current year refers to January and February of the current year; for the third and fourth types of areas, the winter of the current year refers to December of the previous year and January and February of the current year.

[0095] On the basis of clarifying the range of months included in winter, the temperature data and humidity data of each province in each type of region in the winter of that year can be obtained from the local meteorological bureau, and based on these data, the average temperature and average humidity of each day in the winter months can be calculated, so as to obtain the daily average temperature and daily average humidity of each province in the four regions in the winter of that year. Among them, it should be specially noted that for dates that have not arrived in that year, the weather forecast data of the meteorological bureau shall prevail. For example, assuming that the current date is January 1, 2024, at this time, January 4, 2024 to February 29, 2024 are all dates that have not yet arrived, and there is no real weather data. For the dates within this period, the weather forecast data of the local meteorological bureau (including the predicted daily temperature and humidity) can be used as the reference data for these dates to calculate the corresponding daily average temperature and daily average humidity. If the credibility of the weather forecast data is not high, for example, the date to be analyzed is 45 days after the current date, or the forecast confidence output by the meteorological bureau is less than 60%, then the average temperature and humidity of the corresponding dates in previous years (the last N years) can be used as the corresponding daily average temperature and daily average humidity. For example, assuming that the current date is January 1, 2024, and February 28, 2024 exceeds the interval of 45 days, the historical temperature data and historical humidity data on February 28 in the last N years can be used as reference data for February 28, 2024 to calculate the average temperature and average humidity on February 28, 2024.

[0096] Specifically, after determining the daily average temperature and daily average humidity in a certain area in the winter of that year, the daily historical average temperature and daily historical average humidity in the area can be matched day by day based on these data to find the historical date that is most similar to the weather of each date of that year. Among them, since there are N groups of data for each day in the historical data, the difference can be calculated to determine the dates with the smallest difference, that is, the weather is closest to the highest matching degree.

[0097] Specifically, the difference calculation method is as follows: Assume that the number of days in winter each year is M, where M is the total number of days from January to February or the total number of days from December to February of the following year, and the specific M value is determined according to which type of area is to be calculated. At this time, the temperature and humidity data of the past years can be converted into a three-dimensional matrix of M×N×2, which means: there are M days (M dates) in winter each year, and there are N groups of weather data every day in N years, and each group of weather data contains 1 historical average temperature and 1 historical average humidity, a total of 2 data. On this basis, for the M days in winter of the year, each day can be compared with the N groups of data of each date in the three-dimensional matrix based on the average temperature and average humidity of the day to obtain the difference, thereby obtaining M differences. Finally, the first H dates with the smallest difference are used as the multiple historical dates with the highest weather matching degree. Where H is an integer greater than 1, which can be set according to actual needs, for example, it can be 2, 3, 4, 5 or 6. It should be understood that the relevant date at this time is used to correspond to the estimated electricity consumption in the winter electricity consumption forecast data, and therefore only includes a month and day mark without a specific year.

[0098] Exemplarily, when calculating the difference between a single-day weather data and N groups of weather data on a certain date, it is possible to choose to calculate the absolute value of the difference between the temperature data and the humidity data for each group, thereby obtaining N absolute values ​​of the temperature difference and N absolute values ​​of the humidity difference. Then the N absolute values ​​of the temperature difference are normalized respectively, and the N absolute values ​​of the humidity difference are normalized respectively. Finally, the normalized N absolute values ​​of the temperature difference and the N absolute values ​​of the humidity difference are summed to obtain the difference between the weather on the single day and the weather on the certain date. Based on this method, M dates are compared respectively to obtain M differences. It should be noted that in order to match dates with similar weather as much as possible, the embodiment of the present invention defaults to the same weight for the difference between temperature and humidity, that is, to find dates with the same or similar temperature and humidity as much as possible. The overall temperature and humidity of the date matched in this way will be as close to the date of the year as possible, which can be used to make the maximum possible analysis of the subsequent heating and dehumidification electricity demand potential.

