Power demand fluctuation risk identification system and method for power grid
Through the power demand fluctuation risk identification system, using power analysis and power consumption analysis modules, combined with meteorological information to predict power consumption, the power demand fluctuation risk is identified, the problem of power supply and demand imbalance is solved, and the stability of power supply and resource allocation efficiency are improved.
Patent Information
- Application Number
- CN202511012213.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-22
- Publication Date
- 2025-10-17
AI Technical Summary
Existing technologies fail to predict fluctuations in electricity demand in a timely manner, resulting in the inability to fully and effectively guarantee the supply and demand of electricity, especially during peak electricity consumption in winter and summer, when power outages often occur.
By establishing a power demand fluctuation risk identification system, including a power analysis module, a power consumption analysis module and a risk assessment module, we collect and analyze historical power consumption data for each quarter, divide the assessment cycle, predict power consumption in combination with meteorological information, identify the power demand fluctuation risk level, and issue an early warning when the risk exceeds the threshold.
It has achieved accurate prediction of electricity demand and risk identification, improved the stability and reliability of electricity supply, ensured the rational allocation of electricity resources, and reduced power rationing during peak hours.
Smart Images
Figure CN120806530A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the field of power demand, and particularly relates to a power demand fluctuation risk identification system and method for a power grid. BACKGROUND
[0002] In a modern power system, accurate analysis and prediction of power demand are key links for ensuring stable operation of the power grid, optimizing resource allocation, and improving power supply reliability.
[0003] The power industry will arrange the total power production in advance according to the predicted power demand. From the national perspective, the supply and demand of electricity cannot be fully and effectively guaranteed at present, and the fluctuation of power demand cannot be predicted in time. The imbalance in regional power supply and demand has existed for a long time, and the phenomenon of power cut often occurs during the power peak seasons of winter and summer, which brings great inconvenience to the work and life of residents.
[0004] Therefore, the application provides a power demand fluctuation risk identification system and method for a power grid. SUMMARY
[0005] The application aims to at least solve one of the technical problems existing in the prior art. To this end, the application provides a power demand fluctuation risk identification system and method for a power grid, which are used to solve the technical problem that the fluctuation of power demand cannot be predicted in time at present, resulting in that the supply and demand of electricity cannot be fully and effectively guaranteed.
[0006] To achieve the above-mentioned purpose, a first aspect of the application provides a power demand fluctuation risk identification system for a power grid, which comprises a power analysis module, and an electricity consumption analysis module and a risk assessment module connected with the power analysis module.
[0007] The electricity consumption analysis module is used to obtain historical electricity consumption data of each quarter, analyze the average daily electricity consumption of each quarter, and divide each day into a plurality of evaluation periods based on the electricity consumption.
[0008] The power analysis module is used to analyze demand electricity data of a target region in future evaluation periods, and analyze predicted electricity data of the target region in the target region power grid in the future evaluation periods.
[0009] The risk assessment module is used to analyze the power demand fluctuation of the target region power grid in the future evaluation periods according to the predicted electricity data and the demand electricity data of the target region.
[0010] Preferably, the average daily electricity consumption of each quarter is analyzed, which comprises:
[0011] Extracting the power consumption data of several days in each quarter from historical data, calculating the mean of real-time power consumption data of each day in quarter i, and curve fitting the mean of real-time power consumption data to obtain the average daily power consumption curve of quarter i;
[0012] Placing several power consumption curves of the same quarter in the same coordinate system, judging whether the several power consumption curves coincide; if yes, marking any power consumption curve as a standard power consumption curve i; if no, counting the number of coincident parts in the several power consumption curves, and marking the part with a number exceeding a preset coincidence threshold as a partial standard power consumption curve i, and the several partial standard power consumption curves constitute a standard power consumption curve; wherein i is the quarter number, i = 0, 1, 2, 3; the standard power consumption curve i is the standard power consumption curve of each day in quarter i.
