Photovoltaic power generation system optimization management system based on intelligent scheduling

Abstract

The invention discloses a photovoltaic power generation system optimization management system based on intelligent scheduling, and relates to the technical field of renewable energy sources and intelligent power grids. The system comprises the following components: a distributed cooperative control strategy, an information sharing and transaction platform supported by a block chain technology, an intelligent scheduling and optimization engine, intelligent power grid deep integration and a user interaction and visualization interface. Through an innovative distributed cooperative control strategy, comprehensive operation data of a photovoltaic power generation system, a wind energy system, an energy storage system and a micro-grid peripheral energy system can be accurately collected in real time, and an energy supply and demand trend is analyzed and predicted based on big data; therefore, the system can automatically adjust the power generation plan, the energy storage strategy and the load distribution of each system, and the optimal operation of the whole energy system is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy and smart grid, and in particular to a photovoltaic power generation system optimization management system based on smart scheduling. Background Art

[0002] With the world's increasing attention to renewable energy and the continuous development of smart grid technology, photovoltaic power generation systems, as an important source of clean energy, have occupied an increasingly important position in the energy structure. Photovoltaic power generation systems convert solar energy into electrical energy through the photoelectric effect, and have the advantages of being clean, renewable, and widely distributed.

[0003] In traditional photovoltaic power generation system management, data collection and processing capabilities are limited, and it is impossible to obtain real-time and accurate comprehensive operating data of photovoltaic power generation systems, wind energy systems, energy storage systems and microgrid surrounding energy systems. It is difficult to automatically adjust the system's power generation plan, energy storage strategy and load distribution, and it is difficult to achieve the optimal operation of the overall energy system. Therefore, it is particularly important to develop a photovoltaic power generation system optimization management system based on intelligent scheduling. Summary of the invention

[0004] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide a photovoltaic power generation system optimization management system based on intelligent scheduling. The system realizes the efficient coordination and optimized operation of photovoltaic power generation systems and other energy systems through innovative distributed collaborative control strategies, information sharing and trading platforms supported by blockchain technology, and deep integration of smart grids, providing strong support for the large-scale application of renewable energy and the development of smart grids.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a photovoltaic power generation system optimization management system based on intelligent scheduling, which includes a distributed collaborative control strategy, an information sharing and trading platform supported by blockchain technology, a deep integration of intelligent scheduling and optimization engine and smart grid, and a user interaction and visualization interface;

[0006] The distributed collaborative control strategy: real-time collection of operating data of photovoltaic power generation systems, wind energy systems, energy storage systems and energy systems surrounding microgrids, design of distributed collaborative control algorithms, prediction of energy supply and demand trends based on big data analysis, automatic adjustment of power generation plans, energy storage strategies and load distribution of each system, and realization of optimal operation of the overall energy system;

[0007] The information sharing and trading platform supported by the blockchain technology: building a distributed energy trading platform based on blockchain, using the immutability and decentralization of blockchain to achieve automated trading through smart contracts. The photovoltaic power generation system can flexibly participate in power market transactions according to market price fluctuations, and automatically adjust power generation plans and energy storage strategies to maximize economic benefits;

[0008] The intelligent scheduling and optimization engine: through prediction algorithms and optimization algorithms, it can make long-term and short-term predictions and optimizations of energy systems. Based on the prediction results and real-time data, the intelligent scheduling engine can dynamically adjust the operating status of each energy system and optimize the overall energy utilization efficiency;

[0009] The deep integration of smart grids: supports deep integration with smart grids, communicates with smart grid control centers through standard interfaces, participates in voltage regulation and frequency control auxiliary services of the grid, and utilizes the flexibility and rapid response capabilities of photovoltaic power generation systems to provide additional support and regulation capabilities for the grid, thereby enhancing the flexibility and resilience of the grid;

[0010] The user interaction and visualization interface provides a user-friendly interactive interface, displays system operation status, energy trading status, and economic benefit analysis information, supports remote monitoring and remote control functions, and facilitates users and managers to grasp system dynamics in real time and make quick decisions and adjustments.