[0099] Furthermore, in step S103, for each date in the winter of the current year, the predicted electricity consumption data required for daily heating and dehumidification corresponding to each relevant date is determined from the winter electricity consumption forecast data, and the electricity consumption forecast data set associated with each date of the current year is obtained, and the predicted electricity consumption data with the maximum and minimum daily electricity consumption are selected from the electricity consumption forecast data set.

[0100] Specifically, in step S104, the difference between the maximum and minimum predicted power consumption data is calculated to obtain the total responsive power value corresponding to each date in the winter of that year. The method for processing the responsive power value of any single target date is as follows:

[0101] S401, determining the relevant dates to which the maximum value and the minimum value in the electricity consumption forecast data set associated with the target date belong, and filtering out the electricity consumption forecast sub-data of the determined relevant dates from the electricity consumption forecast data; wherein the electricity consumption forecast sub-data includes the estimated electricity consumption in each time period within the relevant date;

[0102] S402. Calculate the responsive electricity data corresponding to the target date based on the electricity consumption forecast sub-data; and use the responsive electricity data as the responsive electricity on the target date; wherein the responsive electricity data includes the responsive electricity values ​​corresponding to each time period on the target date.

[0103] Thus, the predicted electricity consumption data for the two relevant dates, the maximum and the minimum, corresponding to each of the M dates in the current winter can be obtained. Among them, the minimum predicted electricity consumption data is the theoretical minimum value of electricity required for heating and dehumidification on that day; the maximum predicted electricity consumption data is the theoretical maximum value of electricity required for heating and dehumidification on that day. The difference between the two (which can be refined to the difference in different time periods) is the adjustable potential space of residents' heating and dehumidification electricity consumption on that day, that is, the response amount.

[0104] Take an example for illustration. Assume that the winter of the year includes 60 days from January 1, 2024 to February 29, 2024, that is, M is 60 days, and H is set to 5. That is, for each day in the winter of the year, 5 relevant dates will be matched. At this time, the embodiment of the present invention will calculate the predicted power consumption data required for heating and dehumidification corresponding to each of the 5 dates in the winter power consumption forecast data (that is, the total estimated power consumption obtained by summing the estimated power consumption of each time period under the date in the winter power consumption forecast data), and then filter out the predicted power consumption data with the largest and smallest predicted power consumption data, and also determine the corresponding 2 relevant dates. For example, assuming that for January 1, 2024, the relevant dates are January 1, January 2, January 3, January 4 and February 1, and the predicted power consumption data corresponding to the 5 relevant dates are 20 degrees, 22 degrees, 23 degrees, 21 degrees and 19 degrees respectively. At this time, it can be filtered out that the maximum predicted electricity consumption data is 23 degrees on January 3, and the minimum predicted electricity consumption data is 19 degrees on February 1, and the difference between the two is 4 degrees.

[0105] Understandably, first, the relevant dates of a certain date in winter of the year matched according to S103 are all relevant dates with weather very close to that date. Correspondingly, the heating and dehumidification needs of residents will be relatively close. However, even in exactly the same weather, there will be certain differences in the actual heating and dehumidification behaviors of residents. For example, on two days with the same temperature of 10° and humidity of 70%, residents may turn on the air conditioner for heating for a long time (such as 12 hours or even longer) on one day and only turn on the air conditioner for heating for a few hours (such as about 8 hours during sleep at night) on another day, and the dehumidification time may also be very different. This is also one of the characteristics of temperature control load and humidity control load. Therefore, the maximum and minimum predicted power consumption data on the relevant date represent the maximum and minimum values ​​of the possible power consumption of residents for heating and dehumidification under the weather on that date (since the sample analyzed is the residents of all provinces in the entire region, it is a representative statistical data), and finally the difference between the two is calculated, that is, the maximum predicted power consumption data is subtracted from the minimum predicted power consumption data to obtain the predicted power consumption difference. The predicted electricity consumption difference is the total responsive electricity consumption for heating and dehumidification of residential users during the day, that is, the electricity demand of residents for heating and dehumidification during the day has adjustable potential within the range of this predicted electricity consumption difference.

