Power grid system optimization scheduling method and system based on big data and cloud computing

Abstract

The invention belongs to the technical field of big data, and discloses a power grid system optimization scheduling method and system based on big data and cloud computing, and the technology comprises the steps: collecting mass data; processing by a cloud computing platform; revealing operation rules and problems; an optimal scheduling scheme is automatically generated; the operation cost is reduced and the energy utilization efficiency is improved. By analyzing and mining the data, the operation rule and potential problems of the power grid system are disclosed, and data support is provided for optimizing the scheduling strategy. Based on a data analysis result, the system can automatically generate an optimal scheduling scheme, and efficient and economical operation of a power grid system is realized. According to the optimal scheduling method, the operation cost of a power grid system can be reduced, and the energy utilization efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data, and in particular relates to a method and system for optimizing and dispatching a power grid system based on big data and cloud computing. Background Art

[0002] As the scale of power systems continues to expand and become more complex, the amount of data required for grid operation control and safe production is growing rapidly. These data not only come from traditional basic control data and grid operation data, but also include monitoring data, status data, operating data, new energy resource data, and natural environment change data of primary and secondary equipment.

[0003] As the scale and complexity of power systems increase, the amount of data involved in power grid operation control and safe production is indeed growing rapidly. These data come from a wide range of sources, including basic control data, power grid operation data, equipment monitoring data, etc. However, there are some problems in the existing technology when processing these data, as follows:

[0004] 1. Data sharing is difficult:

[0005] Grid data is currently scattered across multiple independent systems, which makes data sharing difficult. The data barriers between various systems make comprehensive analysis and centralized management complex and inefficient.

[0006] 2. Lack of centralized management and comprehensive analysis:

[0007] Due to the scattered data and the lack of a centralized management platform for comprehensive analysis, this limits the grid operator's ability to fully understand the overall status of the grid and optimize decision-making.

[0008] 3. Unable to automatically generate optimized scheduling solutions:

[0009] The existing system cannot automatically generate optimized dispatching plans based on real-time data, which reduces the flexibility and efficiency of power grid dispatching and makes it difficult for the power grid to achieve efficient and economical operation.

[0010] 4. High operating costs:

[0011] Due to the lack of intelligent dispatching and management systems, the operating costs of the power grid are relatively high, which includes not only direct operating costs, but also indirect costs caused by inefficiency.

[0012] 5. Low energy efficiency:

[0013] In the absence of an intelligent scheduling system, the distribution and utilization of energy is not optimal, resulting in inefficient energy utilization, which not only wastes resources but also increases operating costs.

[0014] In summary, the existing technology has obvious deficiencies in power grid data management and dispatching. In order to solve these problems, it is necessary to establish a centralized data management platform to achieve data sharing and comprehensive analysis, and combine intelligent algorithms to automatically generate optimized dispatching plans to improve the operation efficiency and energy utilization efficiency of the power grid. Summary of the invention

[0015] In view of the problems existing in the prior art, the present invention provides a method for optimizing and dispatching a power grid system based on big data and cloud computing.

[0016] The present invention is implemented as follows: a method for optimizing the dispatching of a power grid system based on big data and cloud computing, the technology comprising:

[0017] a) Massive data collection: Collect grid operation data, user power consumption data, meteorological data, etc. from multiple sources such as the grid SCADA system, smart meters, and weather stations;

[0018] b) Cloud computing platform processing: Upload the collected massive data to the cloud computing platform and use parallel computing technology to clean, integrate and feature engineer the data;

[0019] c) Revealing operation rules and problems: Based on the cloud computing platform, statistical analysis, machine learning, deep learning and other methods are used to analyze the processed data, explore the operation rules of the power grid, and diagnose potential problems;

[0020] d) Automatically generate optimized scheduling plans: Based on the analysis results, establish an optimization model, use linear programming, mixed integer programming, heuristic algorithms and other solving methods to automatically generate optimized scheduling plans that meet the requirements of economy, safety and environmental protection;

[0021] e) Reduce operating costs and improve energy efficiency: The generated optimized dispatching plan will be sent to the power grid dispatching and control center for execution, and the power grid operation will be monitored in real time. The dispatching plan will be dynamically adjusted according to the actual situation to reduce the power grid operation cost and improve energy efficiency.

