Electric power supply and distribution intelligent scheduling early warning detection method and system

Abstract

The invention relates to the technical field of control, in particular to an electric power supply and distribution intelligent scheduling early warning detection method and system, and the method comprises the steps: carrying out the clustering of the daily electricity consumption of a set number of days of an electricity consumption collection unit, obtaining a plurality of clustering clusters, and enabling each clustering cluster to represent a time period electricity consumption sequence with similar electricity consumption behaviors in one day; determining all power utilization time periods based on the time period power utilization sequence of each day; a complete electricity utilization period is constructed; screening the power utilization period to obtain an effective period; calculating a first ratio and a second ratio in the effective period; the difference value between the second mean value and the first mean value is used as the power utilization margin; and calculating the ratio of the current residual electric quantity of the power utilization unit to the power utilization residual quantity, and if the ratio is smaller than a preset residual quantity threshold value, giving out an early warning of insufficient power supply of the power utilization unit. The invention aims to optimize power resource configuration by formulating an effective power management strategy so as to ensure the stability of power supply.

Description

Technical Field

[0001] The present invention generally relates to the field of control technology. More specifically, the present invention relates to a method and system for detecting intelligent dispatching and early warning of power supply and distribution. Background Art

[0002] Power supply and distribution dispatching is the core link of power system operation. Its task is to ensure the safe, stable and economic operation of the power system by commanding, supervising and managing power production and operation. This includes the coordination and control of multiple links such as power generation, transmission, transformation, distribution and power consumption.

[0003] The power demand of power consumption units (such as residential areas, commercial areas, administrative areas, etc.) fluctuates with time (such as different times of the day), which makes power supply and distribution dispatching face huge challenges. In order to optimize power supply and distribution, power companies need to take a series of measures. However, traditional power grid dispatching often relies on the experience of dispatchers and a set of fixed operating rules, which limits the flexibility and accuracy of dispatching decisions when faced with emergencies or non-standard operating situations. In addition, dispatchers' power grid dispatching tends to be post-dispatching, and it is impossible to predict and plan in advance.

[0004] Therefore, in order to meet these challenges, an intelligent scheduling early warning detection method and system are needed to achieve optimal allocation of power resources, reduce the risk of insufficient power supply, and provide early warning of possible power shortages. Summary of the invention

[0005] In order to solve the technical problem of unbalanced power resource allocation in the above-mentioned traditional power dispatching, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a method for detecting early warning of intelligent dispatching of electric power supply and distribution comprises: The daily electricity consumption of the electricity consumption unit for a set number of days is collected, and the daily electricity consumption is clustered to obtain multiple clusters, each of which represents a time period electricity consumption sequence with similar electricity consumption behavior within a day; Based on the power consumption sequence of each day, all power consumption periods are determined; any power consumption period is selected as the target period, and the power consumption period with a preset interval of days after the target period is used as the pending period, and the matching coefficient between the target period and the pending period and the periods before and after the pending period is calculated, and the power consumption period with the highest matching coefficient is selected as the power consumption period in the same cycle, and the interval of days is recorded as the cycle length, and the power consumption period with the highest matching coefficient is used as the new target period, and the matching coefficient is iteratively calculated until a power consumption period that coincides with any power consumption period in the same cycle is found, that is, a complete power consumption cycle is constructed; Calculating the cycle index of the power usage cycle, and expanding the cycle length of the power usage cycle according to a preset ratio, and when the corresponding cycle index is greater than a preset cycle threshold, taking the power usage cycle with the expanded cycle length as a valid cycle; Calculate the average power consumption of all power consumption periods within the effective period as the first average; calculate the average power consumption corresponding to each power consumption period within the effective period, and take the maximum value of the average power consumption corresponding to all power consumption periods as the second average; take the difference between the second average and the first average as the power margin; The ratio of the current remaining power of the power consuming unit to the power remaining capacity is calculated, and if the ratio is less than a preset remaining capacity threshold, an early warning of insufficient power supply of the power consuming unit is issued.