[0106] Still taking the above example of January 1, 2024, the maximum predicted electricity consumption data is 23 degrees on January 3, the minimum predicted electricity consumption data is 19 degrees on February 1, and the difference between the two is 4 degrees. At this time, it is explained that under the temperature and humidity conditions on January 1, 2024, the residents' expected minimum heating and dehumidification electricity consumption is 19 degrees, and the expected maximum heating and dehumidification electricity consumption is 23 degrees. There is a difference of 4 degrees of electricity that can be adjusted, that is, these 4 degrees of electricity are the total electricity consumption potential of residents under the temperature and humidity conditions on January 1, 2024 in the winter of that year.

[0107] As another optional embodiment of the present invention, the daily electricity consumption potential of residents can also be finely analyzed, so as to provide more fine and reliable responsive electricity for load aggregators and power grid companies with more fine electricity load regulation needs. In this case, after step S103, step S105 can be selected to be executed. Step S105 is described in detail as follows:

[0108] S105. Determine the power consumption forecast sub-data of the relevant date to which the maximum and minimum forecast power consumption data belong respectively from the winter power consumption forecast data, wherein the power consumption forecast sub-data includes the estimated power consumption in each time period of the relevant date. Based on the determined power consumption forecast sub-data, calculate the responsive power data corresponding to each date in the winter of that year, wherein each responsive power data includes the responsive power value corresponding to each time period of a single date.

[0109] Specifically, after determining the maximum and minimum predicted electricity consumption data, the corresponding detailed forecast data for each relevant date will continue to be determined from the winter electricity consumption forecast data, that is, the estimated electricity consumption for each time period on the relevant date (that is, the electricity consumption forecast sub-data). On this basis, for each date in the winter of that year, the difference in estimated electricity consumption can continue to be calculated in units of time periods and the absolute value can be taken. In this way, the specific responsive electricity value (that is, responsive electricity data) for each time period on a single date can be obtained. Then the responsive electricity data for each date in the winter of that year is obtained, that is, the specific responsive electricity value corresponding to each time period on each date. This can facilitate load aggregators or power grid companies to carry out targeted regulation of the responsive electricity situation in different time periods to achieve more refined electricity regulation.

[0110] Take an example for illustration. Assume that each day is divided into three time periods, namely: t0-t1, 8 am to 6 pm, during which residents generally carry out daytime activities, such as going to work and school; t1-t2, 6 pm to 8 pm, during which time is in the period from nighttime activities to bedtime preparation, and the probability of residents using the first type of dehumidification appliances is relatively high; t2-t3, 8 pm to 8 am, during which time is in the bedtime activities and sleep time period, and the probability of residents using the second type of heating appliances is relatively high. On this basis, for the two relevant dates selected corresponding to a certain date in winter of that year, the embodiment of the present invention can compare the power consumption of the two relevant dates in the three time periods respectively, calculate the absolute value of the difference, and thus obtain the responsive power values ​​of the residents in the three time periods. Based on this, the load aggregator can formulate targeted control schemes for the responsive power values ​​of residents in the three different time periods, such as guiding residents to reduce the heating or dehumidification power consumption of residents during the peak power consumption period, and guiding residents to increase the heating or dehumidification power consumption of residents during the low power consumption period. In addition, since the embodiment of the present invention specifically considers the residents' usage time habits of the first and second types of electrical appliances for dehumidification and heating during the time period division process, the responsive power consumption in different time periods is obtained, and the power demand potential for heating and dehumidification is further subdivided, that is, the different potentials of residents for heating and dehumidification can be determined more finely. Based on this, it can better help load aggregators and power grid companies to conduct targeted regulation of the use of different types of electrical appliances, thereby achieving more refined and efficient regulation.

