Power plant data processing and analysis system based on big data technology

Abstract

The invention discloses a power plant data processing and analysis system based on a big data technology, and relates to the technical field of data processing and analysis, and the system comprises a data collection module which is configured to obtain the power generation data and the power consumption fund consumption data of a power plant; the regional grid division module is configured to perform unit grid division on a power supply region based on a clustering algorithm, and input of the clustering algorithm comprises population density data and economic level data; and the power demand analysis module is configured to predict future power consumption data of each unit grid according to the power consumption fund consumption data. According to the method, the power consumption demands in the divided regional grids are deeply analyzed in combination with historical data, power consumption value data of different regions are predicted, a reliable basis is provided for power distribution, the stability and efficiency of power supply are improved, and the power consumption demands of different regions are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and analysis, and in particular to a power plant data processing and analysis system based on big data technology. Background Art

[0002] A power plant is a power plant that converts some form of raw energy into electricity for fixed facilities or transportation. Examples include thermal, hydro, steam, diesel, or nuclear power plants. With the rapid development of the power industry, power plants generate massive amounts of data during operation. This data originates from various equipment and systems within the power plant, such as generators, boilers, turbines, and control systems. Traditional data processing and analysis methods are no longer sufficient to handle this large amount of data. In the power distribution process, traditional methods lack accurate analysis of regional electricity demand and typically employ a more extensive distribution approach, transmitting electricity based on fixed ratios or empirical evidence. This approach fails to fully consider regional differences and fails to incorporate factors such as population density and economic level. This can lead to power shortages in some densely populated and economically developed areas, impacting local production and life. Meanwhile, some sparsely populated and economically underdeveloped regions may experience a waste of power resources, resulting in irrational power distribution. To address this, we propose a power plant data processing and analysis system based on big data technology. Summary of the Invention

[0003] In order to solve the above technical problems, a power plant data processing and analysis system based on big data technology is provided. This technical solution solves the above-mentioned problem of unreasonable allocation of power resources.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: a power plant data processing and analysis system based on big data technology, comprising:

[0005] a data acquisition module configured to obtain power generation data and electricity financial consumption data of the power plant;

[0006] A regional grid division module configured to divide the power supply area into unit grids based on a clustering algorithm, wherein the input of the clustering algorithm includes population density data and economic level data;

[0007] The power demand analysis module is configured to predict the future power consumption data of each unit grid based on the power capital consumption data;

[0008] The regional priority allocation module is configured to calculate and sort the electricity consumption priorities of each unit grid based on the industrial production importance, people's livelihood security and commercial impact indicators;

[0009] A dynamic adjustment module is configured to monitor the power consumption data of each unit grid in real time and dynamically adjust the power consumption priority by comparing it with a preset power consumption threshold range;

[0010] The power dispatching and transmission module is configured to distribute the power supply of each unit grid in proportion according to the adjusted power consumption priority and power generation data.

[0011] Preferably, the data acquisition module obtains the power generation and power capital consumption data of the power plant from the power plant database; the regional grid division module standardizes the population density data and economic level data through a clustering algorithm, and calculates the similarity to complete the unit grid division.

[0012] Preferably, the specific steps of unit grid division are: standardizing the population density and economic level data, converting them into standard normal distribution data based on the Z-score method, calculating the similarity of distribution data points using Euclidean distance, dividing the data points according to similarity based on the clustering algorithm until the clustering converges, and dividing the geographic space into unit grids based on the clustering results;

[0013] Standardization processing: Let the population density data be x i , economic level data is y i , the population density data standardization formula is:

[0014]

[0015] in x i is the population density data; the standardization formula for economic level data is:

[0016]

[0017] in y i is the mean of economic level data;

[0018] For the normalized data points and The similarity calculation is based on the Euclidean distance formula. The calculation formula is:

[0019]

[0020] where d E The smaller it is, the higher the similarity is, and vice versa;

[0021] Clustering, based on similarity d E As a result, the data points are divided into different clusters, K initial cluster centers are selected, and and Data points are assigned to the most similar cluster centers, and the cluster centers are updated repeatedly until the cluster to which each data point belongs no longer changes, and areas with similar population density and economic level are divided into the same unit grid.