[0022] The data analysis methods used in step c) include but are not limited to one or more of the following:

[0023] Load forecasting: using historical load data, meteorological data, etc., using time series analysis, neural network and other methods to predict load demand in the future;

[0024] Power generation forecast: Using meteorological data, power generation equipment parameters, etc., using machine learning, deep learning and other methods to predict the output of renewable energy power generation;

[0025] Equipment status assessment: Utilize equipment operation data, historical failure data, etc., and adopt machine learning, statistical analysis and other methods to assess equipment health status and predict failure risks.

[0026] Furthermore, the data sources in S1 specifically include:

[0027] Smart meter: collects data such as user electricity consumption and electricity consumption time periods.

[0028] Sensors: monitor parameters such as voltage, current, power, frequency, and temperature in the power grid.

[0029] Monitoring equipment: records the operating status of substations, transmission lines and power generation equipment.

[0030] External data: including weather data, electricity market price data, etc.;

[0031] The S1 also includes utilizing the Internet of Things (IoT) technology to transmit the collected data to a cloud computing platform via a wireless communication network (such as WiFi, LoRa, NBIoT).

[0032] Further, the S2 specifically includes:

[0033] Data Lake: Use distributed storage systems (such as Hadoop HDFS) to create a data lake to store raw data and processed data;

[0034] Database management system: Use NoSQL databases (such as Cassandra) or SQL databases (such as MySQL) to manage structured and semi-structured data;

[0035] Data cleaning: remove noise and outliers from data to ensure data accuracy;

[0036] Data integration: Integrate and standardize data from different sources to form a unified data format;

[0037] Data preprocessing: Perform preprocessing operations such as data normalization and smoothing to facilitate subsequent analysis and mining.

[0038] Further, the S3 specifically includes:

[0039] Statistical analysis: Use statistical methods to conduct basic analysis of data and calculate indicators such as mean, variance, and correlation coefficient;

[0040] Time series analysis: Use time series models (such as ARIMA) to analyze the changing trends and seasonal patterns of power load;

[0041] Pattern recognition: using machine learning algorithms (such as Kmeans clustering and principal component analysis PCA) to identify typical patterns and abnormal conditions in power grid operation;

[0042] Association rule mining: Use association rule algorithms (such as Apriori) to mine the associations in power grid operation, such as the association between high load and a specific time period;

[0043] Predictive analytics: Use regression analysis and deep learning models (such as LSTM) to predict future electricity demand and load peaks.

[0044] Further, the S4 specifically includes:

[0045] S41: Optimization model construction;

[0046] S42: optimization algorithm;

[0047] S43: Solution generation and evaluation.

[0048] Further, the S41 specifically includes:

[0049] Objective function: defines the optimization goal, such as minimizing power loss, minimizing operating costs, maximizing renewable energy utilization, etc.

[0050] Constraints: Set constraints for grid operation, such as power supply and demand balance, equipment capacity limitations, transmission line carrying capacity, etc.

[0051] The S42 specifically includes:

[0052] Genetic Algorithm (GA): Use genetic algorithm for global optimization and solve scheduling solutions;

[0053] Particle Swarm Optimization (PSO): Particle swarm optimization algorithm is used to accelerate the solution process and improve optimization efficiency;

[0054] Hybrid optimization algorithm: Combining multiple optimization algorithms (such as GA+PSO) to further improve the optimization effect;

[0055] The S43 specifically includes:

[0056] Automatic generation: Automatically generate an optimized scheduling plan based on the calculation results of the optimization algorithm;

[0057] Evaluation and verification: Simulate and evaluate the generated scheduling plan to ensure its feasibility and effectiveness.

[0058] Further, the S5 specifically includes:

[0059] Implementation:

[0060] Dispatching system integration: Integrate the optimized dispatching scheme into the power grid dispatching system and automatically execute the dispatching strategy;

[0061] Real-time adjustment: Adjust the dispatch strategy based on real-time data and dynamic changes to ensure efficient operation of the power grid;

[0062] Effect monitoring and feedback:

[0063] Real-time monitoring: Real-time monitoring of the grid operation status and dispatching effect through the monitoring system;

[0064] Feedback adjustment: Based on monitoring data and feedback information, the dispatch strategy is continuously adjusted and optimized to improve energy efficiency and reduce operating costs.