[0111] It is understandable that in theory, the precision of the time period level within each day may not be achieved. For example, in some embodiments, only the responsive power analysis at the overall level of a single day in S104 may be performed, depending on the precision requirements of the load aggregator and the power grid company for load regulation, which is not limited here. However, it is understandable that the embodiment of the present invention is compatible with two granularities of responsive power analysis at the same time, so it has a strong compatibility with scene requirements, and can meet the scene requirements of load aggregators and power grid companies with different precision requirements. Based on this, it is understandable that in the embodiment of the present invention, S104 and S105 are mutually and / or, that is, according to actual needs, any one or more of the methods can be selected to conduct a specific responsive power evaluation of southern residents in winter, that is, potential evaluation. For example, in some embodiments, only the responsive power analysis of a single day as the overall level of S104 can be performed, or only the responsive power analysis of a single day at the time period level of S105 can be performed, and both analyses can be performed at the same time, so as to obtain two potential evaluation results with different granularities at the same time. That is, S104 and S105 can be summarized as: based on the difference between the predicted power consumption data with the largest power consumption and the predicted power consumption data with the smallest power consumption, determine the responsive power consumption for each date in the winter of the current year. The difference can be the difference between the maximum and minimum power consumption of a single day, or the difference between different power consumption in each time period of a single day.

[0112] Finally, after obtaining the potential evaluation results of S104 and / or S105, the embodiment of the present invention can further formulate an electricity load adjustment plan based on the total value of responsive electricity for heating and dehumidification every day in winter of that year, or the responsive electricity value for heating and dehumidification at each time period of each day. Since electricity load adjustment is not the focus of the embodiment of the present invention, it will not be described in detail here.

[0113] The embodiment of the present invention accurately distinguishes the climate characteristics of provinces in the region, divides them into different time periods and simulates electricity consumption habits, and then simulates the types of electrical appliances used in different climates and electricity consumption behaviors, to achieve scientific and accurate simulation and evaluation of actual southern residents' winter heating electricity consumption, and to obtain accurate and reliable predicted electricity consumption and predicted responsive electricity consumption.

[0114] It should be noted that the embodiments of the present invention can be applied to any scenario where the potential electricity consumption of residents in the southern region needs to be evaluated, including but not limited to the situation where load aggregators need to analyze the potential electricity consumption of residents in the southern region and perform power supply load regulation, or power grid companies need to analyze the potential electricity consumption of residents in the southern region and formulate power supply incentive strategies. The specific situation can be determined according to the actual application situation, and no excessive restrictions are made here.

[0115] At the same time, in practical applications, the embodiments of the present invention can be combined with strategies such as energy load aggregation and power load regulation. For example, firstly, through energy load aggregation, the aggregation classification of different users (including the aggregation classification of residents with different electricity consumption types) is realized, and then the potential evaluation of some users is performed based on the embodiments of the present invention, and finally the power load of users is adjusted based on the potential evaluation results, so as to realize the refinement of user load management, improve the user's experience of electricity consumption, and ensure the stability, safety and higher efficiency of user electricity consumption.

[0116] Embodiment 2

[0117] Based on the same inventive concept, this embodiment provides a device for evaluating the potential of electric power users, and the principle of solving the problem is similar to that of the method for evaluating the potential of electric power users provided in the first embodiment, and the repeated parts will not be repeated.

[0118] This embodiment provides a power user potential assessment device for assessing the power consumption potential of residents in the southern region in winter, including:

[0119] The regional division module is used to divide each province in the southern region into multiple target areas according to the temperature and humidity of each province in winter;

[0120] The electricity consumption prediction module is used to analyze the electricity consumption patterns of the daily historical electricity consumption data of residents in each target area in the past N years, and obtain the daily electricity consumption prediction data corresponding to each target area; where N is an integer greater than or equal to 3;

[0121] The data corresponding module is used to determine the electricity consumption forecast data corresponding to each relevant date from the electricity consumption forecast data according to each date of the current year, and obtain the electricity consumption forecast data set associated with each date of the current year; wherein the method for obtaining the relevant dates is: according to the daily average temperature and daily average humidity of each target area in the current year, the daily historical average temperature and daily historical average humidity of each target area in the past N years are matched respectively, and multiple relevant dates with the highest matching degree of daily average temperature and daily average humidity are determined;

[0122] The potential assessment module is used to determine the responsive power for each date in the current year based on the difference between the maximum and minimum values ​​in the power consumption forecast data set.

