Cross-regional energy supply and demand big data intelligent matching system

Abstract

The invention relates to the technical field of energy supply and demand matching analysis, in particular to a cross-regional energy supply and demand big data intelligent matching system, which comprises the following modules: a data acquisition module which is responsible for collecting energy supply data and demand data of each region; the data processing module is used for cleaning, integrating and analyzing the collected data, and predicting future energy supply and demand conditions of each region by utilizing a machine learning algorithm; the intelligent matching module is used for intelligently matching an optimal energy supply and demand scheme according to an analysis result of the data processing module; the scheduling instruction module is used for sending a scheduling instruction to the energy management center of each region to realize cross-region allocation of energy; and the feedback adjustment module is used for collecting feedback information, adjusting algorithm parameters and optimizing a matching scheme according to an actual allocation effect. According to the invention, the optimization of energy distribution is ensured, and the loss and cost in the energy transmission process are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of energy supply and demand matching analysis, and in particular to a cross-regional energy supply and demand big data intelligent matching system. Background Art

[0002] In the current energy management field, especially considering the rapid growth of renewable energy and the gradual liberalization of the electricity market, there is an urgent need for efficient and intelligent energy allocation solutions. Traditional energy management systems are often faced with information silos, inefficient data processing, and inability to respond to complex supply and demand changes in real time. These challenges exacerbate energy waste, limit the full utilization of renewable energy, and increase the instability and insecurity of energy supply.

[0003] The development of big data and machine learning technologies has brought new solutions to the field of energy management. These technologies can process and analyze large amounts of dispersed energy data, provide accurate energy supply and demand forecasts, and implement intelligent energy allocation strategies. However, effectively integrating and applying these technologies to cross-regional energy allocation to improve energy efficiency, reduce environmental impact, and ensure the stability and security of energy supply remains a technical challenge to be solved.

[0004] In addition, in order to meet the real-time and safety requirements in the energy allocation process, it is necessary to develop an efficient scheduling instruction transmission mechanism and adopt adaptive adjustment strategies to cope with the constant changes in energy market and environmental conditions. Summary of the invention

[0005] Based on the above objectives, the present invention provides a cross-regional energy supply and demand big data intelligent matching system.

[0006] The technical solution of the present invention is: a cross-regional energy supply and demand big data intelligent matching system, comprising: Data collection module: responsible for collecting energy supply and demand data in various regions, including wind power, solar power generation data and energy demand data of various users; Data processing module: cleans, integrates and analyzes the collected data, and uses machine learning algorithms to predict the future energy supply and demand conditions in each region; Intelligent matching module: According to the analysis results of the data processing module, intelligently match the optimal energy supply and demand plan to ensure efficient use of energy and balance between regions; Dispatching instruction module: Sends dispatching instructions to the energy management center in each region to achieve cross-regional allocation of energy; Feedback adjustment module: used to collect feedback information for data processing and calculation analysis based on the actual deployment effect, and dynamically optimize the implementation of the existing intelligent matching plan based on the analysis results; including: obtaining each dispatch instruction issued and receiving the execution feedback corresponding to the dispatch instruction; The single dispatching effect between the execution feedback and the dispatching instruction is digitally processed and calculated to obtain the corresponding single dispatching state degree and single dispatching state; Obtain all single dispatch abnormal states and single dispatch normal states corresponding to all dispatch instructions, and perform data processing and calculation of the overall dispatch reliability state on all acquired single dispatch abnormal states and single dispatch normal states to obtain the corresponding overall dispatch reliability; Perform data analysis on the overall dispatch reliability to obtain the corresponding overall dispatch reliability state or overall dispatch unreliable state; Maintain the subsequent implementation of the existing intelligent matching solution based on the overall scheduling reliability status obtained through analysis; Furthermore, the subsequent implementation of the existing intelligent matching solution is dynamically optimized and adjusted based on the overall scheduling unreliability status obtained through analysis.

[0007] Furthermore, the data acquisition module specifically includes: Adopt multi-source data collection technology, including weather station data, real-time energy production data and user-side energy consumption data; Use wireless sensor networks and IoT technologies to monitor widely distributed energy resources in real time; Data collection includes time series data, geographic location information, and equipment status information, which are encoded in a standardized data format for subsequent processing.