[0065] Another object of the present invention is to provide a power grid system optimization dispatching system based on big data and cloud computing for implementing the power grid system optimization dispatching method based on big data and cloud computing, the system comprising:

[0066] The data acquisition and storage module collects the operating data of various parts of the power grid through smart meters, sensors and monitoring equipment, including load data, power generation data, transmission data, etc.; uses the cloud computing platform for data storage and management to ensure data security and accessibility;

[0067] The data analysis and mining module uses big data analysis technologies (such as Hadoop and Spark) to process and analyze the collected data to reveal the laws and trends of power grid operation; it uses machine learning algorithms (such as cluster analysis and regression analysis) to conduct data mining to identify potential problems and optimization opportunities in power grid operation;

[0068] The optimization scheduling strategy generation module builds a power grid scheduling optimization model based on data analysis results, taking into account various constraints (such as power demand, power supply capacity, and transmission loss); uses optimization algorithms (such as genetic algorithms and particle swarm optimization) to solve the scheduling optimization model and generate the optimal scheduling plan;

[0069] The dispatch execution and feedback module applies the generated optimized dispatch plan to the power grid dispatch system to dynamically adjust the power generation, transmission and distribution strategies; monitors the execution effect of the dispatch plan in real time, collects feedback data, and further optimizes the dispatch strategy;

[0070] The visualization and reporting module provides an intuitive visualization interface to display the grid operation status, dispatching scheme and optimization effect; it generates detailed dispatching reports to provide data support and optimization suggestions for decision makers.

[0071] Another object of the present invention is to provide a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the power grid system optimization and scheduling method based on big data and cloud computing.

[0072] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the power grid system optimization and scheduling method based on big data and cloud computing.

[0073] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0074] First, the present invention proposes a method for optimizing the dispatching of a power grid system based on big data and cloud computing. This technology can optimize the dispatching strategy of the power grid and realize efficient and economical operation of the power grid by analyzing and mining massive power grid data. By collecting massive data of the power grid system, the cloud computing platform is used for data storage and processing. By analyzing and mining the data, the operating laws and potential problems of the power grid system are revealed, providing data support for optimizing the dispatching strategy. Based on the data analysis results, the system can automatically generate an optimized dispatching plan to realize efficient and economical operation of the power grid system. The optimization dispatching method of the present invention can reduce the operating cost of the power grid system and improve energy utilization efficiency.

[0075] Second, traditional grid dispatching methods mainly rely on manual experience and limited real-time data, which is difficult to cope with the complexity and uncertainty of large-scale power grids. This leads to problems such as delayed dispatching decisions, unreasonable resource allocation, and low energy efficiency, making it difficult to meet the higher requirements of modern power grids for safe, economical, and environmentally friendly operation.

[0076] The present invention introduces big data technology to collect massive real-time data from all aspects of the power grid, providing a comprehensive and accurate information basis for power grid dispatching. The powerful computing power of the cloud computing platform is used to efficiently process and analyze massive data, explore the operation rules of the power grid, and provide a scientific basis for optimizing dispatching.

[0077] The present invention uses advanced machine learning, deep learning and other algorithms to build accurate load forecasting, power generation forecasting, equipment status assessment and other models to achieve comprehensive perception and prediction of the power grid operation status. Based on these models, the power grid operation trend can be predicted in advance, providing strong support for scheduling decisions.

[0078] The present invention automatically generates a scheduling scheme that meets multiple objective constraints by establishing an optimization scheduling model and combining multiple optimization methods such as linear programming, mixed integer programming, and heuristic algorithms. This intelligent scheduling method can minimize operating costs, improve energy utilization efficiency, and achieve economical and environmentally friendly operation of the power grid while ensuring safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 It is a flow chart of a method for optimizing and dispatching a power grid system based on big data and cloud computing provided in an embodiment of the present invention.

[0080] Figure 2 is a flow chart of a method for automatically generating an optimized scheduling solution provided by an embodiment of the present invention;

[0081] Figure 3 It is a schematic diagram of the structure of a power grid system optimization and dispatching system based on big data and cloud computing provided by an embodiment of the present invention;

[0082] Figure 4 is the expected processing time variance provided by the embodiment of the present invention;

[0083] Figure 5 is the load balancing degree provided by the embodiment of the present invention;

[0084] Figure 6 Comparison of scheduling method costs over time;

[0085] Figure 7 Comparison of energy efficiency of scheduling methods. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0087] like Figure 1 As shown, an embodiment of the present invention provides a method for optimizing and dispatching a power grid system based on big data and cloud computing, and the technology includes:

[0088] S1: Massive data collection;

[0089] S2: cloud computing platform processing;

[0090] S3: Revealing operation rules and problems;

[0091] S4: Automatically generate optimized scheduling solutions;

[0092] S5: Reduce operating costs and improve energy efficiency.

