Power load dynamic regulation and control system and method based on population flow analysis

Abstract

The invention discloses a power load dynamic regulation and control system and method based on population flow analysis. The system comprises a data acquisition module which fuses meteorological data, operator population flow data and power grid load data; the meteorological load analysis module constructs a space-time correlation model of the power load and the air temperature, and quantifies the correlation between the load and the lowest air temperature through a Spearman correlation coefficient; the load fluctuation module predicts day-level and hour-level load gaps based on a preset calculation model in combination with the population migration volume; and the dynamic regulation and control module generates a three-level response strategy according to the load fluctuation percentage to realize dynamic allocation of power grid resources. According to the method, the problems of data isolation, insufficient dynamic response and regulation and control lag in traditional power load prediction are solved, and the load prediction precision and the power grid dispatching efficiency in extreme weather and holiday and festival scenes are improved through multi-source data fusion and real-time correlation analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular to a system and method for dynamically regulating power loads based on population flow analysis. Background Art

[0002] Current power load forecasting and control technologies mainly rely on linear regression analysis of historical load data and static meteorological parameters: traditional methods use historical power load curves as the core input and combine regional meteorological statistical data (such as regional average daily temperature and humidity) to predict load trends; load forecasting models with fixed time windows (such as ARIMA and grey prediction models) are used to establish linear relationships based solely on the correlation between historical load and meteorological data.

[0003] Traditional methods use historical power load curves as core inputs and lack real-time monitoring of dynamic changes in population mobility. Static models find it difficult to correlate the dynamic relationship between population mobility and load changes in real time. Load forecasting models using fixed time windows do not consider the spatiotemporal disturbances of population migration on loads during holidays, extreme weather, and other scenarios, and static models find it difficult to correlate the dynamic relationship between population mobility and load changes in real time. Moreover, linear models based on historical data in existing technologies cannot effectively analyze the coupling effects of extreme weather and population migration. Load regulation relies on periodic manual scheduling, with backup capacity preset based on the previous day's peak load. These models are unable to respond in real time to load fluctuations caused by sudden population movements (such as a surge in instantaneous passenger flow in scenic spots or a large-scale outflow of summer residents from urban areas).

[0004] Therefore, how to create a dynamic power load control system based on population flow analysis can systematically solve the problems of data silos, control lag and poor adaptability to extreme scenarios in traditional power load forecasting and control technologies, and provide a more complete technical solution for real-time response and resource optimization of smart grids. Summary of the Invention

[0005] The purpose of the present invention is to provide a dynamic power load control system based on population flow analysis. The present invention can systematically solve the core problems existing in traditional power load forecasting and control technologies, such as data islands, low prediction accuracy, control lag, and poor adaptability to extreme scenarios, and provide a complete technical solution for real-time response and resource optimization of smart grids.

[0006] To achieve this purpose, the present invention designs a power load dynamic control system based on population flow analysis, which includes:

[0007] The data acquisition module is used to pre-process the meteorological data, population flow data and power load data of the area to be regulated to obtain the pre-processed meteorological data, population flow data and power load data;

[0008] The meteorological load analysis module is used to draw a scatter plot of the power load and the minimum temperature of the area to be regulated and a scatter plot of the power load and the maximum temperature of the area to be regulated based on the preprocessed meteorological data, population flow data and power load data, fit the scatter plot of the power load and the minimum temperature of the area to be regulated, and calculate the Spearman (Spearman's rank correlation coefficient) correlation coefficient between the power load and the minimum temperature, and fit the scatter plot of the power load and the maximum temperature of the area to be regulated to calculate the Spearman correlation coefficient between the power load and the maximum temperature;

[0009] The load fluctuation module calculates the predicted load change of the area to be regulated based on the pre-processed population flow data and the preset load fluctuation calculation model, and calculates the predicted load change percentage of the area to be regulated based on the predicted load change of the area to be regulated;

[0010] The dynamic control module generates a hierarchical control strategy for the power load based on the predicted load change percentage, the Spearman correlation coefficient between the power load and the minimum temperature, and the Spearman correlation coefficient between the power load and the maximum temperature in the area to be controlled, and dynamically adjusts the power resource configuration of the power grid in the area to be controlled according to the hierarchical control strategy for the power load.