[0123] Embodiment 3

[0124] This embodiment provides an electronic device 6, including a memory 61, a processor 60 and a motor. The memory 61 stores a computer program 62 that can be run on the processor 60. When the processor 60 executes the computer program 62, a method for evaluating the potential of electricity users provided in the first embodiment is implemented.

[0125] Specifically, the electronic device 6 provided in the embodiment of the present invention can be a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set top box (STB), customer premise equipment (CPE) and / or other devices used for communicating on a wireless system and a next-generation communication system, for example, electronic devices in a 5G network or electronic devices in a future evolved public land mobile network (PLMN) network, etc.

[0126] Reference Figure 2 The electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 2 Only one is shown in the figure), a memory 61, and a computer program 62 that can be run on the processor 60 is stored in the memory 61. When the processor 60 executes the computer program 62, the steps in the above-mentioned various power user potential assessment method embodiments are implemented, such as Figure 1 Alternatively, when the processor 60 executes the computer program 62, the functions of each module / unit in the above-mentioned device embodiments are realized.

[0127] The electronic device 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that Figure 2 It is only an example of the electronic device 6 and does not constitute a limitation of the electronic device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 6 may also include an input sending device, a network access device, a bus, etc.

[0128] Specifically, the processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0129] Specifically, the memory 61 may be an internal storage unit of the electronic device 6 in some embodiments, such as a hard disk or memory of the electronic device 6. The memory 61 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the electronic device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of a computer program, etc. The memory 61 may also be used to temporarily store data that has been sent or is to be sent.

[0130] Exemplarily, the electronic device 6 provided in the embodiment of the present invention is a computer 70, and the structure of the computer 70 is as shown in FIG. Figure 3 The computer 70 may include a computer processor 71 , an internal memory 72 , a button 73 , a display 74 and a wireless communication module 75 .

[0131] It is to be understood that the structure shown in the embodiment of the present invention does not constitute a specific limitation on the computer 70. In other embodiments of the present invention, the computer 70 may include: Figure 3 More or fewer components, or combining some components, or splitting some components, or different arrangements of components. Figure 3 The components may be implemented as hardware, software or a combination of software and hardware.

[0132] The computer processor 71 may include one or more processing units. For example, the computer processor 71 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processor (NPU). Among them, different processing units may be independent devices or integrated into one or more processors. Among them, the controller may be the nerve center and command center of the computer 70. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0133] The computer processor 71 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the computer processor 71 is a cache memory. The memory may store instructions or data that the computer processor 71 has just used or circulated. If the computer processor 71 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the computer processor 71, and thus improves the efficiency of the system.

[0134] The computer processor 71 can run the power user potential assessment method provided by the embodiment of the present invention to facilitate accurate and reliable assessment of the power user potential. The computer processor 71 can include different devices. For example, when a CPU and a GPU are integrated, the CPU and the GPU can cooperate to execute a power user potential assessment method provided by an embodiment of the present invention. For example, part of the algorithm in the power user potential assessment method is executed by the CPU, and another part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0135] The internal memory 72 can be used to store computer executable program codes, which include instructions. The computer processor 71 executes various functional applications and data processing of the computer 70 by running the instructions stored in the internal memory 72. The internal memory 72 can include a program storage area and a data storage area. The program storage area can store operating system, application program code, etc. The data storage area can store data created during the use of the computer 70, etc.

[0136] The internal memory 72 may also store one or more computer programs corresponding to the power user potential assessment method provided in the embodiment of the present invention. The one or more computer programs are stored in the above-mentioned memory and are configured to be executed by the one or more computer processors 71, and the one or more computer programs include instructions. In addition, the internal memory 72 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0137] The wireless communication function of the computer 70 can be implemented through the wireless communication module 75, the modem processor, etc.

[0138] The application processor outputs sound signals through an audio device (not limited to a speaker, a receiver, etc.), or displays images or videos through a display 74. In some embodiments, the modem processor can be an independent device. In other embodiments, the modem processor can be independent of the computer processor 71 and be set in the same device as the wireless communication module 75 or other functional modules.