[0093] The following is the working principle of the power grid system optimization dispatching method based on big data and cloud computing, which is elaborated in detail in combination with algorithms and models:

[0094] Massive data collection (S1):

[0095] Data source:

[0096] Power grid SCADA system: real-time collection of voltage, current, power and other operating data in each link of power generation, transmission, transformation and distribution.

[0097] Smart meter: collects data such as user electricity consumption and load curve.

[0098] Meteorological data: Obtain data on wind speed, light, temperature, etc. that affect renewable energy power generation.

[0099] Geographic Information System (GIS): Obtain information such as power grid topology and equipment location.

[0100] Data storage: Store massive data in distributed file systems (such as HDFS) or NoSQL databases (such as MongoDB) to ensure data reliability and scalability.

[0101] Cloud computing platform processing (S2):

[0102] Data cleaning: remove outliers, fill in missing values, and ensure data quality.

[0103] Data integration: Unify and integrate data from different sources and formats.

[0104] Feature engineering: Extract key features related to grid operation, such as load forecast, power generation forecast, equipment status, etc.

[0105] Parallel computing: Utilize the elastic computing resources of the cloud computing platform to process massive amounts of data in parallel and improve computing efficiency.

[0106] Revealing operating rules and problems (S3):

[0107] Data analysis: Use statistical analysis, machine learning, deep learning and other methods to analyze historical data and real-time data to explore the operation rules of the power grid, such as load patterns and fault characteristics.

[0108] Problem diagnosis: Based on data analysis results, identify potential problems in power grid operation, such as overload, voltage limit exceeding, and excessive line loss.

[0109] Visual display: The analysis results are displayed intuitively in the form of charts, curves, etc., making it easier for decision makers to understand the operating status of the power grid.

[0110] Automatically generate optimized scheduling plan (S4):

[0111] Optimization goal:

[0112] Economic dispatch: minimizing power generation costs, power purchase costs, network losses, etc.

[0113] Safe dispatch: Ensure safe and stable operation of the power grid to avoid problems such as overload and voltage exceeding the limit.

[0114] Environmental protection scheduling: improve the utilization rate of new energy and reduce pollutant emissions.

[0115] Optimizing the model:

[0116] Optimal Power Flow (OPF): Solve the optimal power generation plan and transmission scheme that meets various constraints.

[0117] Unit Output (UC): Determines the start and stop status of the unit to meet the system load requirements.

[0118] Economic dispatch (ED): Minimize the cost of power generation while satisfying constraints.

[0119] Solving algorithm:

[0120] Linear programming: Applicable to linear optimization problems such as ED.

[0121] Mixed integer programming: Applicable to optimization problems involving discrete variables, such as UC.

[0122] Heuristic algorithms: such as genetic algorithms, particle swarm algorithms, etc., are suitable for large-scale, nonlinear optimization problems, such as OPF.

[0123] Reduce operating costs and improve energy efficiency (S5):

[0124] Implementation of optimized dispatching plan: The generated optimized dispatching plan will be sent to various power plants, substations, etc. for execution.

[0125] Real-time monitoring and adjustment: Monitor the operation of the power grid in real time and dynamically adjust the dispatch plan based on actual conditions.

[0126] Effect evaluation: Evaluate the effect of the implementation of the optimized scheduling plan, analyze the cost savings, improved energy efficiency, etc.

[0127] Specific implementation cases

[0128] Taking a provincial power grid as an example, cloud computing platform and big data technology are used to optimize dispatch:

[0129] Data collection: Massive data is collected from SCADA systems, smart meters, weather stations, etc. and stored in AWS S3.

[0130] Data processing: Use AWS EMR (a cloud computing platform based on Hadoop) to clean, integrate and feature engineer data.

[0131] Data analysis: Use the Spark MLlib machine learning library to analyze data for load forecasting, power generation forecasting, equipment status assessment, etc.

[0132] Optimized scheduling:

[0133] Economic dispatch: Use the CPLEX solver to solve the mixed integer programming model and determine the unit start and stop plan.

[0134] Optimal power flow: Use the IPOPT solver to solve nonlinear optimization models and determine power generation output and transmission plans.

[0135] Plan implementation and evaluation: The optimized dispatch plan will be sent to the dispatch control center to monitor the operation of the power grid in real time and evaluate the optimization effect.

[0136] Through this technology, the provincial power grid has achieved an average annual savings of 5% in power generation costs and an 8% reduction in carbon emissions, significantly improving the economy and environmental performance of power grid operations.

[0137] First, data collection and storage

[0138] 1. Data Collection:

[0139] Use data scraping tools (such as Apache Flume, Logstash, etc.) to scrape data from SCADA systems, smart meters, meteorological data interfaces, and GIS systems in real time.