[0011] Furthermore, the distributed collaborative control strategy deploys IoT sensors at key locations of photovoltaic power generation systems, wind energy systems, energy storage systems and microgrids, and transmits the data collected by the sensors to the central control unit or distributed data processing nodes through wireless or wired communication to ensure the real-time and reliability of data transmission, and performs cleaning, denoising and compression preprocessing operations on the received raw data to improve the accuracy and efficiency of subsequent data analysis, and conducts in-depth analysis on the preprocessed data to identify the periodicity, seasonality and abnormal fluctuations of energy supply and demand. Based on historical data and real-time data, the energy supply and demand trend in the future is predicted through prediction algorithms, and the prediction results will serve as an important basis for subsequent collaborative control;

[0012] Clarify the goal of collaborative control, and design a distributed collaborative control algorithm based on the control goal. The algorithm should be able to comprehensively consider the operating status, prediction results and grid constraints of each energy system, and automatically adjust the power generation plan, energy storage strategy and load distribution of each system. Through simulation experiments or small-scale pilots, verify and optimize the designed algorithm to ensure its effectiveness and reliability in practical applications. Continuously monitor the operating status and grid conditions of each energy system, and provide real-time feedback to the collaborative control algorithm. Based on real-time monitoring data and prediction results, the collaborative control algorithm automatically calculates and generates the optimal control strategy for each system, sends the control strategy to the control unit of each energy system, and executes the power generation plan, energy storage strategy and load distribution operations. At the same time, dynamically adjust the control strategy according to the execution effect and market changes, regularly evaluate the operating effect of the system, and continuously optimize the distributed collaborative control algorithm and data processing flow according to the evaluation results and user feedback to improve the overall performance of the system and user experience.

[0013] Furthermore, the distributed collaborative control strategy predicts the energy supply and demand trend in the future through a prediction algorithm, and the prediction algorithm is: in: is the forecast value of supply and demand at the future time t+h, a0 is the intercept term, a1 is the slope of the time trend, indicating a long-term growth or decline trend, a2 and a3 are the coefficients of the seasonal component, which are used to capture the annual seasonal changes, where S is the seasonal cycle, is an autoregressive term, which indicates the impact of supply and demand at the past p time points on the current forecast value, ∈ t+h is the forecast error term, which is usually assumed to be an independent and identically distributed random variable.

[0014] Furthermore, the distributed collaborative control strategy designs a distributed collaborative control algorithm: defines control objectives and constraints; clarifies control objectives, and at the same time, various constraints need to be considered. Among them, P i ,t is the output power of generator i at time t, S j , t is the state of energy storage system j at time t (such as power), L k , t is the demand of load k at time t, C ii ,C jl ,D k They are the corresponding cost function, constraint condition example, power generation capacity constraint: P i ,min≤P i,t ≤P i,max , energy storage capacity constraint: S j,min ≤S j,t ≤S j,max , grid supply and demand balance:∑ i P i,t -∑ j (S j,t -S j,t-1 )=∑ k L k,t ; Local sub-problems: Among them, z t is the Lagrange multiplier related to the balance of power grid supply and demand, ρ is the penalty parameter, and the Lagrange multiplier is updated: Among them, α is the step size parameter, k is the number of iterations, simulation experiments and small-scale pilots. After designing the algorithm, it is necessary to verify its effectiveness and reliability through simulation experiments or small-scale pilots. This usually involves building a simulation environment, deploying the algorithm in it, and observing its performance in actual operation. According to the experimental results, the algorithm can be adjusted and optimized as necessary.

[0015] Furthermore, the information sharing and trading platform supported by the blockchain technology specifies the functions that the platform needs to support, including but not limited to access to photovoltaic power generation systems, real-time acquisition of electricity market prices, automated trading, energy storage strategy adjustment, user account management, and data security and privacy protection, designs the overall architecture of the platform, including the front-end user interface, back-end service system, blockchain network, smart contract layer, and data storage and processing system, selects a suitable blockchain platform, determines the smart contract programming language, and database and cache technology, according to the platform scale and needs;