[0022] Preferably, the power demand analysis module predicts the future power consumption data of the unit grid based on the time series decomposition method, including: decomposing the power consumption data into trend items A t 、Seasonal item B' t 、Periodic term C t , random term D' t , and calculate the predicted value of electricity consumption data, the calculation expression is:

[0023] Y t =A t +B' t +C t +D' t

[0024] Where Y t To obtain the predicted value of electricity consumption data in different regions through time series calculation;

[0025] Among them, the trend item is obtained by linear fitting calculation, the seasonal item is determined by calculating the average seasonal deviation of each season by historical data. When making a forecast, it is selected based on the current season at the time of forecast, and the cycle item is determined by extracting cycle characteristics.

[0026] Preferably, the priority calculation in the regional priority allocation module is based on the importance of industrial production, the degree of people's livelihood security and the degree of commercial influence, wherein the calculation formula is:

[0027] P=w1*E′+w2*F′+w3*G′

[0028] Where P is the electricity priority calculated for different regions, w1, w2, and w3 are the weights corresponding to the importance of industrial production, livelihood security, and commercial impact, respectively; E′ is the importance of industrial production, F′ is the livelihood security, and G′ is the commercial impact;

[0029] The quantification steps for E′ industrial production importance, F′ people's livelihood security and G′ commercial influence are: through collection, determine the evaluation indicators, including the total industrial output value, the classification results of daily necessities and the sales share of commercial stores in the market, standardize the obtained evaluation indicator data, determine the indicator weights, and calculate them based on the scores.

[0030] Preferably, the weight values corresponding to the importance of industrial production, the degree of people's livelihood security and the degree of commercial influence are determined based on the entropy weight method. Samples of the area surrounding the power plant are obtained through big data. For the three indicators of industrial production importance E', people's livelihood security F' and commercial influence G', their data are standardized to obtain the standardized matrix X = (x ij)m×3, where xij is the jth indicator value of the i-th regional sample, and the standardization method formula is:

[0031]

[0032] The same is true for F′ and G′; the information entropy of the j-th indicator is calculated using the following formula:

[0033]

[0034] in

[0035] The weight of each indicator is calculated according to the information entropy. The calculation formula is:

[0036]

[0037] Among them, w1 corresponds to the weight of industrial production importance, w2 corresponds to the weight of people's livelihood security, and w3 corresponds to the weight of commercial influence; through the above simultaneous calculations, the weight values corresponding to industrial production importance, people's livelihood security and commercial influence are obtained.

[0038] Preferably, the power to be transmitted is intelligently allocated based on the sorting priority and the power generation data of the power plant. The allocation is based on the total power generation value of the power plant. In combination with the obtained priority, the power consumption values of different regional intervals are allocated and calculated. It is assumed that there are n′ divided regional intervals, where the power consumption priority of the i-th area is Pi, and the sum of all regional priorities is calculated as follows:

[0039]

[0040] Ph is the sum of all regional priorities, and the total power generation of the power plant is H′. The formula for calculating the power allocated to the i-th region is:

[0041]

[0042] Hi is the amount of electricity allocated to the i-th region, and the amount of electricity transmitted to different regions is intelligently allocated.

[0043] Preferably, the dynamic adjustment module collects historical electricity consumption data and calculates the quantiles of the historical electricity consumption data through the quantile method, including the 25% quantile and the 75% quantile, and uses them as the lower limit and upper limit of the electricity consumption threshold range; when the real-time electricity consumption exceeds the threshold range, the priority adjustment is triggered.