[0011] Preferably, a visualization module is also included, which divides the percentage value of the load change into different levels according to settings, sets corresponding warning colors according to different levels, and displays the load heat map in real time.

[0012] Preferably, the specific implementation steps of the control strategy are: generating a graded response strategy based on the expected load change percentage, the graded response strategy includes a three-level response mechanism, when the expected load change percentage is ≤10%, no adjustment is required, when 10%<expected load change percentage≤20%, the first-level warning is activated and an adjustment strategy is proposed, when the expected load change percentage is >20%, the second-level warning is activated and an emergency strategy is proposed.

[0013] Beneficial effects of the present invention: The present invention proposes a dynamic power load control system based on population flow analysis. Through 1km grid-based fine processing of meteorological data, 500m base station clustering optimization of population flow and power grid substation-level topology mapping, the meteorological monitoring error is controlled within ±0.5℃, the demographic error is ≤5%, and the load forecast error is ±2%. It solves the problem of heterogeneous formats and precision mismatch of traditional multi-source data, and realizes efficient fusion and mutual verification of cross-dimensional data; through the innovative construction of a summer crowd characteristic analysis model and an inflow and outflow population load fluctuation calculation model, combined with a weekday / holiday distinction mechanism and a seasonal fluctuation compensation algorithm, the nonlinear relationship between population migration scale and load change is analyzed in real time (for example, a 9.44% decrease in population on weekends in Yubei District corresponds to a 34.24% decrease in load); a three-level response mechanism (normal / warning / emergency mode) is constructed based on the load fluctuation percentage. When the influx of population into the scenic area exceeds 80,000, triggering a load fluctuation of >20%, the cross-regional scheduling and energy storage discharge strategy are automatically activated, shortening the control response time in extreme scenarios. The present invention systematically solves technical problems such as the lack of population mobility correlation modeling and slow response to sudden load fluctuations in power supply and demand management, and provides a complete dynamic control solution for urban power grid planning, extreme weather emergency response and holiday load optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a structural schematic diagram of the present invention;

[0015] Figure 2 is the scatter plot of the correlation between minimum temperature and load;

[0016] Figure 3 is the scatter plot of the correlation between maximum temperature and load;

[0017] Figure 4 This is a statistical map of the urban area's summer permanent population;

[0018] Figure 5 This is a schematic diagram of the changes in the permanent population in Chongqing's main urban area;

[0019] Figure 6 This is a schematic diagram of the changes in the overnight population in scenic spots during the summer;

[0020] Figure 7 This is a schematic diagram comparing the population overflow in urban areas and overnight stays in scenic areas;

[0021] Figure 8 This is a diagram of Chongqing's per capita air conditioning load from June to August;

[0022] Figure 9 This is the flow chart for ultra-short-term load forecasting calculation. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0024] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0025] Example 1

[0026] A power load dynamic control system based on population flow analysis, such as Figure 1 As shown, it includes:

[0027] The data acquisition module is used to pre-process the meteorological data, population flow data and power load data of the area to be regulated to obtain the pre-processed meteorological data, population flow data and power load data;

[0028] The meteorological load analysis module is used to draw a scatter plot of the power load and the minimum temperature in the area to be regulated and a scatter plot of the power load and the maximum temperature in the area to be regulated based on the preprocessed meteorological data, population flow data and power load data, fit the scatter plot of the power load and the minimum temperature in the area to be regulated, and calculate the Spearman correlation coefficient between the power load and the minimum temperature, and fit the scatter plot of the power load and the maximum temperature in the area to be regulated, and calculate the Spearman correlation coefficient between the power load and the maximum temperature;

[0029] The load fluctuation module calculates the predicted load change of the area to be regulated based on the pre-processed population flow data and the preset load fluctuation calculation model, and calculates the predicted load change percentage of the area to be regulated based on the predicted load change of the area to be regulated;

[0030] The dynamic control module generates a hierarchical control strategy for the power load based on the predicted load change percentage, the Spearman correlation coefficient between the power load and the minimum temperature, and the Spearman correlation coefficient between the power load and the maximum temperature in the area to be controlled, and dynamically adjusts the power resource configuration of the power grid in the area to be controlled according to the hierarchical control strategy for the power load.