[0007] The present invention first clusters the daily electricity consumption to preliminarily identify the electricity consumption behavior patterns of electricity users, and then captures the electricity consumption rules of electricity users over a long period of time, and then constructs a power consumption cycle, and further screens out cycles with stable and predictable electricity consumption rules to provide a reliable basis for subsequent power consumption warnings. Then, by calculating the power margin, the power consumption fluctuations of the power users within the effective cycle and the potential growth space for electricity demand are understood. By calculating the ratio of the current remaining power to the power margin and comparing it with a preset margin threshold, when the ratio is less than the threshold, an early warning of insufficient power supply is issued, and the potential power consumption risks of the power users are discovered in advance, providing timely decision support for power dispatching and power supply management, and avoiding problems such as power outages or unstable power supply due to insufficient power consumption.

[0008] In order to ensure the stability and reliability of the power system, the present invention optimizes the use of power resources through prediction and planning, especially in the face of uncertainty of renewable energy and fluctuations in electricity demand.

[0009] In one embodiment, the clustering adopts ordered sample clustering.

[0010] In one embodiment, the step of determining all power usage time periods includes: The first step is to calculate the power consumption coefficients of the first day and the second day, the first day and the third day, and finally the first day and the last day of the set days, starting from the first day of the set days. When the power consumption coefficient of the first day and any day is greater than or equal to the preset coefficient threshold, all daily power consumption between the first day and the corresponding day is regarded as a power consumption period; Step 2: Starting from the next day after the end day of the electricity usage period determined in Step 1, repeat Step 1 to obtain a new electricity usage period; Step 3: Each time a new power usage period is determined, the starting point is updated as the next day of the end day of the current power usage period, and step 2 is repeated until all the set days are included in the power usage period.

[0011] In one embodiment, ; In the formula, is the electricity consumption coefficient of the first and second days, is the total number of electricity consumption sequences in the period included in the first day, is the total number of electricity consumption sequences in the period of the second day, For the first day The start time of the electricity consumption sequence in each period, For the first day The end time of the electricity consumption sequence in each period, For the second day The start time of the electricity consumption sequence in each period, For the second day The end time of the electricity consumption sequence in each period, For the first day The average power consumption of the power consumption sequence in each period, For the second day The average power consumption of the power consumption sequence in each period, is the maximum value.

[0012] In one embodiment, the process of obtaining the matching coefficient includes: Calculate the number of days that the target period overlaps with the pending period, and calculate the absolute value of the difference between the average power consumption of the target period and the average power consumption of the pending period; The product of the number of days of overlap between the target period and the pending period and the absolute value of the difference between the average power consumption of the target period and the average power consumption of the pending period is taken as the matching coefficient.

[0013] In one embodiment, the period index satisfies the relationship: ; In the formula, is the period index, For the cycle The number of days with electricity consumption period, For the cycle The average power consumption during each power consumption period, is a natural exponential function.

[0014] In one embodiment, the process of obtaining the remaining threshold includes: Calculate the average number of days of electricity consumption within the effective period; The number of days entering the valid cycle at the current moment is obtained, and the ratio of the difference between the average number of power consumption days in the valid cycle and the number of days entering the valid cycle at the current moment to the average number of power consumption days in the valid cycle is used as the surplus threshold.

[0015] In a second aspect, a system for intelligent dispatching and early warning detection of electric power supply and distribution includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned method for intelligent dispatching and early warning detection of electric power supply and distribution is implemented.

[0016] The beneficial effects of the present invention are: By clustering the daily electricity consumption of the electricity consumption unit for a set number of days, the electricity consumption sequences with similar electricity consumption behaviors can be classified into one category, thereby identifying different electricity consumption behavior patterns. The electricity consumption time periods are divided based on the clustering results. By selecting the target time period and the pending time period, calculating the matching coefficient, and iterating this process, the electricity consumption cycle can be constructed, that is, the periodic law of electricity consumption behavior can be identified. Analyzing the electricity consumption cycle helps to predict future electricity demand, provide a reliable basis for power dispatch, and optimize the allocation and use of power resources.

[0017] By further evaluating the periodicity and screening out effective periods with stable periodicity, and calculating the power surplus based on the effective period, power companies can allocate power resources more effectively to meet the power demand in different time periods and improve resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a method flow chart of steps S1-S6 in a method for intelligent dispatching and early warning detection of electric power supply and distribution in an embodiment of the present invention.

[0019] Figure 2 It is a structural block diagram of a valve intelligent control system based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] The application scenario of the present invention is to complete intelligent scheduling of power supply and distribution according to the power consumption habits of power users.