[0016] Set up a sufficient number of blockchain nodes, configure the communication protocol, consensus mechanism, and block generation speed parameters of the blockchain network, develop smart contracts according to business needs, deploy smart contracts on the blockchain network, and conduct functional testing, performance testing, and security testing. Develop the interface between the photovoltaic power generation system and the blockchain platform to achieve real-time uploading of power generation data and receiving of transaction instructions, integrate the power market data interface, obtain market price information in real time, provide decision-making basis for smart contracts, connect the energy storage system to the platform, realize automatic adjustment of energy storage strategies, and develop a user-friendly front-end interface for energy producers and consumers to view account information, transaction records, market prices, and conduct transaction operations;

[0017] According to market price fluctuations and preset trading strategies, smart contracts automatically trigger trading processes. The photovoltaic power generation system automatically adjusts the power generation plan according to market prices and energy storage status through smart contracts. According to trading needs and electricity market price forecasts, smart contracts automatically adjust the charging and discharging strategies of the energy storage system to maximize economic benefits. Sensitive data is encrypted for storage and transmission to ensure data security. Strict access control policies are implemented to ensure that only authorized users can access relevant data. Smart contracts are regularly audited for security, potential security vulnerabilities are discovered and fixed in a timely manner, and the entire system is integrated and tested to ensure smooth collaboration between components. Some users are invited to test the platform, collect feedback and optimize it. After confirming that the platform is stable and reliable, it is officially put online and continuously monitored and maintained.

[0018] Furthermore, the intelligent scheduling and optimization engine analyzes in detail the characteristics of the energy system, the existing operation mode, the future development needs and the specific goals of scheduling and optimization, designs the overall architecture of the intelligent scheduling and optimization engine, determines and integrates all relevant data sources, removes outliers, duplicate data and incomplete records, ensures data quality, and standardizes and normalizes the data to facilitate subsequent model training and algorithm application, selects prediction algorithms according to business needs and data characteristics, uses historical data to train prediction models, evaluates model performance through cross-validation, adjusts model parameters according to evaluation results, optimizes model performance, deploys trained models to production environments, performs short-term and long-term energy demand forecasts based on real-time data, clarifies optimization goals, builds corresponding optimization models based on optimization goals and system constraints, uses algorithms to solve optimization models, and obtains optimal and suboptimal scheduling solutions;

[0019] Based on the prediction results and optimization plans, design intelligent scheduling strategies, dynamically adjust the scheduling strategies according to real-time data and system status, integrate the prediction model, optimization algorithm and scheduling strategy into the intelligent scheduling and optimization engine, and connect it with the existing energy management system. Conduct a comprehensive test on the integrated system to ensure that the system runs stably and achieves the expected results, formulate a detailed deployment plan, deploy the intelligent scheduling and optimization engine to the production environment according to the deployment plan, continuously monitor the system operation, collect feedback, adjust and optimize the system performance in a timely manner, evaluate the system performance regularly, pay attention to the development of new technologies and algorithms, update and optimize the system in a timely manner, and maintain its competitiveness and advancement.

[0020] Furthermore, the smart grid deep integration analyzes the needs of the smart grid in detail, clarifies the role that the photovoltaic power generation system should play and the expected effect therein, formulates a detailed plan for the deep integration of the smart grid and the photovoltaic power generation system based on the results of the demand analysis, selects communication protocols and data exchange formats that meet industry standards, ensures seamless connection between the smart grid control center and the photovoltaic power generation system, develops interfaces that meet the selected standards in the photovoltaic power generation system, and conducts strict testing on the developed interfaces to ensure the accuracy, real-time and reliability of data transmission. According to the needs of the smart grid, the photovoltaic power generation system is upgraded as necessary to enhance its flexibility and rapid response capability, and the upgraded photovoltaic power generation system is connected to the smart grid control center through a standard interface to complete the establishment of physical connection and data channels, configures relevant parameters of the photovoltaic power generation system in the smart grid control center, develops or configures corresponding functional modules in the photovoltaic power generation system, conducts comprehensive testing on the developed functions, and conducts joint debugging with the smart grid control center to ensure the stable operation and effective support of the photovoltaic power generation system in the smart grid;