[0031] In the above technical solution, by constructing a core system framework and defining the collaborative working mechanism of the four basic modules of the system (data acquisition, meteorological load analysis, load fluctuation calculation, and dynamic regulation), the core innovation point of driving dynamic regulation of power load through population flow data is established, and the technical characteristics of data fusion (meteorological data, population flow data, and power load data) are clarified, which differentiates it from the traditional static model.

[0032] The above technical solution also includes a visualization module, which divides the percentage value of the load change into different levels according to the settings, sets corresponding warning colors according to different levels, and displays the load heat map in real time.

[0033] In the above technical solution, an interactive display interface is developed to display load heat maps, population migration paths and control suggestions in real time; it supports multi-dimensional queries (such as region, time, and load type) and generates analysis reports; and it is linked with the heat map to superimpose and display the load (red > 1000MW), population density (arrow width) and meteorological warnings (high temperature red mark).

[0034] In the above technical solution, by supplementing the visualization implementation means of dynamic control, load fluctuations are combined with geographic spatial information, a warning color grading mechanism is defined, the system's real-time response capability is enhanced, the interactive design of the heat map and load linkage is protected, and decision-making efficiency is improved.

[0035] In the above technical solution, the meteorological data, population flow data and power load data specifically include: the meteorological data includes daily meteorological information and hourly meteorological information, and the parameters of the daily meteorological information and the hourly meteorological information are as follows: grid code, data time, meteorological type, maximum temperature, minimum temperature, average temperature, humidity, daily rainfall, daily rainfall probability, average wind speed and other meteorological elements;

[0036] Population mobility data is located through the operator's base station, accessing the passenger flow data of the area to be regulated, and counting the population migration in the area to be regulated, specifically including: the number of people who stay overnight in the area to be regulated on the same day, the total number of people on working days in the base month in the area to be regulated, the total number of people on non-working days in the base month in the area to be regulated, the number of people per hour on working days in the area to be regulated in the to-be-calculated month, the number of people per hour on non-working days in the area to be regulated in the to-be-calculated month, the hourly roaming-in or roaming-out data of the area to be regulated on working days, the hourly roaming-in or roaming-out data of the area to be regulated on non-working days, the daily roaming-in or roaming-out data of the area to be regulated on working days, and the daily roaming-in or roaming-out data of the area to be regulated on non-working days;

[0037] The power load data includes current load data, hourly load and power consumption at the substation level, real-time load data of the entire network, ultra-short-term load forecast data in the area to be regulated, maximum residential load of the day in the area to be regulated, and current hourly residential load in the area to be regulated.

[0038] In the above technical solution, by limiting the specific dimensions of meteorological, population, and power data (such as hourly population inflow and outflow, and substation-level load mapping), the technical integration points of operator base station positioning and substation topology mapping are clarified, and abstract data are integrated into verifiable technical features, thereby improving data utilization.

[0039] In the above technical solution, the specific method for optimizing meteorological data is as follows: the original meteorological data only has integrated information for the region, that is, a region only has one maximum temperature, minimum temperature and other information. It is now changed to be obtained from the meteorological NC grid data file. The specific solution is: select 100 longitude and latitude landmark points in the area to be determined, obtain the temperature of these points from the meteorological file and calculate the average value as the temperature of the area. If it is necessary to further reduce the error, more points can be selected for calculation.

[0040] In the above technical solution, the specific method for optimizing population mobility data is as follows: the data is obtained from operators such as China Mobile and China Unicom, and the electronic fences in urban areas and scenic areas are further optimized, with the accuracy increased from the original 5km to 500m, avoiding repeated counting of mobile personnel and greatly reducing the error of the original statistical data.

[0041] In the above technical solution, the specific method for optimizing grid load is as follows: the original data accessed from the power company only contained regional load data, and no load data for places like scenic spots. Now, the grid load at the substation level (10kV line) is accessed. Based on the substation power supply radius, the grid load can be mapped to the scenic area, further eliminating load errors.