[0140] The data should contain key fields such as timestamp, device ID, voltage, current, power, electricity consumption, meteorological information (wind speed, light, temperature) and device location.

[0141] 2. Data storage:

[0142] Use AWS SDK to upload data to AWS S3 bucket to ensure data persistence and scalability.

[0143] Data should be partitioned by date and type to facilitate subsequent data processing and analysis.

[0144] 2. Data Processing and Analysis

[0145] 1. Data cleaning and integration:

[0146] Create a Hadoop cluster using AWS EMR (Elastic MapReduce).

[0147] Write MapReduce jobs or Spark jobs to process the data in S3, remove outliers, fill missing values, and integrate data from different sources into a unified dataset.

[0148] 2. Feature Engineering:

[0149] Extract features related to grid operation, such as average daily power consumption, peak load, and renewable energy power generation.

[0150] Use Spark SQL or Hive to transform data and calculate features.

[0151] 3. Data Analysis:

[0152] Spark MLlib can be used for load forecasting and power generation forecasting, using machine learning algorithms such as random forest and gradient boosting tree.

[0153] Evaluate equipment status and identify potential failures.

[0154] Third, optimization scheduling model and algorithm implementation

[0155] 1. Economic dispatch model:

[0156] A mixed integer programming (MIP) model is defined, and the goal is to minimize the power generation cost.

[0157] Constraints include unit output limitation, load demand satisfaction, unit start and stop time, etc.

[0158] Use IBM's CPLEX optimizer or Gurobi to solve the MIP model and obtain the start and stop plan and output distribution of the unit.

[0159] 2. Optimal power flow model:

[0160] A nonlinear optimization model is established with the goal of optimizing the power flow in the power grid to reduce network losses and improve voltage stability.

[0161] Constraints include node voltage limits, line capacity limits, etc.

[0162] Solve the model using IPOPT or another nonlinear optimization solver.

[0163] Fourth, optimize the generation and implementation of scheduling plans

[0164] 1. Solution generation:

[0165] Based on the calculation results of economic dispatch and optimal power flow, specific dispatch instructions are generated, including the start and stop and output plan of each generating unit.

[0166] Taking into account the access of new energy and real-time changes in load, dynamically adjust the scheduling plan.

[0167] 2. Implementation of the program:

[0168] The dispatch instructions are sent to the dispatch control center, which is responsible for their specific implementation.

[0169] Monitor the operation status of the power grid in real time to ensure the correct execution of dispatch instructions.

[0170] 3. Effect evaluation and feedback:

[0171] Collect grid operation data after implementation and compare cost, emission and other indicators before and after optimization.

[0172] Make feedback adjustments based on the implementation results and continuously optimize the scheduling model and algorithm parameters.

[0173] Fifth, technical support and security

[0174] Ensure the stability and security of cloud computing platforms and big data processing environments.

[0175] Back up data and models regularly to prevent data loss or model corruption.

[0176] Establish a technical support team to monitor the system's operating status and resolve any problems that arise in a timely manner.

[0177] Through the above specific implementation plan, we can fully utilize the advantages of big data and cloud computing technology to achieve optimized scheduling of the power grid system and improve the economy, safety and environmental protection of power grid operation.

[0178] The data sources in S1 specifically include:

[0179] Smart meter: collects data such as user electricity consumption and electricity consumption time periods.

[0180] Sensors: monitor parameters such as voltage, current, power, frequency, and temperature in the power grid.

[0181] Monitoring equipment: records the operating status of substations, transmission lines and power generation equipment.

[0182] External data: including weather data, electricity market price data, etc.;

[0183] The S1 also includes utilizing the Internet of Things (IoT) technology to transmit the collected data to a cloud computing platform via a wireless communication network (such as WiFi, LoRa, NBIoT).

[0184] The S2 specifically includes:

[0185] Data Lake: Use distributed storage systems (such as Hadoop HDFS) to create a data lake to store raw data and processed data;

[0186] Database management system: Use NoSQL databases (such as Cassandra) or SQL databases (such as MySQL) to manage structured and semi-structured data;

[0187] Data cleaning: remove noise and outliers from data to ensure data accuracy;

[0188] Data integration: Integrate and standardize data from different sources to form a unified data format;

[0189] Data preprocessing: Perform preprocessing operations such as data normalization and smoothing to facilitate subsequent analysis and mining.