[0021] The integrated photovoltaic power generation system will be formally deployed in the smart grid and start actual operation. The operating status of the photovoltaic power generation system will be continuously monitored, operating data will be collected, and its performance will be evaluated. According to the operating data and feedback, the performance of the photovoltaic power generation system will be optimized to improve its support and regulation capabilities. Emergency plans will be formulated to deal with possible power grid failures or photovoltaic power generation system failures to ensure the stable operation of the power grid. Pay attention to the latest developments in smart grid and photovoltaic power generation technologies, understand the application of new technologies and new algorithms, and regularly upgrade the photovoltaic power generation system and the smart grid control center according to technological development trends and actual needs to maintain the system's advancement and competitiveness. Based on operating data and user feedback, the integration solution of the smart grid and photovoltaic power generation system will be continuously optimized to improve overall operating efficiency and reliability.

[0022] Furthermore, the user interaction and visualization interface collects users' needs and preferences through questionnaires and interviews to understand their concerns and expectations regarding system operation status, energy trading, and economic benefit analysis. Based on the user survey results, the core functions that the visualization interface needs to support are clarified, and the layout, color, and icon elements of the user interaction interface are designed to ensure that the interface is concise, intuitive, and easy to operate. Responsive design is adopted to adapt to different devices and screen sizes. Appropriate front-end technology stacks and back-end technologies, as well as database and cache technologies are selected to support the development of the visualization interface. A development environment is built to ensure that the development team can carry out development work efficiently. A data interface is developed to obtain system operation status and energy trading status data in real time from the system back-end or third-party data sources, and the basic framework of the interface is implemented. A real-time monitoring module is developed to display the current operation status of the system, and a historical data query function is implemented. Users can query historical data according to time range and energy type conditions, and use a chart library to display data so that users can understand the data more intuitively.

[0023] Develop remote control functions to allow users to control the start and stop of equipment and adjust parameters through the interface, display economic benefit analysis information, interactively optimize the interface to ensure that users can operate smoothly, perform functional tests on the interface to ensure that all functional modules can work properly and meet user needs, test the performance of the interface to ensure stable operation even under high load conditions, invite users to conduct actual operation tests, collect user feedback, iteratively optimize the interface, prepare the deployment environment, deploy the developed interface to the production environment, perform final debugging and testing, and officially launch the user interaction and visualization interface after confirming that the system is stable and reliable. Perform daily monitoring and maintenance on the interface to ensure the stability and security of the system. According to user feedback and technological development, regularly upgrade and optimize the interface to maintain its advancement and competitiveness.

[0024] Compared with the existing technology, a photovoltaic power generation system optimization management system based on intelligent scheduling has the following beneficial effects:

[0025] 1. Through innovative distributed collaborative control strategies, the system can collect comprehensive operating data of photovoltaic power generation systems, wind energy systems, energy storage systems and energy systems around microgrids in real time and accurately, and predict energy supply and demand trends based on big data analysis. This enables the system to automatically adjust the power generation plans, energy storage strategies and load distribution of each system to achieve optimal operation of the overall energy system. At the same time, through the information sharing and trading platform supported by blockchain technology, photovoltaic power generation systems can flexibly participate in electricity market transactions according to market price fluctuations, automatically adjust power generation plans and energy storage strategies, and thus maximize economic benefits.

[0026] 2. The system supports deep integration with smart grids, communicates with the smart grid control center through standard interfaces, participates in the grid's voltage regulation and frequency control auxiliary services, and utilizes the flexibility and rapid response capabilities of the photovoltaic power generation system. The system can provide additional support and adjustment capabilities for the grid, effectively alleviate the pressure on the grid, and enhance its flexibility and resilience. Especially when responding to emergencies, such as grid failures or imbalances between supply and demand, the photovoltaic power generation system can quickly adjust the power generation and energy storage status, provide stable power support for the grid, and ensure the safe and stable operation of the grid. This deep integration not only improves the intelligence level of the grid, but also provides strong support for the sustainable development of the smart grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 An operation flow chart of a photovoltaic power generation system optimization management system based on intelligent scheduling. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Embodiment 1

[0031] High-precision IoT sensors are carefully deployed at key locations of photovoltaic panel arrays, wind turbines, energy storage battery packs and load points within microgrids to ensure comprehensive and real-time collection of key parameters including power generation, wind speed, light intensity, energy storage status and load demand. A hybrid wireless and wired communication method is used to build a stable and reliable data transmission network to ensure instant transmission and efficient processing of data.