[0042] In the above technical solution, the power load data includes the hourly load and power consumption at the substation level and the real-time load data of the entire network. According to the power supply radius of the substation, the grid load can be mapped to the scenic area, and the ultra-short-term load forecast data of the entire network and various regions for the next 4 hours can be connected.

[0043] In the above technical solution, the specific access method is: the real-time and ultra-short-term predicted load of the entire network is mainly obtained by querying the DAMO database table of Zone III of the power company's automated control cloud platform; the substation-level load and power data are mainly provided by the power marketing company or the digitalization department, and the main access method is to retrieve it through the data interface or Kafka service provided by the power company's Zone IV data center; a part of it is also obtained through the E-file method, and the marketing company generates a specific E-text for the data and transmits it to the designated server. When obtaining the data, it is necessary to download and parse it from the designated server.

[0044] In the above technical solution, the Kafka service interface is only a way to obtain data.

[0045] In the above technical solution, the specific method for obtaining ultra-short-term load forecast data is as follows: the ultra-short-term load forecast is provided by the power company, and the acquisition method is also to query the Dameng database table of Zone III of the control cloud platform. If the data is not obtained or missing, the ultra-short-term load forecast algorithm is used for calculation. The main algorithms include: exponential smoothing method, linear regression method, and neural network method. The input components are the day-ahead predicted load, real-time load, temperature, similar day data, etc. The specific calculation process is as follows: Figure 9 shown.

[0046] In the above technical solution, the specific calculation formula for calculating the Spearman correlation coefficient ρ between power load and minimum temperature is:

[0047]

[0048] Among them, i represents each independent data point, x i Indicates the temperature of the i-th data, y i represents the peak power load of the i-th data, represents the average temperature, Indicates the peak average value of power load.

[0049] In the above technical solution, the meteorological load analysis module is used to draw a scatter plot of the power load and the minimum temperature of the area to be regulated and a scatter plot of the power load and the maximum temperature of the area to be regulated based on the preprocessed meteorological data, population flow data and power load data. The calculated Spearman correlation coefficient under the minimum temperature condition is 0.86, and the goodness of fit is 0.77. The Spearman correlation coefficient under the maximum temperature condition is 0.49, and the goodness of fit is 0.69. Figure 2 and Figure 3 As shown in the figure, the correlation between the peak power load and the minimum temperature in the area to be regulated is higher, and the fitting effect is better.

[0050] In the above technical solution, through the innovation of statistical methods for analyzing the correlation between protection meteorology and load, the traditional linear regression is upgraded to a non-parametric statistical model to adapt to the nonlinear relationship of extreme weather (such as the summer vacation situation mentioned later).

[0051] The above technical solution includes a meteorological load characteristic analysis model, which is used to build a summer meteorological load characteristic analysis model and analyze the correlation between meteorology and load. Based on some population flow data provided by China Unicom, China Mobile, and China Telecom, as well as the residential load provided by the Marketing Department of Chongqing Electric Power Company and the load data of the entire network provided by the control center, scatter plots of the city's daily maximum residential load and the minimum and maximum temperatures from June to August are drawn respectively, and a straight line is used for fitting. The calculation concludes that the correlation between the load peak and the minimum temperature is higher than the correlation with the maximum temperature of the day, such as Figure 2 and Figure 3 shown.

[0052] The above technical solution also includes the construction of a summer crowd characteristic analysis model. By analyzing the operator data, we can get the trend of people avoiding the summer heat. During the summer vacation period from June to August, the resident population in each district shows a downward trend. It can be considered that there are people who stay away from the summer heat for a long time. This helps us provide reasonable grid scheduling and planning suggestions during the peak summer period. Taking Chongqing as an example, we can conclude that the permanent population of Chongqing's main urban area has decreased from July to August compared with June. Some people who avoid the summer heat choose to stay away from the summer heat for a long time, such as Figure 4 and Figure 5 As shown in the figure, the number of people who go to summer resorts on weekends in July and August increased significantly compared with June, with the highest number being around 45,000 (China Mobile users). The proportion of people staying overnight in scenic spots during the summer vacation is high, as shown in the figure. Figure 6 As shown in the figure, during July and August, the outflow of people from urban areas on Saturdays mainly flowed to summer resorts, such as Figure 7 shown.