[0190] The S3 specifically includes:

[0191] Statistical analysis: Use statistical methods to conduct basic analysis of data and calculate indicators such as mean, variance, and correlation coefficient;

[0192] Time series analysis: Use time series models (such as ARIMA) to analyze the changing trends and seasonal patterns of power load;

[0193] Pattern recognition: using machine learning algorithms (such as Kmeans clustering and principal component analysis PCA) to identify typical patterns and abnormal conditions in power grid operation;

[0194] Association rule mining: Use association rule algorithms (such as Apriori) to mine the associations in power grid operation, such as the association between high load and a specific time period;

[0195] Predictive analytics: Use regression analysis and deep learning models (such as LSTM) to predict future electricity demand and load peaks.

[0196] like Figure 2 As shown, the S4 specifically includes:

[0197] S41: Optimization model construction;

[0198] S42: optimization algorithm;

[0199] S43: Solution generation and evaluation.

[0200] The S41 specifically includes:

[0201] Objective function: defines the optimization goal, such as minimizing power loss, minimizing operating costs, maximizing renewable energy utilization, etc.

[0202] Constraints: Set constraints for grid operation, such as power supply and demand balance, equipment capacity limitations, transmission line carrying capacity, etc.

[0203] The S42 specifically includes:

[0204] Genetic Algorithm (GA): Use genetic algorithm for global optimization and solve scheduling solutions;

[0205] Particle Swarm Optimization (PSO): Particle swarm optimization algorithm is used to accelerate the solution process and improve optimization efficiency;

[0206] Hybrid optimization algorithm: Combining multiple optimization algorithms (such as GA+PSO) to further improve the optimization effect;

[0207] The S43 specifically includes:

[0208] Automatic generation: Automatically generate an optimized scheduling plan based on the calculation results of the optimization algorithm;

[0209] Evaluation and verification: Simulate and evaluate the generated scheduling plan to ensure its feasibility and effectiveness.

[0210] The S5 specifically includes:

[0211] Implementation:

[0212] Dispatching system integration: Integrate the optimized dispatching scheme into the power grid dispatching system and automatically execute the dispatching strategy;

[0213] Real-time adjustment: Adjust the dispatch strategy based on real-time data and dynamic changes to ensure efficient operation of the power grid;

[0214] Effect monitoring and feedback:

[0215] Real-time monitoring: Real-time monitoring of the grid operation status and dispatching effect through the monitoring system;

[0216] Feedback adjustment: Based on monitoring data and feedback information, the dispatch strategy is continuously adjusted and optimized to improve energy efficiency and reduce operating costs.

[0217] like Figure 3 As shown, an embodiment of the present invention provides a power grid system optimization dispatching system based on big data and cloud computing for implementing the power grid system optimization dispatching method based on big data and cloud computing, the system comprising:

[0218] The data acquisition and storage module collects the operating data of various parts of the power grid through smart meters, sensors and monitoring equipment, including load data, power generation data, transmission data, etc.; uses the cloud computing platform for data storage and management to ensure data security and accessibility;

[0219] The data analysis and mining module uses big data analysis technologies (such as Hadoop and Spark) to process and analyze the collected data to reveal the laws and trends of power grid operation; it uses machine learning algorithms (such as cluster analysis and regression analysis) to conduct data mining to identify potential problems and optimization opportunities in power grid operation;

[0220] The optimization scheduling strategy generation module builds a power grid scheduling optimization model based on data analysis results, taking into account various constraints (such as power demand, power supply capacity, and transmission loss); uses optimization algorithms (such as genetic algorithms and particle swarm optimization) to solve the scheduling optimization model and generate the optimal scheduling plan;

[0221] The dispatch execution and feedback module applies the generated optimized dispatch plan to the power grid dispatch system to dynamically adjust the power generation, transmission and distribution strategies; monitors the execution effect of the dispatch plan in real time, collects feedback data, and further optimizes the dispatch strategy;

[0222] The visualization and reporting module provides an intuitive visualization interface to display the grid operation status, dispatching scheme and optimization effect; it generates detailed dispatching reports to provide data support and optimization suggestions for decision makers.

[0223] An embodiment of the present invention provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the power grid system optimization and scheduling method based on big data and cloud computing.

[0224] An embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the power grid system optimization and scheduling method based on big data and cloud computing.

[0225] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. A person of ordinary skill in the art will appreciate that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVDROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0226] The embodiments of the present invention have achieved some positive effects during the development or use process, and indeed have great advantages over the prior art. The following content is described in conjunction with data, charts, etc. of the test process.