[0032] Establish a central control unit or distributed data processing nodes, adopt cloud computing or edge computing technology, perform real-time cleaning, denoising, and compression preprocessing operations on the massive amount of raw data received, improve data quality and processing efficiency, apply big data analysis technology, and deeply mine the historical and real-time data of energy supply and demand, identify its periodic and seasonal changes and abnormal fluctuations, and provide a solid data foundation for subsequent prediction and control.

[0033] Based on the prediction algorithm, the prediction algorithm is: in: is the forecast value of supply and demand at the future time t+h, a0 is the intercept term, a1 is the slope of the time trend, indicating a long-term growth or decline trend, a2 and a3 are the coefficients of the seasonal component, which are used to capture the annual seasonal changes, where S is the seasonal cycle, is an autoregressive term, which indicates the impact of supply and demand at the past p time points on the current forecast value, ∈ t+h It is the prediction error term, which is usually assumed to be an independent and identically distributed random variable. It combines seasonal factors, time trends and historical data to make high-precision predictions on energy supply and demand trends in the future, design distributed collaborative control algorithms, define control objectives and constraints; clarify control objectives, and at the same time, consider various constraints. Among them, P i ,t is the output power of generator i at time t, S j , t is the state of energy storage system j at time t (such as power), L k , t is the demand of load k at time t, C ii ,C jl ,D k They are the corresponding cost function, constraint condition example, power generation capacity constraint: P i ,min≤P i,t ≤P i,max , energy storage capacity constraint: S j,min ≤S j,t ≤S j,max , grid supply and demand balance:∑ i P i,t -∑ j (S j,t -S j,t-1 )=∑k L k,t ; Local sub-problems: Among them, z t is the Lagrange multiplier related to the balance of power grid supply and demand, ρ is the penalty parameter, and the Lagrange multiplier is updated: Among them, α is the step size parameter, k is the number of iterations, simulation experiments and small-scale pilots, the algorithm needs to comprehensively consider the volatility of photovoltaic power generation, wind power generation, the charging and discharging characteristics of the energy storage system, the dynamic changes in load demand, and the constraints of the power grid, in order to maximize the economic benefits and operational stability of the overall energy system, and automatically adjust the power generation plan, energy storage strategy and load distribution.

[0034] Build a virtual model of the microgrid in a simulation environment, deploy and test the distributed collaborative control algorithm, and verify its effectiveness, stability, and robustness by simulating various operating scenarios. Make necessary adjustments and optimizations to the algorithm based on the simulation results to ensure that it can perform well in complex and changeable actual environments. Deploy the optimized algorithm on-site in a small-scale pilot project, closely monitor the system's operating status and performance, and collect actual operating data to provide valuable experience for subsequent algorithm optimization and system upgrades.

[0035] Regularly evaluate the operating performance of the system, and continuously optimize the distributed collaborative control algorithm and data processing process based on the evaluation results and user feedback, improve the overall performance of the system and user experience, strengthen the deep integration with the smart grid, achieve seamless connection with the smart grid control center through standard interfaces, participate in the voltage regulation and frequency control auxiliary services of the power grid, improve the flexibility and resilience of the power grid, develop user-friendly interactive and visual interfaces, display the system operation status, energy trading status, and economic benefit analysis information in real time, support remote monitoring and remote control functions, and facilitate users and managers to grasp the system dynamics in real time and make quick decisions.

[0036] Embodiment 2

[0037] A professional team, including energy experts, data scientists, and system engineers, was formed to be responsible for the planning and implementation of the entire project, conduct a comprehensive assessment of photovoltaic power plants and wind power plants, and identify key locations for the deployment of IoT sensors.

[0038] High-precision IoT sensors are deployed at key locations of photovoltaic power stations and wind power stations. Sensor types include but are not limited to power generation sensors, wind speed sensors, wind direction sensors, and light intensity sensors to collect key operating data such as power generation, wind speed, wind direction, and light intensity in real time.