[0022] The embodiment of the present invention discloses a method for detecting intelligent dispatching of electric power supply and distribution, referring to Figure 1, including steps S1-S6, which are as follows: S1: Collect the daily electricity consumption of the electricity consumption unit for a set number of days, cluster the daily electricity consumption, and obtain multiple clusters. Each cluster represents a time period electricity consumption sequence with similar electricity consumption behavior within a day.

[0023] First, the daily power consumption data of the power consumption unit is collected. This data can be the daily power consumption (in kilowatt-hours) of the power consumption unit in the power department collection system in the past month, half a year or a year. In the implementation of the present invention, the daily power consumption of the power consumption unit in the past month is collected. The power consumption unit can be a residential area, an administrative area or a commercial area.

[0024] Then, the collected data is preprocessed, including filling in missing data and removing abnormal data.

[0025] Finally, the electricity consumption data of each day in the past month is taken as a sample point, and ordered sample clustering is used to perform cluster analysis on the daily electricity consumption of each day in the past month. Different time periods of the day are grouped according to the similarity of electricity consumption behavior, and then multiple clusters corresponding to each day are obtained. It should be noted that each cluster is actually a subsequence, representing the electricity consumption data in a specific time period. This specific time period can be different time periods of the day (such as morning peak, evening peak, etc.).

[0026] It should be noted that the use of ordered sample clustering can effectively distinguish the time periods of daily electricity consumption changes. This means that within the same cluster, the change in electricity consumption will not be too large, showing similar electricity consumption behavior. For example, a cluster may include the morning peak period of the day, and the electricity consumption during this period may show a similar growth or decline trend. The time periods between different clusters show more significant changes in electricity consumption, and there are obvious differences in electricity consumption behavior. For example, the changes in electricity consumption during the morning peak and evening peak may belong to different clusters because they have different electricity consumption patterns and peak time points during the day.

[0027] S2: Based on the time period electricity consumption data sequence of each day, determine all electricity consumption time periods.

[0028] Based on the above S1, the power consumption sequence of each day is obtained, and the similarity between the power consumption patterns calculated at different times is compared. Through comparison, it can be determined whether the power consumption behaviors in different time periods are similar.

[0029] In one embodiment, specifically, in the first step, starting from the first day of the set number of days, the power consumption coefficients of the first day and the second day, the first day and the third day, and finally the first day and the last day of the set number of days are calculated in sequence. When the power consumption coefficient of the first day and any day is greater than or equal to a preset coefficient threshold (the coefficient threshold is 0.5 in the example of the present invention. If the power consumption data fluctuates greatly, the coefficient threshold can be appropriately adjusted to distinguish different power consumption periods), that is, all daily power consumption between the first day and this day is regarded as a power consumption period; Step 2: Starting from the day after the end of the electricity consumption period determined in Step 1, repeat Step 1 (i.e., calculate the electricity consumption coefficient of the new starting point and each subsequent day) to obtain a new electricity consumption period; Step 3: Each time a new power usage period is determined, the starting point is updated as the next day of the end day of the current power usage period, and step 2 is repeated until all the set days are included in the power usage period.

[0030] By continuously updating the starting point and calculating the power consumption coefficient, the continuous power consumption data is divided into multiple power consumption periods. Each power consumption period is determined based on whether the power consumption coefficient reaches or exceeds the preset threshold. This method can help identify changes in power consumption patterns, thereby better managing and optimizing power resources.

[0031] In another embodiment, when determining whether a power consumption period is completed, by setting flexible days, abnormal power consumption in a short period of time can be ignored. For example, if a special event (such as holidays, extreme weather, etc.) causes abnormal power consumption on a certain day, but this abnormality is not continuous, it will not affect the division of the power consumption period.

[0032] Exemplarily, the flexible days are set to 3 days. For example, when the power consumption coefficients of the first and second days, the first and third days, and the first and fourth days are all greater than the preset coefficient threshold, all daily power consumption between the first and fourth days will be regarded as a power consumption period.

[0033] The introduction of flexible days is to make the division of electricity use periods more in line with actual electricity consumption, reduce the impact of short-term fluctuations, and maintain the flexibility and practicality of the division method. This method helps to more accurately identify long-term changes in electricity consumption patterns and provide more practical data support for power management and energy planning.