[0013] The present application can effectively reduce the influence of accidental factors (such as extreme weather, special events, etc.) on data by calculating the mean of power consumption of several days in each quarter, so that the obtained average daily power consumption data is more representative and can better reflect the normal power consumption of the quarter; curve fitting the mean of real-time power consumption data can generate smooth and continuous power consumption change curves. This method can more accurately reflect the change trend of power consumption than directly using discrete data points, providing a more reliable basis for subsequent analysis and prediction; by placing several power consumption curves of the same quarter in the same coordinate system for comparison, it can be directly judged whether these curves coincide. The coincident curves indicate that the power consumption mode is relatively stable in the quarter, which is convenient for subsequent standardization processing; the standard power consumption curve provides an important reference for energy management, load forecasting, power grid dispatching, etc.
[0014] Preferably, based on the daily power consumption, the day is divided into several evaluation periods, including:
[0015] Extracting each power consumption data on the standard power consumption curve i, calculating the change amplitude between adjacent power consumption data; according to the change amplitude, analyzing the change trend of the standard power consumption curve i, and marking the change trend; wherein the standard power consumption curve i includes several different change trends; the change trend includes a smooth trend, an upward trend and a downward trend;
[0016] Iterating the change trend of the standard power consumption curve i in turn, when a different change trend is iterated, the time point from the iteration starting point to the initial point of the different change trend is an evaluation period, which is marked as evaluation period j; otherwise, continue to iterate; wherein j is the evaluation period number, j = 0, 1, …, N, N is a positive integer; the initial point of the different change trend is the iteration starting point of the next iteration.
[0017] The application can accurately capture the subtle fluctuations of the power consumption over time by calculating the change amplitude between adjacent power consumption data, and provides a data basis for in-depth analysis of the change trend of the standard power consumption curve; the standard power consumption curve is divided into stable trend, rising trend and falling trend according to the change amplitude, and this classification method is intuitive and easy to understand, which helps to accurately identify the overall trend and local characteristics of the curve; by traversing the change trend of the standard power consumption curve and dividing the evaluation period at the turning point of different change trends, the reasonable division of the evaluation period enables the energy management department to formulate more targeted energy plans and scheduling strategies according to the power consumption change characteristics in different time periods, thereby improving the scientificity and efficiency of decision-making.
[0018] Preferably, the analysis of the change trend of the standard power consumption curve i comprises:
[0019] Extracting each power consumption data on the standard power consumption curve i, calculating the change amplitude between adjacent power consumption data, and judging whether the change amplitude is greater than 0 and greater than a preset amplitude threshold; if yes, the change trend between adjacent power consumption data is marked as a rising trend; if no, judging whether the change amplitude is less than 0 and less than a preset amplitude threshold; if yes, the change trend between adjacent power consumption data is marked as a falling trend; if no, the change trend between adjacent power consumption data is marked as a stable trend.
[0020] The application can accurately identify the change trend of the power consumption by comparing the change amplitude between adjacent power consumption data with a preset amplitude threshold, which considers the actual change of the power consumption and excludes the interference of small fluctuations by setting a threshold, so that the identification result is more accurate and reliable; the change trend is clearly divided into three categories of rising trend, falling trend and stable trend, which is simple and clear, and helps the energy management department to quickly understand the overall change characteristics of the power consumption, and provides strong support for the demarcation of the evaluation period.
[0021] Preferably, the analysis of the demand power consumption data of the target area in future evaluation periods comprises:
[0022] Calculating the average power consumption of the evaluation period j;
[0023] Based on the quarter i to which the future evaluation period belongs, extracting the power consumption data of several days of the quarter i from the historical data; dividing the power consumption data into to-be-processed data and normal data;
[0024] Statistically calculating the average number of times of the to-be-processed data, and judging whether the average number of times is greater than a preset number threshold; if yes, the to-be-processed data is marked as abnormal data, the average of the abnormal data is calculated, and the average length of time of the abnormal data is calculated and marked as abnormal time length; if no, the to-be-processed abnormal data is deleted;
[0025] The product of the mean value of the normal data and the normal duration is calculated, and the product of the mean value of the abnormal data and the abnormal duration is added, to obtain the demand power of the evaluation period j; wherein the normal duration is the difference between the duration of the evaluation period j and the abnormal duration.