[0039] Wireless communication technology or wired communication technology is used to transmit the data collected by the sensor to the central control unit or distributed data processing node in real time. During the data transmission process, the integrity and security of the data are ensured, and encryption technology is used to prevent data leakage. In the central control unit or distributed data processing node, the received raw data is cleaned, denoised, and compressed for preprocessing operations to improve the accuracy and efficiency of subsequent data analysis.

[0040] Based on the preprocessed data, the prediction algorithm is used to conduct an in-depth analysis of the cyclical and seasonal laws of energy supply and demand. Combined with historical data and real-time data, the energy supply and demand trend in the future is accurately predicted. The prediction results will serve as an important basis for subsequent coordinated control. The prediction algorithm is: in: is the forecast value of supply and demand at the future time t+h, a0 is the intercept term, a1 is the slope of the time trend, indicating a long-term growth or decline trend, a2 and a3 are the coefficients of the seasonal component, which are used to capture the annual seasonal changes, where S is the seasonal cycle, is an autoregressive term, which indicates the impact of supply and demand at the past p time points on the current forecast value, ∈ t+h is the forecast error term, which is usually assumed to be an independent and identically distributed random variable.

[0041] Clarify the goal of collaborative control, that is, maximize energy efficiency, reduce operation and maintenance costs, and ensure grid stability. Design a distributed collaborative control algorithm and define control objectives and constraints. Clarify the control objectives while considering various constraints. Among them, P i ,t is the output power of generator i at time t, S j , t is the state of energy storage system j at time t (such as power), L k , t is the demand of load k at time t, C ii ,C jl ,D k They are the corresponding cost function, constraint condition example, power generation capacity constraint: P i ,min≤P i,t ≤P i,max , energy storage capacity constraint: S j,min ≤S j,t ≤S j,max , grid supply and demand balance:∑ i P i,t -∑ j (S j,t -S j,t-1 )=∑ k L k,t ; Local sub-problems: Among them, z t is the Lagrange multiplier related to the balance of power grid supply and demand, ρ is the penalty parameter, and the Lagrange multiplier is updated: Among them, α is the step size parameter, k is the number of iterations, simulation experiments and small-scale pilots,After the algorithm is designed, it is necessary to verify its effectiveness and reliability through simulation experiments or small-scale pilots, which usually involves building a simulation environment, deploying the algorithm in it, and observing its performance in actual operation. According to the experimental results, the algorithm can be adjusted and optimized as necessary, considering the operating status of photovoltaic power stations and wind power stations, prediction results and grid constraints. The algorithm should be able to automatically adjust the power generation plan of each energy system, including the power generation of photovoltaic power stations and the power generation priority of wind power stations, so as to achieve the optimal operation of the overall energy system.

[0042] The designed collaborative control algorithm is verified in a simulation environment, and its performance in different scenarios is observed. The algorithm is adjusted and optimized as necessary based on the simulation results. Some photovoltaic power stations and wind power stations are selected for small-scale pilot operation, and actual operation data is collected to evaluate the effectiveness and reliability of the algorithm.

[0043] Continuously monitor the operating status and grid conditions of each energy system, and provide real-time feedback to the collaborative control algorithm. Based on the real-time monitoring data and prediction results, the collaborative control algorithm automatically calculates and generates the optimal control strategy for each system, and sends the control strategy to the control unit of each energy system for execution.

[0044] Dynamically adjust control strategies based on execution results and market changes to ensure that the energy system always remains in the optimal operating state.

[0045] Regularly evaluate the system's operating performance, including energy efficiency, operation and maintenance costs, and grid stability. Based on the evaluation results and user feedback, continuously optimize the distributed collaborative control algorithm and data processing process to improve the overall system performance and user experience.