[0044] Preferably, the process of priority adjustment is:

[0045] Assume that the real-time power consumption monitoring value of the i-th region is M' i , the original electricity priority is The lower limit of the power consumption threshold is L' i , the upper limit of power consumption threshold is U i When the power consumption is lower than the threshold, the priority adjustment coefficient is k'1; when the power consumption is higher than the threshold, the priority adjustment coefficient is k'2. The adjusted power priority Pt i for:

[0046]

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention divides the region into grids, scientifically subdivides the region, grasps the characteristics of electricity consumption, combines historical data to predict electricity consumption values, and assists in planning supply. The regional priority allocation module calculates the electricity priority, and intelligently allocates electricity based on the power generation capacity to ensure electricity consumption in key areas and improve resource utilization efficiency. Power dispatching and transmission are scheduled based on priority and allocation results, and electricity consumption thresholds are set by using big data. Real-time monitoring and comparison are carried out, and priorities are flexibly adjusted to enable the system to adapt to changes in demand. The various modules of the system work together to achieve full-process optimization from data to scheduling, improve power utilization efficiency, reduce losses, and ensure power supply and stable economic and social development.

[0049] The present invention combines historical data to conduct an in-depth analysis of electricity demand within the divided regional grids, predicts electricity consumption data for different regions, and provides a reliable basis for power distribution. The regional priority distribution module calculates and sorts the electricity consumption priorities of different regions, and realizes intelligent power distribution in combination with power generation data of power plants. The dynamic adjustment module uses big data to monitor power consumption in real time and dynamically adjusts power priority to ensure that the power distribution plan can adapt to changes in a timely manner. The power dispatching and transmission module performs accurate power dispatching based on priority sorting and power distribution results, improves the stability and efficiency of power supply, and guarantees power demand in different regions. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a framework diagram of the power plant data processing and analysis system of the present invention;

[0051] Figure 2 Flowchart of the allocation steps of the regional priority allocation module of the present invention. DETAILED DESCRIPTION

[0052] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0053] Reference Figures 1 to 2 As shown in the figure, the power plant data processing and analysis system based on big data technology includes:

[0054] a data acquisition module configured to obtain power generation data and electricity financial consumption data of the power plant;

[0055] A regional grid division module configured to divide the power supply area into unit grids based on a clustering algorithm, wherein the input of the clustering algorithm includes population density data and economic level data;

[0056] The power demand analysis module is configured to predict the future power consumption data of each unit grid based on the power capital consumption data;

[0057] The regional priority allocation module is configured to calculate and sort the electricity consumption priorities of each unit grid based on the industrial production importance, people's livelihood security and commercial impact indicators;

[0058] A dynamic adjustment module is configured to monitor the power consumption data of each unit grid in real time and dynamically adjust the power consumption priority by comparing it with a preset power consumption threshold range;

[0059] The power dispatching and transmission module is configured to distribute the power supply of each unit grid in proportion according to the adjusted power consumption priority and power generation data.

[0060] This application obtains real-time data on power plant generation and electricity capital consumption, providing a real and comprehensive data source for subsequent analysis. It integrates power production and consumption data, breaks down information silos, and supports multi-dimensional analysis. Based on key indicators such as population density and economic level, it subdivides regions into unit grids, accurately reflecting the electricity consumption characteristics of different regions and providing spatially refined support for subsequent demand analysis and priority allocation. By analyzing historical electricity consumption data, it predicts future electricity consumption values for each grid, improving the foresight of power supply planning. It also explores electricity consumption patterns in different regions and optimizes resource allocation in a targeted manner. It determines regional electricity priority based on electricity demand and socioeconomic factors, ensuring that resources are allocated to high-value areas. Based on power generation and priority, it achieves optimal allocation of power resources and improves overall utilization efficiency. By dynamically comparing power consumption thresholds, it adjusts priorities in real time to adapt to sudden changes in demand, reduces manual intervention, and enhances the system's robustness to complex scenarios. Based on priority and allocation results, it enables targeted power transmission, reduces transmission losses, optimizes power exchange paths, reduces overload risks, improves grid reliability, reduces power waste and shortages, and maximizes the economic benefits per unit of power.