[0026] The application realizes fine processing of data by calculating the mean value of the power consumption of the evaluation period and classifying the power consumption data based on the mean value, which helps to more accurately identify abnormal values and normal values in the power consumption data, and provides strong support for subsequent analysis and decision-making; By comparing the mean value of the number of times of the data to be processed with the preset number of times threshold, the abnormal data is accurately identified, which is helpful to exclude the interference of accidental factors and makes the identification result more reliable; The demand power of each evaluation period is evaluated for the identified abnormal data and normal data, which considers the influence of abnormal data on the total demand, making the evaluation result more stable.
[0027] Preferably, the mean value of the power consumption of the evaluation period j is the mean value of the power consumption data of the evaluation period j in the standard power consumption curve i.
[0028] Preferably, the power consumption data is divided into data to be processed and normal data, including:
[0029] Determine whether the power consumption data collected in the evaluation period j is greater than the mean value of the power consumption; Yes, the power consumption data is marked as data to be processed; No, the power consumption data is marked as normal data.
[0030] Preferably, the analysis of the target area in the future each evaluation period of the target area power grid prediction power consumption data, including:
[0031] Obtain the meteorological information of the future evaluation period j, calculate the sum of the wind power and the light power of the target area in the future evaluation period j, and obtain the prediction power consumption data of the target area in the future evaluation period j; wherein the meteorological information includes wind speed, light intensity and air density;
[0032] Wherein, the wind power is calculated by the formula FN=1 / 2×ρ×A×V 3 ×η×T×S; ρ is the air density, A is the wind sweeping area of the wind turbine blade, V is the wind speed, η is the wind energy conversion efficiency, T is the duration of the future period, S is the number of wind turbines;
[0033] The light power is calculated by the formula DN=G×A1×T×S1×γ; G is the light intensity, A1 is the area of the photovoltaic panel, T is the light time, S1 is the number of photovoltaic panels, and γ is the light energy conversion efficiency.
[0034] The application combines detailed meteorological information (including wind speed, light intensity and air density) and analyzes and evaluates the power generation in the period by using wind power generation and light power generation, the prediction not only considers the direct influence of meteorological conditions, but also improves the accuracy of the prediction through parameterized models (such as wind turbine blade swept area, photovoltaic panel area, etc.) and conversion efficiency coefficients, the method has high flexibility and applicability.
[0035] Preferably, the power demand fluctuation of the analysis target area in each evaluation period in the future is analyzed, including:
[0036] The difference between the demand power data and the predicted power data is calculated, and it is judged whether the difference is greater than the preset difference threshold value; if yes, the power demand fluctuates, and the power risk level is marked as level one; if no, the power demand does not fluctuate, and the power risk level is marked as level two; wherein, the level one of the power risk level is greater than the level two.
[0037] Preferably, the second aspect of the application provides a power demand fluctuation risk identification method for a power grid, including the following steps:
[0038] Obtain a plurality of historical power consumption data of each quarter, and analyze the average daily power consumption of each quarter; based on the power consumption, each day is divided into a plurality of evaluation periods;
[0039] The demand power data of the analysis target area in each evaluation period in the future is analyzed, and the predicted power data of the target area power grid of the analysis target area in each evaluation period in the future is analyzed.
[0040] According to the predicted power data and the demand power data of the target area, the power demand fluctuation of the target area in each evaluation period in the future is analyzed.