[0008] Furthermore, the encoding using a standardized data format specifically includes: Define a unified data model that covers all data types that need to be collected, including meteorological data, energy production and consumption data, and various data timestamps, geographic locations, device IDs, and data values; Select a common data exchange format as the basis for data encoding; Use MQTT or CoAP standardized protocols for data collection and transmission; Provide detailed labels and metadata for each data point to accurately understand and utilize the data in subsequent data processing and analysis.

[0009] Furthermore, the data processing module specifically includes: Ensure data quality using data cleaning techniques, including outlier handling, missing value filling, and data standardization; Use big data technology stack for data storage and computing; Use cluster analysis to predict future energy supply and demand trends and assist in scheduling decisions.

[0010] Furthermore, the cluster analysis uses a K-means clustering algorithm to divide the data into a predefined number of clusters, specifically including: Use Apache Spark's MLlib library to implement the K-means algorithm and Python's Scikit-learn library to perform DBSCAN clustering; When a clustering hierarchy is needed rather than a flat clustering partition, a hierarchical clustering algorithm is used, based on AgglomerativeClustering in the Scikit-learn library for hierarchical clustering.

[0011] Furthermore, the intelligent matching module includes using particle swarm optimization (PSO) to search for an optimal or approximately optimal energy allocation solution based on energy supply and demand forecast results.

[0012] Furthermore, the particle swarm optimization PSO specifically includes: Define the objective function to evaluate the effect of the energy allocation scheme, including minimizing the energy transmission cost and loss, while considering meeting regional demand and maximizing the utilization of renewable energy. Each particle represents an energy allocation scheme, including the energy dispatch amount of each region. Set the parameters of PSO, including the group size, the maximum number of iterations, the learning factor, and the maximum speed and position range of the particles. A set of particles are randomly initialized in the solution space. The position of each particle corresponds to an energy allocation scheme, and the speed determines its search direction and step size. Calculate the objective function value of each particle to evaluate the quality of the solution it represents. For each particle, if the current position is better than the previous individual optimal position, update its individual optimal position. At the same time, select the best position from all particles as the global optimal position. Update the speed and position of each particle according to the individual optimum and the global optimum. The speed update takes into account the current speed of the particle, the difference between the individual optimal position and the current position, and the difference between the global optimal position and the current position. The process of evaluating, updating individual optimal and global optimal, updating speed and position is repeated until the maximum number of iterations or other stopping conditions are reached. After the iteration ends, the global optimal position represents the optimal energy allocation solution found.

[0013] Furthermore, the dispatch instruction module generates detailed dispatch instructions based on the data provided by the intelligent matching module, and each instruction contains information on the target area, energy type, dispatch amount, scheduled time and expected effect.

[0014] Furthermore, the step of digitally processing and calculating a single scheduling effect between the execution feedback and the scheduling instruction includes: Match the execution effect in a single scheduling effect with the expected effect of the scheduling instruction; If the execution effect is consistent with the expected effect, the single dispatch state degree corresponding to the dispatch instruction is set to 0, and the corresponding single dispatch state is marked as a single dispatch normal state; If the execution effect is inconsistent with the expected effect, the single scheduling state degree corresponding to the scheduling instruction is set to 1, and the corresponding single scheduling state is marked as a single scheduling abnormal state.

[0015] Furthermore, the steps of processing and obtaining the overall dispatch reliability include: All the acquired single dispatch abnormal states and single dispatch normal states are calculated by the formula Calculate and obtain the overall dispatch reliability ZK; where NY and NZ are the total number of all single dispatch abnormal states and the total number of all single dispatch normal states, respectively; A is the overall dispatch reliability standard value.

[0016] Beneficial effects of the present invention: The present invention uses big data technology stack and cluster analysis to process and analyze a large amount of energy supply and demand data in real time, predict future energy demand, and thus achieve rapid response and efficient matching. The particle swarm optimization (PSO) algorithm further optimizes the energy allocation scheme, ensures the optimization of energy distribution, and reduces the loss and cost in the energy transmission process.

[0017] The dispatch instruction module of the present invention adopts a secure communication protocol, such as TLS / SSL, to ensure the encrypted transmission and identity authentication of the dispatch instructions, thereby ensuring the security and reliability of energy allocation. In addition, it can adjust the dispatch strategy according to real-time data and feedback, flexibly respond to emergencies and changes, and enhance the stability of energy supply and the robustness of the system.