[0061] The data acquisition module obtains the power generation and power capital consumption data of the power plant from the power plant database; the regional grid division module standardizes the population density data and economic level data through clustering algorithm, and calculates the similarity to complete the unit grid division.

[0062] This application obtains power generation and capital consumption data from the power plant database, providing a reliable basis for analyzing the operating status of the power plant, helping to evaluate the cost-effectiveness of power generation, and optimizing power generation strategies. It can obtain the latest data in real time to reflect the dynamic changes of the power plant. The continuity of data can be used for long-term trend analysis and assist in formulating long-term plans. The collected data serves multiple departments such as production, finance, and operations. Each department adjusts its strategy based on the data to achieve collaborative decision-making and improve the operating efficiency of the power plant. The unit grid is divided according to population density and economic level to clearly show the electricity consumption characteristics of different regions, which facilitates the power plant to reasonably configure power supply facilities according to the characteristics of different regions, allocate electricity according to the grid electricity demand characteristics, ensure power supply in areas with high demand, avoid resource waste, improve power supply efficiency, and provide a spatial layout reference for power grid planning and construction. Based on the division results and electricity demand forecast, the power grid facilities are scientifically planned to reduce costs, enhance stability and reliability, and use big data to obtain updated population density and GDP data in real time to adapt to urban development changes in a timely manner, re-divide the grid and adjust the power supply strategy.

[0063] The specific steps of unit grid division are as follows: standardize the population density and economic level data, convert them into standard normal distribution data based on the Z-score method, calculate the similarity of distribution data points using Euclidean distance, divide the data points according to similarity based on clustering algorithm until the clustering converges, and divide the geographic space into unit grids based on the clustering results;

[0064] Standardization processing: Let the population density data be x i , economic level data is y i , the population density data standardization formula is:

[0065]

[0066] in x i is the population density data; the standardization formula for economic level data is:

[0067]

[0068] in y i is the mean of economic level data;

[0069] For the normalized data points and The similarity calculation is based on the Euclidean distance formula. The calculation formula is:

[0070]

[0071] where d E The smaller it is, the higher the similarity is, and vice versa;

[0072] Clustering, based on similarity d E As a result, the data points are divided into different clusters, K initial cluster centers are selected, and and Data points are assigned to the most similar cluster centers, and the cluster centers are updated repeatedly until the cluster to which each data point belongs no longer changes, and areas with similar population density and economic level are divided into the same unit grid.

[0073] The power demand analysis module predicts the future power consumption data of the unit grid based on the time series decomposition method, including: decomposing the power consumption data into trend items A t 、Seasonal item B' t 、Periodic term C t , random term D' t , and calculate the predicted value of electricity consumption data, the calculation expression is:

[0074] Y t =A t +B' t +C t +D' t

[0075] Where Y t To obtain the predicted value of electricity consumption data in different regions through time series calculation;

[0076] Among them, the trend item is obtained by linear fitting calculation, the seasonal item is determined by calculating the average seasonal deviation of each season by historical data. When making a forecast, it is selected based on the current season at the time of forecast, and the cycle item is determined by extracting cycle characteristics.

[0077] This application subdivides electricity demand into trends, seasons, cycles and random items, comprehensively considers multiple factors, combines electricity capital consumption, comprehensively captures electricity consumption patterns, improves forecast accuracy, provides a reliable basis for power plants and power departments, rationally plans power generation plans, optimizes grid construction and transformation, avoids insufficient or excessive power supply, improves resource utilization efficiency, fully considers the impact of seasons on electricity consumption, flexibly responds to seasonal fluctuations, prepares response measures in advance, improves energy utilization efficiency, meets electricity demand in different seasons, incorporates uncertainty factors, reduces the impact of emergencies on power supply and operations, stabilizes the supply and demand balance in the power market, and ensures the stable and healthy development of the power market.