[0041] Compared with the prior art, the application has the beneficial effects that:
[0042] The application evaluates the seasonal change trend of the power consumption by collecting and analyzing the historical power consumption data of each quarter, and provides an important reference basis for future power demand prediction; the daily power consumption is divided into several evaluation periods, each evaluation period reflects the change trend of the power consumption, which helps to more finely manage the power resources, identify the fluctuation period of the power consumption, and provide data support for power dispatching and energy-saving measures; the predicted power consumption data and demand power data of the target area in future evaluation periods are predicted, which provides an important reference for power planning and dispatching, analyzes the stability and reliability of the power supply, helps to identify potential power supply risks in advance, and timely issues a warning when the power demand fluctuation exceeds the preset threshold through the risk warning mechanism, which helps the power company to better respond to the changes in power demand and potential power supply risks, ensures the safety and stability of the power supply, reasonably allocates the power resources in advance, and improves the efficiency and reliability of the power supply. BRIEF DESCRIPTION OF DRAWINGS
[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.
[0044] Figure 1 The system structure diagram of the present application is shown in the figure;
[0045] Figure 2 The evaluation period division method flowchart of the present application is shown in the figure;
[0046] Figure 3 The method flowchart of the present application is shown in the figure. DETAILED DESCRIPTION
[0047] The technical solutions of the present application will be described in detail below with the embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.
[0048] Please refer to Figure 1 The first aspect embodiment of the present application provides a power demand fluctuation risk identification system for power grid, which comprises a power analysis module, and a power consumption analysis module and a risk assessment module connected thereto;
[0049] The power consumption analysis module acquires a plurality of historical power consumption data of each quarter, and analyzes the average daily power consumption of each quarter;
[0050] Specifically, the power consumption data of several days in each quarter is extracted from historical data, the mean of real-time power consumption data of each day in quarter i is calculated, and the mean of real-time power consumption data is curve-fitted to obtain the average daily power consumption change curve of quarter i.
[0051] The power consumption change curves of the same quarter are placed in the same coordinate system, and it is determined whether the power consumption change curves coincide; if yes, any power consumption change curve is marked as a standard power consumption curve i; if no, the number of coincident parts in the power consumption change curves is counted, and the part with a number exceeding a preset coincidence threshold is marked as a partial standard power consumption curve i, and the partial standard power consumption curves constitute a standard power consumption curve; wherein i is the quarter number, i = 0, 1, 2, 3; the standard power consumption curve i is the standard power consumption curve of each day in quarter i.
[0052] It should be noted that the collection period of daily power consumption data is fixed.
[0053] For example, assuming that the power consumption data of each day in each quarter in the past M years in a certain region is extracted, the power consumption data of each day in each quarter is processed by mean, that is, the power consumption data at each collection time point is processed by mean, for example, the power consumption data is collected once an hour every day, and the power consumption data at 12:00 of each day in the first quarter is the mean of the power consumption data at 12:00 of each day in the first quarter in the past M years; the mean of the power consumption data at other collection time points is calculated in this way, and the mean of the power consumption data at each collection time point of a day is curve-fitted to obtain the average daily power consumption change curve of the first quarter in the region. The daily power consumption change curves of other quarters are obtained in this way.
[0054] According to the analysis of the above embodiment, several power consumption change curves of each quarter in the region are obtained, for example, the power consumption change curves of the first quarter are placed in the same coordinate system, and it is assumed that the power consumption change curves approximately coincide, then any one of the power consumption change curves can be used as the standard power consumption curve of the first quarter; it is assumed that the power consumption change curves do not completely coincide, then the number of coincident curves is counted, and the part with a number exceeding a preset coincidence threshold is extracted as the standard power consumption curve of the collection time period, and the standard power consumption curves of the several collection time periods are fitted to obtain the standard power consumption curve of each day in the first quarter.
[0055] Please refer to Figure 2 , based on the power consumption, each day is divided into several evaluation periods;
[0056] Specifically, each power consumption data on the standard power consumption curve i is extracted, and the change amplitude between adjacent power consumption data is calculated; each power consumption data on the standard power consumption curve i is extracted, and the change amplitude between adjacent power consumption data is calculated, whether the change amplitude is greater than 0 and greater than a preset amplitude threshold is judged; yes, the change trend between adjacent power consumption data is marked as an upward trend; no, whether the change amplitude is less than 0 and less than a preset amplitude threshold is judged; yes, the change trend between adjacent power consumption data is marked as a downward trend; no, the change trend between adjacent power consumption data is marked as a stable trend.