[0018] The present invention intelligently matches the supply and demand of renewable energy, optimizes the utilization efficiency of renewable energy, reduces dependence on fossil fuels, helps reduce greenhouse gas emissions and environmental pollution, and promotes sustainable development of energy and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1Schematic diagram of system function modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0022] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0023] like Figure 1 As shown, the cross-regional energy supply and demand big data intelligent matching system includes: Data collection module: responsible for collecting energy supply and demand data in various regions, including wind power, solar power generation data and energy demand data of various users; Data processing module: cleans, integrates and analyzes the collected data, and uses machine learning algorithms to predict the future energy supply and demand conditions in each region; Intelligent matching module: According to the analysis results of the data processing module, intelligently match the optimal energy supply and demand plan to ensure efficient use of energy and balance between regions; Dispatching instruction module: Sends dispatching instructions to the energy management center in each region to achieve cross-regional allocation of energy; The data acquisition module specifically includes: Adopt multi-source data collection technology, including weather station data, real-time energy production data and user-side energy consumption data; Use wireless sensor networks and IoT technologies to monitor widely distributed energy resources in real time; Data collection includes time series data, geographic location information, and equipment status information, which are encoded in a standardized data format for subsequent processing.

[0024] The use of standardized data formats for encoding specifically includes: Define a unified data model that covers all data types that need to be collected, including meteorological data, energy production and consumption data, and various data timestamps, geographic locations, device IDs, and data values; Select a common data exchange format as the basis for data encoding; Use MQTT or CoAP standardized protocols for data collection and transmission; Provide detailed labels and metadata for each data point to accurately understand and utilize the data in subsequent data processing and analysis.

[0025] The data processing module specifically includes: Ensure data quality using data cleaning techniques, including outlier handling, missing value filling, and data standardization; Use big data technology stack for data storage and computing; Use cluster analysis to predict future energy supply and demand trends and assist in scheduling decisions.

[0026] The big data technology stack includes: Based on HDFS as the storage layer, it provides high-throughput data access and stores unstructured or semi-structured data based on NoSQL database; Based on the distributed data processing framework, it provides batch processing and real-time data processing capabilities; Based on a distributed stream processing platform, it is used to process real-time data streams.

[0027] Cluster analysis uses the K-means clustering algorithm to divide the data into a predefined number of clusters, including: Use Apache Spark's MLlib library to implement the K-means algorithm and Python's Scikit-learn library to perform DBSCAN clustering; When a clustering hierarchy is needed rather than a flat clustering partition, a hierarchical clustering algorithm is used, based on AgglomerativeClustering in the Scikit-learn library for hierarchical clustering.

[0028] The intelligent matching module uses particle swarm optimization (PSO) to search for the optimal or approximately optimal energy allocation solution based on the energy supply and demand forecast results.

[0029] Particle swarm optimization PSO specifically includes: Define the objective function to evaluate the effect of the energy allocation scheme, including minimizing the energy transmission cost and loss, while considering meeting regional demand and maximizing the utilization of renewable energy. Each particle represents an energy allocation scheme, including the energy dispatch amount of each region. Set the parameters of PSO, including the group size, the maximum number of iterations, the learning factor, and the maximum speed and position range of the particles. A set of particles are randomly initialized in the solution space. The position of each particle corresponds to an energy allocation scheme, and the speed determines its search direction and step size. Calculate the objective function value of each particle to evaluate the quality of the solution it represents. For each particle, if the current position is better than the previous individual optimal position, update its individual optimal position. At the same time, select the best position from all particles as the global optimal position. Update the speed and position of each particle according to the individual optimum and the global optimum. The speed update takes into account the current speed of the particle, the difference between the individual optimal position and the current position, and the difference between the global optimal position and the current position. The process of evaluating, updating individual optimal and global optimal, updating speed and position is repeated until the maximum number of iterations or other stopping conditions are reached. After the iteration ends, the global optimal position represents the optimal energy allocation solution found.

[0030] The dispatch instruction module generates detailed dispatch instructions based on the data provided by the intelligent matching module. Each instruction contains information on the target area, energy type, dispatch quantity, scheduled time and expected effect.

[0031] Receive and execute scheduling instructions: Instruction reception: Each regional energy management center receives and parses the dispatch instructions through the integrated message client. The source and integrity of the instructions need to be verified to ensure that they have not been tampered with.

[0032] Instruction execution: Based on the content of the received instructions, the energy management center adjusts the energy output or distribution strategy, such as starting or adjusting the output of power plants, adjusting the power transmission path of the power grid, etc.