[0227] The present invention uses the commonly used virtual machine expected processing time variance to measure the load balancing of the cloud computing cluster. 30 virtual machines and 350 computationally intensive subtasks are randomly selected, and the total length of the tasks assigned to the virtual machines is recorded as L j , the average expected processing time of all virtual machines is Then the expected processing time variance of the virtual machine is

[0228]

[0229] Obviously, the smaller the system variance value, the better the system load balancing. The experimental results obtained according to the above formula are as follows: Figure 4 , 5 shown.

[0230] from Figure 4 It can be seen from the figure that with the increase of the number of tasks, the HIPLTS algorithm, the HNDP algorithm and the HEFT algorithm all have obvious load imbalance. After the algorithm of the present invention introduces the load balancing degree, the algorithm shows good load balancing, and the δ value is smaller than that of the other three algorithms. Figure 5 It can be seen that the experimental results are consistent with Figure 4 The results are consistent with those of the other three algorithms. The load balancing LB value of the LSIPLB algorithm is smaller than that of the other three algorithms from the beginning, and as the number of tasks increases, the LB value tends to be stable. The experimental results show that the LSIPLB algorithm has good load balancing characteristics and is suitable for task scheduling in current large-scale cloud computing clusters.

[0231] The two line graphs intuitively demonstrate the advantages of the present invention over the prior art in terms of cost and energy efficiency:

[0232] Figure 6 The cost of the dispatching method changes over time. The cost of the traditional dispatching method has increased slightly over time, while the cost of the optimized dispatching method has gradually decreased and has been lower than the cost of the traditional dispatching method in the third year. This shows the advantage of optimized dispatching in reducing the cost of power grid operation.

[0233] Figure 7 The energy efficiency comparison of the dispatching methods is shown in Figure 2. The optimized dispatching method is significantly better than the traditional dispatching method in terms of energy efficiency. Especially in the third year, the energy efficiency of the optimized dispatching method increased to 90%, significantly higher than the 80% of the traditional dispatching method. This shows that the optimized dispatching method can effectively improve energy utilization efficiency and reduce energy waste.

[0234] These charts strongly demonstrate the technical progress of the present invention in optimizing the dispatching of power grid systems, and provide an effective solution for achieving economical and environmentally friendly operation of power grids.

[0235] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for optimizing and dispatching a power grid system based on big data and cloud computing, characterized in that: The method includes: a) Massive data collection: Collect grid operation data, user electricity consumption data, and meteorological data from multiple sources such as the grid SCADA system, smart meters, and weather stations; b) Cloud computing platform processing: Upload the collected massive data to the cloud computing platform and use parallel computing technology to clean, integrate and feature engineer the data; c) Revealing operation rules and problems: Based on the cloud computing platform, statistical analysis, machine learning, and deep learning methods are used to analyze the processed data, explore the operation rules of the power grid, and diagnose potential problems; d) Automatically generate optimized scheduling plans: Based on the analysis results, establish an optimization model, use linear programming, mixed integer programming, and heuristic algorithm solution methods to automatically generate optimized scheduling plans that meet economic, safety, and environmental requirements; e) Reduce operating costs and improve energy efficiency: The generated optimized dispatching plan will be sent to the power grid dispatching and control center for execution, and the power grid operation will be monitored in real time. The dispatching plan will be dynamically adjusted according to the actual situation to reduce the power grid operation cost and improve energy efficiency.

2. The power grid system optimization dispatching method based on big data and cloud computing according to claim 1 is characterized in that: The data analysis methods used in step c) include but are not limited to one or more of the following: Load forecasting: using historical load data and meteorological data, using time series analysis and neural network methods to predict load demand in the future; Power generation forecast: Using meteorological data and power generation equipment parameters, machine learning and deep learning methods are used to predict the output of renewable energy power generation; Equipment status assessment: Utilize equipment operation data and historical failure data, and adopt machine learning and statistical analysis methods to assess equipment health status and predict failure risks.

3. The power grid system optimization dispatching method based on big data and cloud computing according to claim 1 is characterized in that: The data sources in S1 specifically include: Smart meter: collects data on users’ electricity consumption and usage periods. Sensors: monitor voltage, current, power, frequency, and temperature parameters in the power grid. Monitoring equipment: records the operating status of substations, transmission lines and power generation equipment. External data: including weather data and electricity market price data; The S1 also includes utilizing Internet of Things (IoT) technology to transmit the collected data to a cloud computing platform via a wireless communication network.