[0057] The change trends of the standard power consumption curve i are sequentially traversed, when different change trends are traversed, then the time point before the initial point of the different change trend from the traversal initial point is an evaluation period, which is marked as evaluation period j; otherwise, the traversal is continued; wherein, j is the evaluation period number, j = 0, 1, …, N, N is a positive integer; the initial point of the different change trend is the traversal initial point of the next traversal.
[0058] For example: assuming the standard power consumption curve of a certain region in the first quarter, the power consumption data of each collection time point on the curve is extracted, the change trend between adjacent two collection time points is sequentially calculated according to the collection time point sequence, such as the adjacent collection time points T0 and T1, and the corresponding power consumption data A and B, respectively, the change amplitude of the power consumption between T0 and T1 is calculated as (B-A) / A, and the change amplitude is compared with 0 and a preset amplitude threshold, respectively, to obtain the change trend of the power consumption between T0 and T1.
[0059] After the above analysis, it is assumed that the change of the standard power consumption curve of the region in the first quarter is from left to right as a stable trend, an upward trend, a downward trend, and a stable trend; and if the collection time points are T0-TN per day, there are N collection time points.
[0060] The power consumption change trends of the collection time points are sequentially traversed from left to right, T0-T4 is a stable trend, T5 is an upward trend, then T0-T4 is evaluation period 0; T5-T10 is an upward trend, T11 is a downward trend, then T5-T10 is evaluation period 1; T11-T18 is a downward trend, T12 is a stable trend, then T11-T18 is evaluation period 2; the remaining time collection points are stable change trends, which are evaluation period 3.
[0061] The power analysis module analyzes the demand power data of the target region in each evaluation period in the future;
[0062] Specifically, the mean value of the power consumption data of the evaluation period j in the standard power consumption curve i is calculated to obtain the power consumption mean value of the evaluation period j; for example, there are X power consumption data in the evaluation period 0, then the sum of the X power consumption data divided by X is the power consumption mean value of the evaluation period 0.
[0063] extracting the daily electricity consumption data of the quarter i from the historical data based on the quarter i to which the future evaluation period belongs; judging whether the electricity consumption data collected in the evaluation period j is greater than the average electricity consumption based on the average electricity consumption of the evaluation period j; if yes, marking the electricity consumption data as to-be-processed data; if no, marking the electricity consumption data as normal data; calculating the average number of times of occurrence of the to-be-processed data, and judging whether the average number of times is greater than a preset number of times threshold; if yes, marking the to-be-processed data as abnormal data, calculating the average of the abnormal data, and calculating the average length of time of occurrence of the abnormal data, which is marked as abnormal length of time; if no, deleting the to-be-verified abnormal data;
[0064] For example: assuming that the abnormal data of the first quarter evaluation period 0 is analyzed, the electricity consumption data of the first quarter evaluation period 0 is extracted from the historical data, the electricity consumption data is compared with the average electricity consumption of the evaluation period 0, to-be-processed data is extracted, and the number of times of occurrence of the to-be-processed data is counted; if it is greater than a preset number of times threshold, the to-be-processed data is abnormal data, the abnormal data in the evaluation period 0 is processed by averaging, and the length of time of occurrence of the abnormal data in each evaluation period 0 is counted, and the length of time of occurrence of the abnormal data in each evaluation period 0 is obtained by averaging, that is, the abnormal length of time.
[0065] The product of the average of the normal data and the normal length of time is calculated, and the product of the average of the abnormal data and the abnormal length of time is added, to obtain the demand electricity consumption of the evaluation period j; wherein the normal length of time is the difference between the length of time of the evaluation period j and the abnormal length of time.