[0033] When executing instructions, you need to consider the current system status and safety constraints to ensure that the operation does not affect system stability.

[0034] Execution feedback: After execution is completed, execution feedback is sent to the scheduling instruction module, including execution status, actual effect and possible exception information. This is crucial for the self-optimization and exception handling of the scheduling system.

[0035] It also includes the functions of collecting feedback information for data processing and calculation analysis based on the actual deployment effect, and dynamically optimizing the implementation of the existing intelligent matching solution based on the analysis results; including: Obtain each dispatch instruction issued and receive the execution feedback corresponding to the dispatch instruction; The single dispatch effect between the execution feedback and the dispatch instruction is digitally processed and calculated to obtain the corresponding single dispatch state degree and single dispatch state; including: Match the execution effect in a single scheduling effect with the expected effect of the scheduling instruction; If the execution effect is consistent with the expected effect, the single dispatch state degree corresponding to the dispatch instruction is set to 0, and the corresponding single dispatch state is marked as a single dispatch normal state; If the execution effect is inconsistent with the expected effect, the single dispatch state degree corresponding to the dispatch instruction is set to 1, and the corresponding single dispatch state is marked as a single dispatch abnormal state; All single dispatch abnormal states and single dispatch normal states corresponding to all dispatch instructions are obtained, and data processing and calculation of the overall dispatch reliability state are performed on all the obtained single dispatch abnormal states and single dispatch normal states to obtain the corresponding overall dispatch reliability; the processing and obtaining steps of the overall dispatch reliability include: All the acquired single dispatch abnormal states and single dispatch normal states are calculated by the formula Calculate and obtain the overall dispatch reliability ZK; where NY and NZ are the total number of all single dispatch abnormal states and the total number of all single dispatch normal states, respectively; A is the overall dispatch reliability standard value, which can be determined by professional and technical personnel in this field according to the design requirement data; Perform data analysis on the overall dispatch reliability to obtain the corresponding overall dispatch reliability state or overall dispatch unreliable state; If the overall scheduling reliability is less than or equal to 1, the overall scheduling reliability state is generated; Otherwise, the overall scheduling is unreliable; Maintain the subsequent implementation of the existing intelligent matching solution based on the overall scheduling reliability status obtained through analysis; Furthermore, the subsequent implementation of the existing intelligent matching solution is dynamically optimized and adjusted based on the overall scheduling unreliability status obtained through analysis.

[0036] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0037] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The cross-regional energy supply and demand big data intelligent matching system is characterized by: include: Data collection module: responsible for collecting energy supply and demand data in various regions, including wind power, solar power generation data and energy demand data of various users; Data processing module: used to clean, integrate and analyze the collected data, and use machine learning algorithms to predict the future energy supply and demand conditions in various regions; Intelligent matching module: used to intelligently match the optimal energy supply and demand plan based on the analysis results of the data processing module to ensure efficient use of energy and balance between regions; Dispatch instruction module: used to send dispatch instructions to the energy management center in each region to achieve cross-regional allocation of energy; Feedback adjustment module: used to collect feedback information for data processing and calculation analysis based on the actual deployment effect, and dynamically optimize the implementation of the existing intelligent matching plan based on the analysis results; including: obtaining each dispatch instruction issued and receiving the execution feedback corresponding to the dispatch instruction; The single dispatching effect between the execution feedback and the dispatching instruction is digitally processed and calculated to obtain the corresponding single dispatching state degree and single dispatching state; Obtain all single dispatch abnormal states and single dispatch normal states corresponding to all dispatch instructions, and perform data processing and calculation of the overall dispatch reliability state on all acquired single dispatch abnormal states and single dispatch normal states to obtain the corresponding overall dispatch reliability; Perform data analysis on the overall dispatch reliability to obtain the corresponding overall dispatch reliability state or overall dispatch unreliable state; Maintain the subsequent implementation of the existing intelligent matching solution based on the overall scheduling reliability status obtained through analysis; Furthermore, the subsequent implementation of the existing intelligent matching solution is dynamically optimized and adjusted based on the overall scheduling unreliability status obtained through analysis.

2. The cross-regional energy supply and demand big data intelligent matching system according to claim 1 is characterized in that: The data acquisition module specifically includes: Adopt multi-source data collection technology, including weather station data, real-time energy production data and user-side energy consumption data; Use wireless sensor networks and IoT technologies to monitor widely distributed energy resources in real time; Data collection includes time series data, geographic location information, and equipment status information, which are encoded in a standardized data format for subsequent processing.