[0034] The calculation formula of the power consumption coefficient on the first day and the second day is given as an example: In the formula, is the electricity consumption coefficient of the first and second days, is the total number of electricity consumption sequences in the period included in the first day, is the total number of electricity consumption sequences in the period of the second day, For the first day The starting time of the electricity consumption sequence in each period, For the first day The end time of the electricity consumption sequence in each period, For the second day The start time of the electricity consumption sequence in each period, For the second day The end time of the electricity consumption sequence in each period, For the first day The average power consumption of the power consumption sequence in each period, For the second day The average power consumption of the power consumption sequence in each period, is the maximum value.

[0035] The above polynomial for the power consumption coefficient can be decomposed into three main parts: Part I: Proportional Differences: ; Part 2: Sum of absolute differences: ;in, It reflects the similarity of the length of the electricity consumption sequence in the two periods. It reflects the similarity of actual power consumption in the power consumption sequences of two time periods.

[0036] Part 3: Maximum time difference: ; It should be noted that the maximum time difference does not directly participate in the calculation of the power consumption coefficient, but is an important condition for screening and determining which pair of time period data is used for calculation. The role of this maximum time difference is to ensure that the starting points of the corresponding accumulation units are close to avoid the problem of deviation in the starting time of the power consumption sequence of similar time periods within two days. Specifically, by limiting The maximum value of can ensure that the selected time periods of the first and second days match as much as possible in time, thereby reducing the analysis error caused by time differences.

[0037] S3: Construct a power consumption cycle based on the power consumption period.

[0038] The electricity consumption per user point is not constant, but fluctuates with different factors (such as seasons, production demand, etc.). This change in the electricity consumption cycle is very important for power supply and grid management. Planning power production and distribution based on periodic changes ensures that demand can be met during peak hours and avoids resource waste during low hours.

[0039] In order to analyze the periodicity of electricity consumption, it is first necessary to determine the period determination method.

[0040] Specifically, any electricity consumption period is selected as the target period, and the electricity consumption period with a preset interval of days after the target period is used as the pending period. The matching coefficients between the target period and the pending period and the periods before and after the pending period are calculated. The electricity consumption period with the highest matching coefficient is selected as the electricity consumption period in the same cycle, and the interval of days is recorded as the cycle length. The electricity consumption period with the highest matching coefficient is used as the new target period, and the matching coefficient is iteratively calculated until a electricity consumption period that coincides with any electricity consumption period in the same cycle is found, that is, a complete electricity consumption cycle is constructed.

[0041] For example, the interval is set to 5 days, and the electricity consumption period corresponding to the target period after 5 days is taken as the pending period, and the matching coefficients of the target period, the pending period, and the periods before and after the pending period are calculated; The calculation process of the matching coefficient between the target time period and the pending time period is given as an example: Calculate the number of days that the target period overlaps with the pending period, and calculate the absolute value of the difference between the average power consumption of the target period and the average power consumption of the pending period; The product of the number of days of overlap between the target period and the pending period and the absolute value of the difference between the average power consumption of the target period and the average power consumption of the pending period is taken as the matching coefficient.

[0042] That is, the matching coefficient between the target period and the pending period satisfies the relationship: In the formula, is the matching coefficient between the target period and the pending period, is the number of power consumption sequences within the target period, is the number of power consumption sequences in the undetermined period, is the number of days that the target period overlaps with the pending period. It is the absolute value of the difference between the average power consumption in the target period and the average power consumption in the pending period.

[0043] According to the calculation formula of the matching coefficient between the target period and the pending period, the matching coefficient between the target period and the periods before and after the pending period can be calculated in the same way.

[0044] The target period is further labeled , and mark the electricity consumption period with the largest matching coefficient as ,Right now is considered to be The next electricity consumption period in the same cycle.

[0045] Further Set as the new current power consumption period, repeatedly calculate the corresponding matching coefficient and find the next power consumption period of the same cycle , continue iterating the calculation until a power consumption period coincides with a previous power consumption period (that is, returns to the starting point) or reaches the end of the data, thereby constructing a complete power consumption cycle.

[0046] The set interval days (such as the 5 days set above) is used as the length of the power consumption cycle.

[0047] By repeating the above steps, all power usage time periods are traversed, thereby identifying multiple power usage cycles, each of which is composed of a series of power usage time periods with the largest matching coefficient.

[0048] S4: Calculate the cycle index of the power usage cycle, and expand the cycle length of the power usage cycle according to a preset ratio. When the corresponding cycle index is greater than a preset cycle threshold, the power usage cycle with the expanded cycle length is taken as a valid cycle.