[0139] Embodiment 4

[0140] An embodiment of the present invention provides a storage medium storing computer executable instructions. When the computer executable instructions are executed by a computer processor, they are used to execute a method for evaluating the potential of power users provided in the first embodiment.

[0141] Embodiment 5

[0142] An embodiment of the present invention provides a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0143] Embodiment 6

[0144] An embodiment of the present invention provides a chip system, which includes a processor, the processor is coupled to a memory, and the processor executes a computer program stored in the memory to implement the steps in the above-mentioned method embodiments.

[0145] In the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions and cannot be understood as indicating or suggesting relative importance. It should also be understood that although the terms "first", "second", etc. are used to describe various elements in some embodiments of the present application in the text, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first table can be named as the second table, and similarly, the second table can be named as the first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0146] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0147] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. A method for evaluating the potential of power users, characterized in that , used to assess the potential for winter electricity use in southern China, including: According to the temperature and humidity of each province in the southern region in winter, each province is divided into multiple target areas; wherein the multiple target areas include first-category areas, second-category areas, third-category areas and fourth-category areas, wherein the winter temperature of the first-category areas and the second-category areas is higher than the winter temperature of the third-category areas and the fourth-category areas, and the winter humidity of the first-category areas and the third-category areas is higher than the winter humidity of the second-category areas and the fourth-category areas; the division criteria of the multiple target areas are: The first type of area includes provinces and regions that belong to both warm and high humidity areas; The second type of area includes provincial areas that belong to both warm and medium-humidity areas; The third category of regions includes provinces and regions that are both cold regions and high humidity regions; The fourth category of regions includes provinces and regions that belong to both cold and medium humidity regions; The daily historical electricity consumption data of residents in each of the target areas in the past N years are analyzed for electricity consumption patterns, and the daily electricity consumption forecast data corresponding to each of the target areas is obtained; wherein N is an integer greater than or equal to 3; the daily historical electricity consumption data of residents in the first and second areas in the past N years are the daily historical electricity consumption data of residents from January to February in the past N years; the daily historical electricity consumption data of residents in the third and fourth areas in the past N years are the daily historical electricity consumption data of residents from December to February of the following year in the past N years; According to each date of the current year, the electricity consumption forecast data corresponding to each relevant date is determined from the daily electricity consumption forecast data, and the electricity consumption forecast data set associated with each date of the current year is obtained; wherein the method for obtaining the relevant dates is: according to the daily average temperature and daily average humidity of each target area in the current year, the daily historical average temperature and daily historical average humidity of each target area in the past N years are matched respectively, and by calculating the difference between the daily historical average temperature and the daily historical average humidity of the past N years, a plurality of the relevant dates with the highest matching degree of the daily average temperature and the daily average humidity are determined; The responsive power quantity for each date in the current year is determined according to the difference between the maximum value and the minimum value in the power consumption forecast data set.

2. A method for evaluating the potential of power users according to claim 1, characterized in that: The method for obtaining the electricity consumption forecast data is as follows: The historical power consumption data is analyzed for power consumption data of the first category of electrical appliances and the second category of electrical appliances to obtain dehumidification power consumption data and heating power consumption data respectively; Respectively analyzing the dehumidification electricity consumption data and the heating electricity consumption data to obtain corresponding dehumidification electricity consumption prediction data and heating electricity consumption prediction data; According to different time periods, the dehumidification electricity consumption forecast data and the heating electricity consumption forecast data are combined to obtain the electricity consumption forecast data.

3. A method for evaluating the potential of power users according to claim 2, characterized in that: The power consumption data of the first category of electrical appliances and the second category of electrical appliances are analyzed for the historical power consumption data, including the power consumption data analysis of any target date. The power consumption data analysis method of any target date is: Analyze the historical electricity consumption data of the target date to select a target time period that satisfies the conditions at the same time, wherein the conditions include: the electricity consumption in the time period is higher than the electricity consumption threshold, the time for which the electricity consumption in the time period is continuously higher than the electricity consumption threshold is greater than a preset time threshold, and the electricity consumption in the time period fluctuates regularly over time; The target time period includes a first target time period and a second target time period; according to the amount of power consumption per unit time, the first target time period belonging to the first type of electrical appliance usage time period and the second target time period belonging to the second type of electrical appliance usage time period are identified; The dehumidification power consumption data and the heating power consumption data in the historical power consumption data are obtained according to the first target period and the second target period.