[0078] The priority calculation in the regional priority allocation module is based on the importance of industrial production, livelihood security and commercial impact. The calculation formula is:

[0079] P=w1*E′+w2*F′+w3*G′

[0080] Where P is the electricity priority obtained by calculating the different regions, w1, w2 and w3 are the weights corresponding to the importance of industrial production, livelihood security and commercial impact respectively, E' is the importance of industrial production, F' is the livelihood security, and G' is the commercial impact;

[0081] The quantification steps for E' industrial production importance, F' livelihood security, and G' commercial influence are: determine the evaluation indicators through collection, including the total industrial output value, the classification results of daily necessities, and the sales share of commercial stores in the market; standardize the obtained evaluation indicator data, determine the indicator weights, and calculate them based on the scores;

[0082] The important quantitative steps of industrial production are:

[0083] Determine evaluation metrics

[0084] Use industrial output value, added value, and output indicators to measure, analyze the degree of correlation between the industry and upstream and downstream industries, and use input-output ratio and industry dependence indicators to measure;

[0085] Collect data

[0086] Collect specific data for each indicator through corporate financial statements, statistical yearbooks, industry reports, and government statistical data channels;

[0087] Indicator standardization

[0088] Since the dimensions and value ranges of each indicator are different, they are standardized and converted into dimensionless values. Experts are invited to score the importance of each indicator through the Delphi method to determine the weight;

[0089] Calculating importance scores

[0090] The standardized index value is multiplied by the corresponding weight and then added to obtain the quantitative score of industrial production importance;

[0091] The steps for quantifying livelihood security are as follows:

[0092] Determine evaluation metrics

[0093] Classify them according to their indispensability in residents' lives, and measure them by the frequency of supply interruptions and the amplitude of supply fluctuations;

[0094] Collect data

[0095] Collect data from government departments' livelihood statistics, industry regulatory reports, corporate operation data, and social survey channels;

[0096] The same method as in the quantification step of important industrial production is used to standardize each indicator and determine its weight;

[0097] Calculating the livelihood security score

[0098] Multiply the standardized index value by the weight and sum them up to obtain the quantitative score of people's livelihood security;

[0099] Steps to quantify business impact

[0100] Market share, the sales or sales volume share of an enterprise or industry in a specific market, and the annual sales and net profit indicators of an enterprise, reflecting the scale and profitability of business activities;

[0101] Collect data

[0102] Collect data using market research agency data, corporate financial reports, industry research reports, and reports from brand evaluation agencies;

[0103] Indicator standardization and weight determination

[0104] The data were also processed using a standardization method and weights were determined;

[0105] Calculating business impact scores

[0106] Multiply the standardized indicator value by the weight and add them together to obtain a quantitative score of business impact;

[0107] Through the above quantitative steps, we can objectively and accurately quantify the importance of industrial production, the degree of people's livelihood security, and the commercial impact.

[0108] The regional priority allocation module of this application calculates the electricity priority through a specific formula. On the one hand, it accurately and reasonably allocates electricity resources, comprehensively considers industrial production, people's livelihood security and commercial impact, and assigns corresponding weights. It can accurately measure the urgency and importance of electricity demand in different regions. For example, in regions dominated by heavy industry, high weights are given to industry to avoid production stagnation due to power shortages and achieve rational allocation of resources; it effectively guarantees electricity demand in key areas, incorporates people's livelihood security into the calculation, ensures residents' daily electricity demand, and maintains social harmony and stability; considers the importance of industrial production, assists the development of key industrial regions, promotes economic growth and industrial upgrading; involves commercial influence, maintains the operation of commercial venues, and drives employment and commercial prosperity. This module is flexible and adaptable, and the weight values w1, w2, and w3 can be flexibly adjusted according to different periods and regions. In special periods such as post-disaster reconstruction, the weight of people's livelihood is increased, and the weight of industry is increased during the development stage of emerging industries. It can quickly adapt to complex scenarios and improve the overall operating efficiency of the power system.