[0053] In the above technical solution, by constructing a correlation analysis model between the summer population and the resident load, and analyzing the summer population and the resident load, we draw the following conclusions using Chongqing as an example:

[0054] The travel of summer vacationers can effectively reduce the air conditioning load. According to the mobile ratio, based on the peak per capita load of 0.35 kW in July and August (per capita load on that day = total load of residents on that day / number of residents on that day), 100,000 people will reduce the air conditioning load in the urban area by 35,000 kW. Figure 8 As shown;

[0055] It can be concluded that compared with the load taken away by the summer crowds, the air-conditioning load gain generated by residents who do not go out when the temperature rises is greater; therefore, although the summer crowds can reduce some of the load pressure, overall, the load they reduce is relatively small and cannot completely offset the load increase brought about by the increase in air-conditioning demand among residents who do not go out.

[0056] In the above technical solution, the specific method for processing population mobility data is as follows:

[0057] Average number of people per hour in the area to be regulated on working days = total number of people on working days in the base month in the area to be regulated / number of hours

[0058] Average number of people per hour in the area to be regulated on non-working days = total number of people on non-working days in the base month in the area to be regulated / number of hours

[0059] Hourly in- or out-flow data of the area to be regulated on weekdays = (hourly number of people in the area to be regulated on weekdays in the month to be calculated - average hourly number of people in the area to be regulated on weekdays)

[0060] Hourly in- or out-flow data of the area to be regulated on non-working days = (hourly number of people in the area to be regulated on non-working days in the month to be calculated - average hourly number of people in the area to be regulated on non-working days)

[0061]

[0062] Based on the hourly roaming-in or roaming-out data of the area to be regulated on working days and the hourly roaming-in or roaming-out data of the area to be regulated on non-working days, the roaming-in or roaming-out data of the area to be regulated for the current hour are selected; based on the daily roaming-in or roaming-out data of the area to be regulated on working days and the daily roaming-in or roaming-out data of the area to be regulated on non-working days, the roaming-in or roaming-out data of the area to be regulated on the current day are selected.

[0063] In the above technical solution, the benchmark month comparison mechanism is used to solve the static defects of the traditional model, eliminate the interference of seasonal fluctuations, accurately capture sudden flows, and dynamically adjust the baseline.

[0064] In the above technical solution, the specific calculation formula of the load fluctuation calculation model is:

[0065] Calculate the expected load change, that is, the expected load gap in the area to be regulated:

[0066] Estimated daily load gap = (maximum daily residential load in the area to be regulated / overnight population in the area to be regulated) * inflow or outflow data in the area to be regulated on that day)

[0067] Estimated hourly load gap = (current hourly resident load in the area to be regulated / current population in the area to be regulated) * current hourly inflow or outflow data of the area to be regulated).

[0068] In the above technical solution, the specific calculation formula for calculating the load change percentage based on the load change is:

[0069] Estimated load change percentage = (|load gap| / current load)*100%

[0070] Among them, the load gap is selected as the expected daily load gap or the expected hourly load gap according to the set requirements.

[0071] In the above technical solution, the prediction is mainly reflected in predicting the load gap in the current area to be regulated based on the population flow in the previous hour, so as to regulate the power supply.

[0072] In the above technical solution, the specific implementation steps of the control strategy are:

[0073] A graded response strategy is generated based on the percentage of expected load change. The graded response strategy includes a three-level response mechanism. When the expected load change percentage is ≤10%, it is in normal mode and no adjustment is required; when 10% < expected load change percentage ≤20%, it is in early warning mode, the first level early warning is activated and an adjustment strategy is proposed; when the expected load change percentage is >20%, it is in emergency mode, the second level early warning is activated and an emergency strategy is proposed.

[0074] In the above technical solution, the decision tree logic of dynamic control is realized by defining the mapping rules between the load fluctuation percentage and the control strategy.