4. A method for evaluating the potential of power users according to claim 1, characterized in that: The method for determining the responsive power quantity for each date in the current year according to the difference between the maximum value and the minimum value in the power consumption forecast data set includes processing the responsive power quantity value for any single target date, and the method for processing the responsive power quantity value for any single target date is: Determine the relevant date to which the maximum value and the minimum value in the power consumption forecast data set associated with the target date belong, and filter out the power consumption forecast sub-data of the determined relevant date from the power consumption forecast data; wherein the power consumption forecast sub-data includes the estimated power consumption in each time period within the relevant date; According to the electricity consumption forecast sub-data, the responsive electricity data corresponding to the target date is calculated; and the responsive electricity data is used as the responsive electricity of the target date; wherein the responsive electricity data includes the responsive electricity values ​​corresponding to each time period under the target date.

5. A method for evaluating the potential of power users according to claim 1, characterized in that: The method of analyzing the electricity consumption patterns of the daily historical electricity consumption data of residents in each target area in the past N years includes: curve fitting or neural network model or point-to-point ratio method.

6. A device for evaluating the potential of power users, characterized in that: Used to assess the potential for electricity consumption in southern China during winter, including: The regional division module is used to divide each province in the southern region into multiple target areas according to the temperature and humidity of each province in winter; wherein the multiple target areas include a first-category area, a second-category area, a third-category area and a fourth-category area; the winter temperature of the first-category area and the second-category area is higher than the winter temperature of the third-category area and the fourth-category area, and the winter humidity of the first-category area and the third-category area is higher than the winter humidity of the second-category area and the fourth-category area; the division criteria of the multiple target areas are: The first type of area includes provinces and regions that belong to both warm and high humidity areas; The second type of area includes provincial areas that belong to both warm and medium-humidity areas; The third category of regions includes provinces and regions that are both cold regions and high humidity regions; The fourth category of regions includes provinces and regions that belong to both cold and medium humidity regions; The electricity consumption prediction module is used to analyze the electricity consumption patterns of the daily historical electricity consumption data of the residents in each of the target areas in the past N years, and obtain the daily electricity consumption prediction data corresponding to each of the target areas; wherein N is an integer greater than or equal to 3; the daily historical electricity consumption data of the residents in the first and second areas in the past N years are the daily historical electricity consumption data of the residents from January to February in the past N years; the daily historical electricity consumption data of the residents in the third and fourth areas in the past N years are the daily historical electricity consumption data of the residents from December to February of the following year in the past N years; A data corresponding module is used to determine the electricity consumption forecast data corresponding to each relevant date from the electricity consumption forecast data according to each date of the current year, and obtain the electricity consumption forecast data set associated with each date of the current year; wherein the method for obtaining the relevant dates is: according to the daily average temperature and daily average humidity of each target area in the current year, the daily historical average temperature and daily historical average humidity of each target area in the past N years are matched respectively, and by calculating the difference between the daily historical average temperature and the daily historical average humidity of the past N years, a plurality of relevant dates with the highest matching degree of the daily average temperature and the daily average humidity are determined; The potential assessment module is used to determine the responsive power quantity for each date in the current year according to the difference between the maximum value and the minimum value in the power consumption forecast data set.

7. An electronic device, characterized in that: The invention comprises a memory, a processor and a motor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, a method for evaluating the potential of electric power users as claimed in any one of claims 1 to 5 is implemented.

8. A storage medium storing computer executable instructions, characterized in that: The computer executable instructions are used to execute a method for evaluating the potential of electric power users as described in any one of claims 1 to 5 when executed by a computer processor.

Images