[0109] The weights corresponding to the importance of industrial production, people's livelihood security and commercial impact are determined based on the entropy weight method. Samples of the area around the power plant are obtained through big data. For the three indicators of industrial production importance E', people's livelihood security F' and commercial impact G', their data are standardized to obtain the standardized matrix X = (x ij )m×3, where xij is the jth indicator value of the i-th regional sample, and the standardization method formula is:

[0110]

[0111] The same is true for F′ and G′; the information entropy of the j-th indicator is calculated using the following formula:

[0112]

[0113] in

[0114] The weight of each indicator is calculated according to the information entropy. The calculation formula is:

[0115]

[0116] Among them, w1 corresponds to the weight of industrial production importance, w2 corresponds to the weight of people's livelihood security, and w3 corresponds to the weight of commercial influence; through the above simultaneous calculations, the weight values corresponding to industrial production importance, people's livelihood security and commercial influence are obtained.

[0117] The entropy weight method of this application determines the weight based on the information entropy of the data itself, and does not rely on subjective judgment and experience. By collecting and standardizing sample data from the area around the power plant, the importance of each indicator is mined from the data, avoiding the interference of human factors in the weight assignment, and making the determination of the weight value more objective and fair; there are differences in industrial production structure, people's livelihood needs and commercial development levels in different regions. The entropy weight method can adaptively determine the weight of each indicator based on sample data from different regions; accurate weight values provide a solid foundation for regional priority allocation. When calculating electricity priority, based on objective and reasonable weights, it can more accurately reflect the importance of electricity demand in different regions.

[0118] According to the sorting priority, the power transmission is intelligently distributed in combination with the power generation data of the power plant. The distribution is based on the total power generation value of the power plant. Combined with the obtained priority, the power consumption value of different regional intervals is distributed and calculated. It is assumed that there are n′ divided regional intervals, where the power consumption priority of the i-th area is Pi, and the sum of all regional priorities is calculated as follows:

[0119]

[0120] Ph is the sum of all regional priorities, and the total power generation of the power plant is H′. The formula for calculating the power allocated to the i-th region is:

[0121]

[0122] Hi is the amount of electricity allocated to the i-th region, and the amount of electricity transmitted to different regions is intelligently allocated.

[0123] This application distributes electricity by combining the total power generation of power plants with the electricity consumption priorities of different regions, which can ensure that electricity resources flow to the areas that need them most. High-priority regions, areas involving important industrial production and people's livelihood security, can obtain relatively more electricity, avoid waste of electricity resources, achieve optimal allocation of resources, and improve the utilization efficiency of electricity resources; intelligent distribution based on priority and power generation helps to balance the load of the power grid, avoid overload of the power grid due to excessive power consumption in some areas, and also prevent insufficient power supply in other areas. By reasonably distributing electricity, the operation of the power grid is made more stable, and the risk of failures and accidents caused by uneven power distribution is reduced.

[0124] The dynamic adjustment module collects historical electricity consumption data and calculates the quantiles of the historical electricity consumption data through the quantile method, including the 25% quantile and the 75% quantile, and uses them as the lower and upper limits of the electricity consumption threshold range; when the real-time electricity consumption exceeds the threshold range, the priority adjustment is triggered.

[0125] This application collects historical electricity consumption data and calculates its 25% quantile and 75% quantile as the lower and upper limits of the threshold range. It can fully take into account the distribution characteristics of past electricity consumption, monitor electricity consumption in real time and compare it with the threshold, and quickly discover abnormal electricity consumption. When the electricity consumption exceeds the set threshold range, it indicates that a special electricity consumption event may have occurred. The threshold is dynamically optimized and adjusted according to the monitoring results and new data, so that the system can adapt to various changes. Over time, regional economic development, population growth, and industrial structure adjustment factors may cause changes in electricity consumption. By continuously collecting new data and adjusting the threshold, the electricity consumption threshold range can reflect these changes in a timely manner.