[0066] In addition, the predicted electricity consumption data of the target area power grid in each future evaluation period is analyzed, and the analysis process is as follows:
[0067] Obtaining the meteorological information of the future evaluation period j, calculating the sum of the wind power generation and the light energy generation of the target area in the future evaluation period j, and obtaining the predicted electricity consumption data of the target area in the future evaluation period j; wherein the meteorological information includes wind speed, light intensity and air density;
[0068] Wherein, the wind power generation is calculated by the formula FN=1 / 2×ρ×A×V 3 ×η×T×S; ρ is air density, A is the wind sweeping area of the wind turbine blade, V is wind speed, η is wind energy conversion efficiency, T is the length of time of the future period, and S is the number of wind turbines;
[0069] The light energy generation is calculated by the formula DN=G×A1×T×S1×γ; G is the light intensity, A1 is the area of the photovoltaic panel, T is the light time, S1 is the number of photovoltaic panels, and γ is the light energy conversion efficiency.
[0070] The risk assessment module analyzes power demand fluctuation of the target area in the power grid in each evaluation period in the future.
[0071] Specifically, a difference between the demand power data and the predicted power data is calculated, and it is determined whether the difference is greater than a preset difference threshold; if yes, the power demand fluctuates, and the power risk level is level one; if no, the power demand does not fluctuate, and the power risk level is level two; wherein, the level one of the power risk level is greater than the level two.
[0072] Referring to Figure 3 The second aspect of the present application provides a power demand fluctuation risk identification method for a power grid, comprising the following steps:
[0073] According to historical quarterly power consumption data, average daily power consumption in each quarter is analyzed; based on the power consumption, each day is divided into several evaluation periods;
[0074] The demand power data of the target area in each evaluation period in the future is analyzed, and the predicted power data of the target area in each evaluation period in the future is analyzed.
[0075] According to the predicted power data and the demand power data of the target area, the power demand fluctuation of the target area in the power grid in each evaluation period in the future is analyzed.
[0076] Part of the data in the above formula is calculated by removing the dimension, and the formula is obtained by software simulation of a large amount of collected data to be closest to the real situation; the preset parameters and the preset threshold in the formula are set by the person skilled in the art according to the actual situation or obtained by a large amount of data simulation.
[0077] The above embodiments are only used to illustrate the technical method of the present application and not to limit it, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.
Claims
1. A power demand fluctuation risk identification system for a power grid, characterized in that: It includes a power analysis module, as well as a power consumption analysis module and a risk assessment module connected thereto; Power consumption analysis module: used to obtain several historical power consumption data for each quarter and analyze the average daily power consumption of each quarter; based on the power consumption, each day is divided into several evaluation periods; Power analysis module: used to analyze the target area's demand power data in each future assessment period, and to analyze the target area's predicted power data for the power grid in each future assessment period; Risk assessment module: used to analyze the power demand fluctuations of the target area in each future assessment period based on the predicted power data and demand power data of the target area.
2. A power demand fluctuation risk identification system for a power grid according to claim 1, characterized in that: The analysis of the average daily electricity consumption in each quarter includes: Extract electricity consumption data for several days in each quarter from the historical data, calculate the mean of the real-time electricity consumption data for each day in quarter i, and perform curve fitting on the mean of the real-time electricity consumption data to obtain the average daily electricity consumption change curve for quarter i; Place several electricity consumption change curves of the same quarter in the same coordinate system and determine whether the several electricity consumption change curves overlap; if so, mark any electricity consumption change curve as standard electricity consumption curve i; if not, count the number of overlapping parts in the several electricity consumption change curves, mark the parts whose number exceeds the preset overlap threshold as partial standard electricity consumption curve i, and several partial standard electricity consumption curves constitute a standard electricity consumption curve; where i is the quarter number, i = 0, 1, 2, 3; standard electricity consumption curve i is the standard electricity consumption curve for each day in quarter i.