4. The power grid system optimization dispatching method based on big data and cloud computing according to claim 1 is characterized in that: The S2 specifically includes: Data Lake: Use distributed storage systems (such as Hadoop HDFS) to create a data lake to store raw data and processed data; Database management system: Use NoSQL databases (such as Cassandra) or SQL databases (such as MySQL) to manage structured and semi-structured data; Data cleaning: remove noise and outliers from data to ensure data accuracy; Data integration: Integrate and standardize data from different sources to form a unified data format; Data preprocessing: Perform data normalization and smoothing preprocessing operations to facilitate subsequent analysis and mining.

5. The power grid system optimization dispatching method based on big data and cloud computing according to claim 1 is characterized in that: The S3 specifically includes: Statistical analysis: Use statistical methods to conduct basic analysis of data and calculate mean values, variances, and correlation coefficients; Time series analysis: Use time series models (such as ARIMA) to analyze the changing trends and seasonal patterns of power load; Pattern recognition: using machine learning algorithms (such as Kmeans clustering and principal component analysis PCA) to identify typical patterns and abnormal conditions in power grid operation; Association rule mining: Use association rule algorithms (such as Apriori) to mine the associations in power grid operation, such as the association between high load and a specific time period; Predictive analytics: Use regression analysis and deep learning models (such as LSTM) to predict future electricity demand and load peaks.

6. The method for optimizing and dispatching a power grid system based on big data and cloud computing according to claim 1, characterized in that: The S4 specifically includes: S41: Optimization model construction; S42: optimization algorithm; S43: Solution generation and evaluation.

7. The method for optimizing and dispatching a power grid system based on big data and cloud computing according to claim 1, characterized in that: The S41 specifically includes: Objective function: defines the optimization goal, such as minimizing power loss, minimizing operating costs, and maximizing renewable energy utilization; Constraints: Set constraints for grid operation, such as power supply and demand balance, equipment capacity limitations, and transmission line carrying capacity; The S42 specifically includes: Genetic Algorithm (GA): Use genetic algorithm for global optimization and solve scheduling solutions; Particle Swarm Optimization (PSO): Particle swarm optimization algorithm is used to accelerate the solution process and improve optimization efficiency; Hybrid optimization algorithm: Combining multiple optimization algorithms (such as GA+PSO) to further improve the optimization effect; The S43 specifically includes: Automatic generation: Automatically generate an optimized scheduling plan based on the calculation results of the optimization algorithm; Evaluation and verification: Simulate and evaluate the generated scheduling plan to ensure its feasibility and effectiveness.

8. The method for optimizing and dispatching a power grid system based on big data and cloud computing according to claim 1, characterized in that: The S5 specifically includes: Implementation: Dispatching system integration: Integrate the optimized dispatching scheme into the power grid dispatching system and automatically execute the dispatching strategy; Real-time adjustment: Adjust the dispatch strategy based on real-time data and dynamic changes to ensure efficient operation of the power grid; Effect monitoring and feedback: Real-time monitoring: Real-time monitoring of the grid operation status and dispatching effect through the monitoring system; Feedback adjustment: Based on monitoring data and feedback information, the dispatch strategy is continuously adjusted and optimized to improve energy efficiency and reduce operating costs.

9. A power grid system optimization dispatching system based on big data and cloud computing that implements the power grid system optimization dispatching method based on big data and cloud computing as claimed in any one of claim 18, characterized in that: The system includes: The data acquisition and storage module collects the operation data of various parts of the power grid, including load data, power generation data, and transmission data, through smart meters, sensors, and monitoring equipment; uses cloud computing platforms for data storage and management to ensure data security and accessibility; The data analysis and mining module uses big data analysis technology to process and analyze the collected data to reveal the laws and trends of power grid operation; it uses machine learning algorithms to conduct data mining to identify potential problems and optimization opportunities in power grid operation; The optimization dispatch strategy generation module builds a power grid dispatch optimization model based on data analysis results, taking into account various constraints; it uses optimization algorithms to solve the dispatch optimization model and generate the optimal dispatch plan; The dispatch execution and feedback module applies the generated optimized dispatch plan to the power grid dispatch system to dynamically adjust the power generation, transmission and distribution strategies; monitors the execution effect of the dispatch plan in real time, collects feedback data, and further optimizes the dispatch strategy; The visualization and reporting module provides an intuitive visualization interface to display the grid operation status, dispatching scheme and optimization effect; it generates detailed dispatching reports to provide data support and optimization suggestions for decision makers.

10. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the power grid system optimization and scheduling method based on big data and cloud computing as claimed in any one of claim 17.

Images