[0126] The monitored value is directly compared with the power usage threshold to determine whether the real-time monitored value falls within the power usage threshold. The priority adjustment process is as follows:

[0127] Assume that the real-time power consumption monitoring value of the i-th region is M' i , the original electricity priority is The lower limit of the power consumption threshold is L' i , the upper limit of power consumption threshold is U iWhen the power consumption is lower than the threshold, the priority adjustment coefficient is k'1; when the power consumption is higher than the threshold, the priority adjustment coefficient is k'2. The adjusted power priority Pt i for:

[0128]

[0129] The above formula is used to dynamically adjust the power priority; based on the adjusted power priority, the power supply in different areas is allocated and calculated again.

[0130] This application directly compares the monitoring value with the power consumption threshold, and can quickly determine whether the real-time power consumption is within the normal range. Once it is found that the power consumption deviates from the threshold, the power consumption priority is immediately adjusted according to the established formula, and the power supply is redistributed according to the dynamically adjusted power consumption priority to ensure that power flows first to areas with urgent power demand. When the total power supply is limited, this method avoids waste of resources and improves the utilization efficiency of unit power.

[0131] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. Various changes and improvements are possible without departing from the spirit and scope of the present invention, and such changes and improvements fall within the scope of the invention as claimed.

Claims

1. The power plant data processing and analysis system based on big data technology is characterized by: include: a data acquisition module configured to obtain power generation data and electricity financial consumption data of the power plant; A regional grid division module configured to divide the power supply area into unit grids based on a clustering algorithm, wherein the input of the clustering algorithm includes population density data and economic level data; The power demand analysis module is configured to predict the future power consumption data of each unit grid based on the power capital consumption data; The regional priority allocation module is configured to calculate and sort the electricity consumption priorities of each unit grid based on the industrial production importance, people's livelihood security and commercial impact indicators; A dynamic adjustment module is configured to monitor the power consumption data of each unit grid in real time and dynamically adjust the power consumption priority by comparing it with a preset power consumption threshold range; The power dispatching and transmission module is configured to distribute the power supply of each unit grid in proportion according to the adjusted power consumption priority and power generation data.

2. The power plant data processing and analysis system based on big data technology according to claim 1 is characterized in that: The data acquisition module obtains the power generation and power capital consumption data of the power plant from the power plant database; the regional grid division module standardizes the population density data and economic level data through clustering algorithm, and calculates the similarity to complete the unit grid division.

3. The power plant data processing and analysis system based on big data technology according to claim 2 is characterized in that: The specific steps of unit grid division are as follows: standardize the population density and economic level data, convert them into standard normal distribution data based on the Z-score method, calculate the similarity of distribution data points using Euclidean distance, divide the data points according to similarity based on clustering algorithm until the clustering converges, and divide the geographic space into unit grids based on the clustering results; Standardization processing: Let the population density data be x i , economic level data is y i , the population density data standardization formula is: in x i is the population density data; the standardization formula for economic level data is: in y i is the mean of economic level data; For the normalized data points and The similarity calculation is based on the Euclidean distance formula. The calculation formula is: where d E The smaller it is, the higher the similarity is, and vice versa; Clustering, based on similarity d E As a result, the data points are divided into different clusters, K initial cluster centers are selected, and and Data points are assigned to the most similar cluster centers, and the cluster centers are updated repeatedly until the cluster to which each data point belongs no longer changes, and areas with similar population density and economic level are divided into the same unit grid.