3. The power demand fluctuation risk identification system for a power grid according to claim 2, characterized in that: Based on the electricity consumption, each day is divided into several evaluation cycles, including: Extract each power consumption data on the standard power consumption curve i and calculate the change range between adjacent power consumption data; analyze the change trend of the standard power consumption curve i based on the change range and mark the change trend; wherein the standard power consumption curve i includes several different change trends; the change trend includes a stable trend, an upward trend and a downward trend; Traverse the changing trend of the standard electricity consumption curve i in sequence. When traversing to different changing trends, the time from the traversal initial point to the previous time point of the different changing trend initial point is an evaluation cycle, marked as evaluation cycle j; otherwise, continue traversing; where j is the evaluation cycle number, j = 0, 1, ..., N, N is a positive integer; the initial point of the different changing trend is the traversal initial point of the next traversal.
4. The power demand fluctuation risk identification system for a power grid according to claim 3, characterized in that: According to the change range, the change trend of the analysis standard power consumption curve i includes: Extract each power consumption data on the standard power consumption curve i and calculate the variation range between adjacent power consumption data; Determine whether the change amplitude is greater than 0 and greater than a preset amplitude threshold; If yes, the change trend between adjacent power consumption data is marked as an upward trend; If not, determine whether the change amplitude is less than 0 and less than the preset amplitude threshold; if yes, the change trend between adjacent power consumption data is marked as a downward trend; if not, the change trend between adjacent power consumption data is marked as a stable trend.
5. The power demand fluctuation risk identification system for a power grid according to claim 3, characterized in that: The analysis of the power demand data of the target area in each future evaluation period includes: Calculate the mean power consumption during evaluation period j; Based on the quarter i to which the future evaluation period belongs, extract the daily electricity consumption data of quarter i from the historical data; divide the electricity consumption data into pending data and normal data; Count the average number of times the data to be processed appears, and determine whether the average number of times is greater than the preset number threshold; if yes, mark the data to be processed as abnormal data, calculate the average of the abnormal data, and calculate the average duration of the abnormal data, and mark it as abnormal duration; if not, delete the abnormal data to be processed; Calculate the product of the mean of the normal data and the normal duration, and add the product of the mean of the abnormal data and the abnormal duration to obtain the required power consumption for evaluation period j; the normal duration is the difference between the duration of evaluation period j and the abnormal duration.
6. The power demand fluctuation risk identification system for a power grid according to claim 5, characterized in that: The average power consumption of the evaluation period j is the average of the power consumption data of the evaluation period j in the standard power consumption curve i.
7. The power demand fluctuation risk identification system for a power grid according to claim 5, characterized in that: The dividing of the power data into data to be processed and normal data includes: Determine whether the power consumption data collected in the evaluation period j is greater than the power consumption mean; if yes, the power consumption data is marked as pending data; if not, the power consumption data is marked as normal data.
8. The power demand fluctuation risk identification system for a power grid according to claim 5, characterized in that: The analysis of the predicted power data of the target area's power grid in each future evaluation period includes: Obtain meteorological information for the future assessment period j, calculate the sum of wind power generation and solar power generation in the target area for the future assessment period j, and obtain predicted electricity data for the target area for the future assessment period j; wherein the meteorological information includes wind speed, light intensity, and air density.
9. The power demand fluctuation risk identification system for a power grid according to claim 8, characterized in that: The analysis of power demand fluctuations in the target area during each future assessment period includes: Calculate the difference between the demand power data and the predicted power data, and determine whether the difference is greater than the preset difference threshold; if so, the power demand fluctuates and the power risk level is marked as level one; if not, the power demand does not fluctuate and the power risk level is marked as level two; among which, the power risk level level one is greater than level two.
10. A method for identifying power demand fluctuation risks for a power grid, based on the power demand fluctuation risk identification system for a power grid according to any one of claims 1 to 9, characterized in that: The following steps are involved: Obtain some historical electricity consumption data for each quarter and analyze the average daily electricity consumption for each quarter; based on the electricity consumption, divide each day into several evaluation periods; Analyze the target area's demand electricity data for each future assessment period, and analyze the target area's predicted electricity data for the power grid in each future assessment period; Based on the predicted power data and demand power data of the target area, the power demand fluctuations of the target area in the power grid in each future evaluation period are analyzed.