3. The cross-regional energy supply and demand big data intelligent matching system according to claim 2 is characterized in that: The use of standardized data formats for encoding specifically includes: Define a unified data model that covers all data types that need to be collected, including meteorological data, energy production and consumption data, and various data timestamps, geographic locations, device IDs, and data values; Select a common data exchange format as the basis for data encoding; Use MQTT or CoAP standardized protocols for data collection and transmission; Provide detailed labels and metadata for each data point to accurately understand and utilize the data in subsequent data processing and analysis.

4. The cross-regional energy supply and demand big data intelligent matching system according to claim 1 is characterized in that: The data processing module specifically includes: Ensure data quality using data cleaning techniques, including outlier handling, missing value filling, and data standardization; Use big data technology stack for data storage and computing; Use cluster analysis to predict future energy supply and demand trends and assist in scheduling decisions.

5. The cross-regional energy supply and demand big data intelligent matching system according to claim 4 is characterized in that: The cluster analysis uses the K-means clustering algorithm to divide the data into a predefined number of clusters, including: Use Apache Spark's MLlib library to implement the K-means algorithm and Python's Scikit-learn library to perform DBSCAN clustering; When a clustering hierarchy is needed rather than a flat clustering partition, a hierarchical clustering algorithm is used, based on AgglomerativeClustering in the Scikit-learn library for hierarchical clustering.

6. The cross-regional energy supply and demand big data intelligent matching system according to claim 1 is characterized in that: The intelligent matching module includes using particle swarm optimization (PSO) to search for the optimal or approximately optimal energy allocation solution based on the energy supply and demand forecast results.

7. The cross-regional energy supply and demand big data intelligent matching system according to claim 6 is characterized in that: The particle swarm optimization PSO specifically includes: Define the objective function to evaluate the effect of the energy allocation scheme, including minimizing the energy transmission cost and loss, while considering meeting regional demand and maximizing the utilization of renewable energy. Each particle represents an energy allocation scheme, including the energy dispatch amount of each region. Set the parameters of PSO, including the group size, the maximum number of iterations, the learning factor, and the maximum speed and position range of the particles. A set of particles are randomly initialized in the solution space. The position of each particle corresponds to an energy allocation scheme, and the speed determines its search direction and step size. Calculate the objective function value of each particle to evaluate the quality of the solution it represents. For each particle, if the current position is better than the previous individual optimal position, update its individual optimal position. At the same time, select the best position from all particles as the global optimal position. Update the speed and position of each particle according to the individual optimum and the global optimum. The speed update takes into account the current speed of the particle, the difference between the individual optimal position and the current position, and the difference between the global optimal position and the current position. The process of evaluating, updating individual optimal and global optimal, updating speed and position is repeated until the maximum number of iterations or other stopping conditions are reached. After the iteration ends, the global optimal position represents the optimal energy allocation solution found.

8. The cross-regional energy supply and demand big data intelligent matching system according to claim 7 is characterized in that: The dispatch instruction module generates detailed dispatch instructions based on the data provided by the intelligent matching module, and each instruction contains information on the target area, energy type, dispatch amount, scheduled time and expected effect.

9. The cross-regional energy supply and demand big data intelligent matching system according to claim 1 is characterized in that: The steps of digitally processing and calculating a single dispatch effect between execution feedback and dispatch instructions include: Match the execution effect in a single scheduling effect with the expected effect of the scheduling instruction; If the execution effect is consistent with the expected effect, the single dispatch state degree corresponding to the dispatch instruction is set to 0, and the corresponding single dispatch state is marked as a single dispatch normal state; If the execution effect is inconsistent with the expected effect, the single scheduling state degree corresponding to the scheduling instruction is set to 1, and the corresponding single scheduling state is marked as a single scheduling abnormal state.

10. The cross-regional energy supply and demand big data intelligent matching system according to claim 9 is characterized in that: The steps for obtaining the overall dispatch reliability include: All the acquired single dispatch abnormal states and single dispatch normal states are calculated by the formula Calculate and obtain the overall dispatch reliability ZK; where NY and NZ are the total number of all single dispatch abnormal states and the total number of all single dispatch normal states, respectively; A is the overall dispatch reliability standard value.

Images