4. The power plant data processing and analysis system based on big data technology according to claim 1 is characterized in that: The power demand analysis module predicts the future power consumption data of the unit grid based on the time series decomposition method, including: decomposing the power consumption data into trend items A t 、Seasonal item B' t 、Periodic term C t , random term D' t , and calculate the predicted value of electricity consumption data, the calculation expression is: Y t =A t +B’ t +C t +D’ t Where Y t To obtain the predicted value of electricity consumption data in different regions through time series calculation; Among them, the trend item is obtained by linear fitting calculation, the seasonal item is determined by calculating the average seasonal deviation of each season by historical data. When making a forecast, it is selected based on the current season at the time of forecast, and the cycle item is determined by extracting cycle characteristics.

5. The power plant data processing and analysis system based on big data technology according to claim 1 is characterized in that: The priority calculation in the regional priority allocation module is based on the importance of industrial production, livelihood security and commercial impact. The calculation formula is: P=w1*E′+w2*F′+w3*G′ Where P is the electricity priority calculated for different regions, w1, w2, and w3 are the weights corresponding to the importance of industrial production, livelihood security, and commercial impact, respectively; E′ is the importance of industrial production, F′ is the livelihood security, and G′ is the commercial impact; The quantification steps for E′ industrial production importance, F′ people's livelihood security and G′ commercial influence are: through collection, determine the evaluation indicators, including the total industrial output value, the classification results of daily necessities and the sales share of commercial stores in the market, standardize the obtained evaluation indicator data, determine the indicator weights, and calculate them based on the scores.

6. The power plant data processing and analysis system based on big data technology according to claim 5 is characterized in that: The weights corresponding to the importance of industrial production, people's livelihood security and commercial impact are determined based on the entropy weight method. Samples of the area around the power plant are obtained through big data. For the three indicators of industrial production importance E', people's livelihood security F' and commercial impact G', their data are standardized to obtain the standardized matrix X = (x ij )m×3, where xij is the jth indicator value of the i-th regional sample, and the standardization method formula is: The same applies to F′ and G′; Calculate the information entropy of the j-th indicator. The calculation formula is: in The weight of each indicator is calculated according to the information entropy. The calculation formula is: Among them, w1 corresponds to the weight of industrial production importance, w2 corresponds to the weight of people's livelihood security, and w3 corresponds to the weight of commercial influence; through the above simultaneous calculations, the weight values corresponding to industrial production importance, people's livelihood security and commercial influence are obtained.

7. The power plant data processing and analysis system based on big data technology according to claim 1 is characterized in that: According to the sorting priority, the power transmission is intelligently distributed in combination with the power generation data of the power plant. The distribution is based on the total power generation value of the power plant. Combined with the obtained priority, the power consumption value of different regional intervals is distributed and calculated. It is assumed that there are n′ divided regional intervals, where the power consumption priority of the i-th area is Pi, and the sum of all regional priorities is calculated as follows: Ph is the sum of all regional priorities, and the total power generation of the power plant is H′. The formula for calculating the power allocated to the i-th region is: Hi is the amount of electricity allocated to the i-th region, and the amount of electricity transmitted to different regions is intelligently allocated.

8. The power plant data processing and analysis system based on big data technology according to claim 1 is characterized in that: The dynamic adjustment module collects historical electricity consumption data and calculates the quantiles of the historical electricity consumption data using the quantile method, including the 25% quantile and the 75% quantile, which are used as the lower and upper limits of the electricity consumption threshold range; When the real-time power consumption exceeds the threshold range, the priority adjustment is triggered.

9. The power plant data processing and analysis system based on big data technology according to claim 8 is characterized in that: The process of priority adjustment is: Assume that the real-time power consumption monitoring value of the i-th region is M' i , the original electricity priority is The lower limit of the power consumption threshold is L' i , the upper limit of power consumption threshold is U i When the power consumption is lower than the threshold, the priority adjustment coefficient is k'1; when the power consumption is higher than the threshold, the priority adjustment coefficient is k'2. The adjusted power priority Pt i for:

Images