[0049] All the power consumption cycles obtained based on S3 above provide a basic periodic pattern, but in some cases, there may be some abnormal values ​​or noise in the cycle, which cannot accurately reflect the real law of power consumption.

[0050] Specifically, the cycle index of the power consumption cycle is calculated, that is, the relationship is satisfied: In the formula, is the period index, For the cycle The number of days with electricity consumption period, For the cycle The average power consumption during each power consumption period, is a natural exponential function.

[0051] Among them, with and The standard deviation of The value of decreases.

[0052] Furthermore, the cycle threshold is set to 0.55. If the initial setting of the equal interval days is 5 days, the cycle index When it is less than 0.55, the number of equal interval days can be increased to 6 days, and then the cycle index can be recalculated. If the cycle index still does not meet 0.55, continue to increase the number of equal interval days, such as increasing it to 7 days, and calculate the cycle index again. This process continues until the cycle index exceeds 0.55, at which point the number of equal interval days is the required effective cycle.

[0053] S5: Calculate the average power consumption of all power consumption periods within the effective period as the first average; calculate the average power consumption corresponding to each power consumption period within the effective period, and take the maximum value of the average power consumption corresponding to all power consumption periods as the second average; take the difference between the second average and the first average as the power margin.

[0054] Specifically, the average power consumption of all power consumption time periods within the effective period is calculated as the first average; the average power consumption corresponding to each power consumption time period within the effective period is calculated, and the maximum value of the average power consumption corresponding to all power consumption time periods is taken as the second average; the difference between the second average and the first average is taken as the power margin.

[0055] By calculating the extra power that needs to be accumulated in the energy storage device (such as a battery) of the power unit during the effective cycle, it is possible to clearly know how much extra power the power unit needs to accumulate during a certain effective cycle to meet its power demand. This helps prevent power outages or power shortages caused by insufficient power.

[0056] S6: Calculate the ratio of the current remaining power of the power consuming unit to the power remaining capacity. If the ratio is less than a preset remaining capacity threshold, issue a warning that the power consumption unit is undersupplied.

[0057] Specifically, when calculating the power reserve and evaluating whether the remaining power is sufficient to support future power demand, we need to consider the number of days from a certain starting point (such as a specific date, time or time period) to the current moment in this effective cycle. Because as the effective cycle progresses, the remaining power of the power unit will gradually decrease, and the power required in the future will be predicted based on the power consumption pattern and the average power consumption. If the remaining power is not enough to support the power demand for a period of time in the future, then measures need to be taken in advance to accumulate power or adjust the power consumption plan.

[0058] Furthermore, the ratio of the difference between the average number of electricity consumption days in the effective period and the number of days entering the effective period to the average number of electricity consumption days in the effective period is used as the surplus threshold; Get the number of days that have passed from the start time of the effective period to the current time. The ratio of the difference between the average number of electricity consumption days in the effective period and the number of days that have passed from the start time of the effective period to the current time to the average number of electricity consumption days in the effective period is used as the remaining power threshold.

[0059] Furthermore, the ratio of the current remaining power of the power unit (i.e., the power remaining in the user's single energy storage device at the current moment) to the remaining power is calculated. When the ratio of the current remaining power of the power unit to the remaining power is less than the remaining power threshold, it means that the remaining power of the power unit may not be enough to support its power demand for a period of time in the future. At this time, the system or distribution unit can issue an early warning to remind the power unit to pay attention to the management of power consumption, or take timely measures (such as increasing the capacity of the storage battery, adjusting the power consumption plan, etc.) to avoid insufficient power supply.

[0060] Through accurate management and early warning of power consumption, power distribution units can allocate power resources more reasonably and ensure the stability and reliability of power supply. At the same time, this will also help reduce power waste and improve the efficiency of power use.

[0061] An embodiment of the present invention also discloses an intelligent dispatching and early warning detection system for electric power supply and distribution, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent dispatching and early warning detection method for electric power supply and distribution according to the present invention is implemented.