[0075] Example 2

[0076] The method for dynamic power load control based on population flow analysis includes the following steps:

[0077] Preprocessing meteorological data, population flow data, and power load data of the area to be regulated to obtain preprocessed meteorological data, population flow data, and power load data;

[0078] Based on the pre-processed meteorological data, population flow data and power load data, a scatter plot of the power load and the minimum temperature of the area to be regulated and a scatter plot of the power load and the maximum temperature of the area to be regulated are drawn, the scatter plot of the power load and the minimum temperature of the area to be regulated are fitted, and the Spearman correlation coefficient between the power load and the minimum temperature is calculated. The scatter plot of the power load and the maximum temperature of the area to be regulated are fitted, and the Spearman correlation coefficient between the power load and the maximum temperature is calculated;

[0079] According to the pre-processed population flow data, based on the preset load fluctuation calculation model, the predicted load change of the area to be regulated is calculated, and the predicted load change percentage of the area to be regulated is calculated according to the predicted load change of the area to be regulated;

[0080] A hierarchical control strategy for power load is generated based on the predicted load change percentage, the Spearman correlation coefficient between power load and minimum temperature, and the Spearman correlation coefficient between power load and maximum temperature in the area to be regulated. The power resource configuration of the power grid in the area to be regulated is dynamically adjusted according to the hierarchical control strategy for power load.

[0081] Example 3

[0082] A computer program product includes a computer program, which implements the steps of the method described in Example 2 when executed by a processor.

[0083] The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0084] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0086] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system that is implemented in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art may still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.

Claims

1. A power load dynamic control system based on population flow analysis, characterized in that: It includes: The data acquisition module is used to pre-process the meteorological data, population flow data and power load data of the area to be regulated to obtain the pre-processed meteorological data, population flow data and power load data; The meteorological load analysis module is used to draw a scatter plot of the power load and the minimum temperature in the area to be regulated and a scatter plot of the power load and the maximum temperature in the area to be regulated based on the preprocessed meteorological data, population flow data and power load data, fit the scatter plot of the power load and the minimum temperature in the area to be regulated, and calculate the Spearman correlation coefficient between the power load and the minimum temperature, and fit the scatter plot of the power load and the maximum temperature in the area to be regulated, and calculate the Spearman correlation coefficient between the power load and the maximum temperature; The load fluctuation module calculates the predicted load change of the area to be regulated based on the pre-processed population flow data and the preset load fluctuation calculation model, and calculates the predicted load change percentage of the area to be regulated based on the predicted load change of the area to be regulated; The dynamic control module generates a hierarchical control strategy for the power load based on the predicted load change percentage, the Spearman correlation coefficient between the power load and the minimum temperature, and the Spearman correlation coefficient between the power load and the maximum temperature in the area to be controlled, and dynamically adjusts the power resource configuration of the power grid in the area to be controlled according to the hierarchical control strategy for the power load.

2. The power load forecasting and dynamic control system based on population flow analysis according to claim 1 is characterized by: It also includes a visualization module, which divides the percentage value of the load change into different levels according to the settings, sets the corresponding warning colors according to the different levels, and displays the load heat map in real time.

3. The power load forecasting and dynamic control system based on population flow analysis according to claim 1 is characterized by: Meteorological data, population flow data, and power load data specifically include: Meteorological data includes daily and hourly meteorological information. Both daily and hourly meteorological information contain the following parameters: data time, maximum temperature, minimum temperature, and average temperature. Population mobility data is located through the operator's base station, accessing the passenger flow data of the area to be regulated, and counting the population migration in the area to be regulated, specifically including: the number of people who stay overnight in the area to be regulated on the same day, the total number of people on working days in the base month in the area to be regulated, the total number of people on non-working days in the base month in the area to be regulated, the number of people per hour on working days in the area to be regulated in the to-be-calculated month, the number of people per hour on non-working days in the area to be regulated in the to-be-calculated month, the hourly roaming-in or roaming-out data of the area to be regulated on working days, the hourly roaming-in or roaming-out data of the area to be regulated on non-working days, the daily roaming-in or roaming-out data of the area to be regulated on working days, and the daily roaming-in or roaming-out data of the area to be regulated on non-working days; The power load data includes the current load data, the maximum residential load of the day in the area to be regulated, and the current hourly residential load in the area to be regulated.