[0062] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0063] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0064] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0065] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for early warning detection of intelligent dispatching of electric power supply and distribution, characterized in that: include: The daily electricity consumption of the electricity consumption unit for a set number of days is collected, and the daily electricity consumption is clustered to obtain multiple clusters, each of which represents a time period electricity consumption sequence with similar electricity consumption behavior within a day; Based on the power consumption sequence of each day, determine all power consumption periods; Select any electricity consumption period as the target period, and take the electricity consumption period with a preset interval of days after the target period as the pending period, calculate the matching coefficient between the target period and the pending period and the periods before and after the pending period, select the electricity consumption period with the highest matching coefficient as the electricity consumption period in the same cycle, record the interval of days as the cycle length, take the electricity consumption period with the highest matching coefficient as the new target period, iteratively calculate the matching coefficient until a electricity consumption period that coincides with any electricity consumption period in the same cycle is found, that is, a complete electricity consumption cycle is constructed; Calculating the cycle index of the power usage cycle, and expanding the cycle length of the power usage cycle according to a preset ratio, and when the corresponding cycle index is greater than a preset cycle threshold, taking the power usage cycle with the expanded cycle length as a valid cycle; Calculate the average power consumption of all power consumption periods within the effective period as the first average; calculate the average power consumption corresponding to each power consumption period within the effective period, and take the maximum value of the average power consumption corresponding to all power consumption periods as the second average; take the difference between the second average and the first average as the power margin; The ratio of the current remaining power of the power consuming unit to the power remaining capacity is calculated, and if the ratio is less than a preset remaining capacity threshold, an early warning of insufficient power supply of the power consuming unit is issued.

2. According to claim 1, a method for detecting intelligent dispatching of electric power supply and distribution, characterized in that: The clustering adopts ordered sample clustering.

3. The method for detecting intelligent dispatching of electric power supply and distribution according to claim 2 is characterized in that: The step of determining all electricity usage time periods comprises: The first step is to calculate the power consumption coefficients of the first day and the second day, the first day and the third day, and finally the first day and the last day of the set days, starting from the first day of the set days. When the power consumption coefficient of the first day and any day is greater than or equal to the preset coefficient threshold, all daily power consumption between the first day and the corresponding day is regarded as a power consumption period; Step 2: Starting from the next day after the end day of the electricity usage period determined in Step 1, repeat Step 1 to obtain a new electricity usage period; Step 3: Each time a new power usage period is determined, the starting point is updated as the next day of the end day of the current power usage period, and step 2 is repeated until all the set days are included in the power usage period.

4. The method for detecting intelligent dispatching of electric power supply and distribution according to claim 3 is characterized in that: The electricity consumption coefficients on the first and second days satisfy the following relationship: ; In the formula, is the electricity consumption coefficient of the first and second days, is the total number of electricity consumption sequences in the period included in the first day, is the total number of electricity consumption sequences in the period of the second day, For the first day The starting time of the electricity consumption sequence in each period, For the first day The end time of the electricity consumption sequence in each period, For the second day The starting time of the electricity consumption sequence in each period, For the second day The end time of the electricity consumption sequence in each period, For the first day The average power consumption of the power consumption sequence in each period, For the second day The average power consumption of the power consumption sequence in each period, is the maximum value.

5. The method for detecting intelligent dispatching of electric power supply and distribution according to claim 4 is characterized in that: The process of obtaining the matching coefficient includes: Calculate the number of days that the target period overlaps with the pending period, and calculate the absolute value of the difference between the average power consumption of the target period and the average power consumption of the pending period; The product of the number of days of overlap between the target period and the pending period and the absolute value of the difference between the average power consumption of the target period and the average power consumption of the pending period is taken as the matching coefficient.

6. A method for detecting intelligent dispatching of electric power supply and distribution according to claim 5, characterized in that: The periodic index satisfies the relationship: ; In the formula, is the period index, For the cycle The number of days with electricity consumption period, For the cycle The average power consumption during each power consumption period, is a natural exponential function.

7. A method for detecting intelligent dispatching of electric power supply and distribution according to claim 6, characterized in that: The process of obtaining the remaining threshold value includes: Calculate the average number of days of electricity consumption within the effective period; The number of days entering the valid cycle at the current moment is obtained, and the ratio of the difference between the average number of power consumption days in the valid cycle and the number of days entering the valid cycle at the current moment to the average number of power consumption days in the valid cycle is used as the surplus threshold.

8. An intelligent dispatching early warning detection system for power supply and distribution, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the electric power supply and distribution intelligent dispatching early warning detection method according to any one of claims 1-7 is implemented.

Images