4. The power load forecasting and dynamic control system based on population flow analysis according to claim 1 is characterized by: The specific calculation formula for the Spearman correlation coefficient ρ between power load and minimum temperature is: Among them, i represents each independent data point, x i Indicates the temperature of the i-th data, y i represents the peak power load of the i-th data, represents the average temperature, Indicates the peak average value of power load.

5. The power load forecasting and dynamic control system based on population flow analysis according to claim 3 is characterized by: The specific processing methods for population mobility data are as follows: Average number of people per hour in the area to be regulated on working days = total number of people on working days in the base month in the area to be regulated / number of hours Average number of people per hour in the area to be regulated on non-working days = total number of people on non-working days in the base month in the area to be regulated / number of hours Hourly in- or out-flow data of the area to be regulated on weekdays = (hourly number of people in the area to be regulated on weekdays in the month to be calculated - average hourly number of people in the area to be regulated on weekdays) Hourly in- or out-flow data of the area to be regulated on non-working days = (hourly number of people in the area to be regulated on non-working days in the month to be calculated - average hourly number of people in the area to be regulated on non-working days) Based on the hourly roaming-in or roaming-out data of the area to be regulated on working days and the hourly roaming-in or roaming-out data of the area to be regulated on non-working days, the roaming-in or roaming-out data of the area to be regulated for the current hour are selected; based on the daily roaming-in or roaming-out data of the area to be regulated on working days and the daily roaming-in or roaming-out data of the area to be regulated on non-working days, the roaming-in or roaming-out data of the area to be regulated on the current day are selected.

6. The power load forecasting and dynamic control system based on population flow analysis according to claim 5 is characterized by: The specific calculation formula of the load fluctuation calculation model is: Calculate the expected load change, that is, the expected load gap in the area to be regulated: Estimated daily load gap = (maximum daily residential load in the area to be regulated / overnight population in the area to be regulated) * inflow or outflow data in the area to be regulated on that day) Estimated hourly load gap = (current hourly resident load in the area to be regulated / current population in the area to be regulated) * current hourly inflow or outflow data of the area to be regulated).

7. The power load forecasting and dynamic control system based on population flow analysis according to claim 6 is characterized by: The specific calculation formula for calculating the load change percentage based on the load change is: Estimated load change percentage = (|load gap| / current load)*100% Among them, the load gap is selected as the expected daily load gap or the expected hourly load gap according to the set requirements.

8. The power load forecasting and dynamic control system based on population flow analysis according to claim 1 is characterized by: The specific implementation steps of the control strategy are: A graded response strategy is generated based on the percentage of expected load change. The graded response strategy includes a three-level response mechanism. When the expected load change percentage is ≤10%, no adjustment is required. When 10% < expected load change percentage ≤20%, the first-level warning is activated and an adjustment strategy is proposed. When the expected load change percentage is >20%, the second-level warning is activated and an emergency strategy is proposed.

9. A method for power load forecasting and dynamic control based on population flow analysis, characterized in that: It includes: Preprocessing meteorological data, population flow data, and power load data of the area to be regulated to obtain preprocessed meteorological data, population flow data, and power load data; Based on the pre-processed meteorological data, population flow data and power load data, a scatter plot of the power load and the minimum temperature of the area to be regulated and a scatter plot of the power load and the maximum temperature of the area to be regulated are drawn, the scatter plot of the power load and the minimum temperature of the area to be regulated are fitted, and the Spearman correlation coefficient between the power load and the minimum temperature is calculated. The scatter plot of the power load and the maximum temperature of the area to be regulated are fitted, and the Spearman correlation coefficient between the power load and the maximum temperature is calculated; According to the pre-processed population flow data, based on the preset load fluctuation calculation model, the predicted load change of the area to be regulated is calculated, and the predicted load change percentage of the area to be regulated is calculated according to the predicted load change of the area to be regulated; A hierarchical control strategy for power load is generated based on the predicted load change percentage, the Spearman correlation coefficient between power load and minimum temperature, and the Spearman correlation coefficient between power load and maximum temperature in the area to be regulated. The power resource configuration of the power grid in the area to be regulated is dynamically adjusted according to the hierarchical control strategy for power load.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claim 9 are implemented.

Images