[0046] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A photovoltaic power generation system optimization management system based on intelligent scheduling, characterized in that: The system includes distributed collaborative control strategies, information sharing and trading platforms supported by blockchain technology, intelligent scheduling and optimization engines, deep integration with smart grids, and user interaction and visualization interfaces; The distributed collaborative control strategy: real-time collection of operating data of photovoltaic power generation systems, wind energy systems, energy storage systems and energy systems surrounding microgrids, design of distributed collaborative control algorithms, prediction of energy supply and demand trends based on big data analysis, automatic adjustment of power generation plans, energy storage strategies and load distribution of each system, and realization of optimal operation of the overall energy system; The information sharing and trading platform supported by the blockchain technology: building a distributed energy trading platform based on blockchain, using the immutability and decentralization of blockchain to achieve automated trading through smart contracts. The photovoltaic power generation system can flexibly participate in power market transactions according to market price fluctuations, and automatically adjust power generation plans and energy storage strategies to maximize economic benefits; The intelligent scheduling and optimization engine: through prediction algorithms and optimization algorithms, it can make long-term and short-term predictions and optimizations of energy systems. Based on the prediction results and real-time data, the intelligent scheduling engine can dynamically adjust the operating status of each energy system and optimize the overall energy utilization efficiency; The deep integration of smart grids: supports deep integration with smart grids, communicates with smart grid control centers through standard interfaces, participates in voltage regulation and frequency control auxiliary services of the grid, and utilizes the flexibility and rapid response capabilities of photovoltaic power generation systems to provide additional support and regulation capabilities for the grid, thereby enhancing the flexibility and resilience of the grid; The user interaction and visualization interface provides a user-friendly interactive interface, displays system operation status, energy trading status, and economic benefit analysis information, supports remote monitoring and remote control functions, and facilitates users and managers to grasp system dynamics in real time and make quick decisions and adjustments.

2. According to claim 1, a photovoltaic power generation system optimization management system based on intelligent scheduling is characterized in that: The distributed collaborative control strategy deploys IoT sensors at key locations of photovoltaic power generation systems, wind energy systems, energy storage systems and microgrids, transmits the data collected by the sensors to the central control unit or distributed data processing nodes through wireless or wired communication, performs cleaning, denoising and compression preprocessing operations on the received raw data, conducts in-depth analysis on the preprocessed data, identifies the periodicity, seasonality and abnormal fluctuations of energy supply and demand, and predicts the energy supply and demand trend in the future based on historical data and real-time data through prediction algorithms. The prediction results will serve as an important basis for subsequent collaborative control; Clarify the goal of collaborative control, and design a distributed collaborative control algorithm based on the control goal. The algorithm should be able to comprehensively consider the operating status, prediction results and grid constraints of each energy system, and automatically adjust the power generation plan, energy storage strategy and load distribution of each system. Through simulation experiments or small-scale pilots, verify and optimize the designed algorithm, continuously monitor the operating status and grid conditions of each energy system, and provide real-time feedback to the collaborative control algorithm. Based on real-time monitoring data and prediction results, the collaborative control algorithm automatically calculates and generates the optimal control strategy for each system, sends the control strategy to the control unit of each energy system, and executes the power generation plan, energy storage strategy and load distribution operations. At the same time, dynamically adjust the control strategy according to the execution effect and market changes, regularly evaluate the operating effect of the system, and continuously optimize the distributed collaborative control algorithm and data processing flow according to the evaluation results and user feedback to improve the overall performance of the system and user experience.

3. According to claim 2, a photovoltaic power generation system optimization management system based on intelligent scheduling is characterized in that: The distributed collaborative control strategy predicts the energy supply and demand trend in the future through a prediction algorithm. The prediction algorithm is: in: is the forecast value of supply and demand at the future time t+h, a0 is the intercept term, a1 is the slope of the time trend, indicating a long-term growth or decline trend, a2 and a3 are the coefficients of the seasonal component, which are used to capture the annual seasonal changes, where S is the seasonal cycle, is an autoregressive term, which indicates the impact of supply and demand at the past p time points on the current forecast value, ∈ t+h is the forecast error term, which is usually assumed to be an independent and identically distributed random variable.

4. According to claim 2, a photovoltaic power generation system optimization management system based on intelligent scheduling is characterized in that: The distributed collaborative control strategy designs a distributed collaborative control algorithm: defines control objectives and constraints; clarifies control objectives, and at the same time, various constraints need to be considered. Among them, P i ,t is the output power of generator i at time t, S j , t is the state of energy storage system j at time t, L k ,t is the demand of load k at time t, D k They are the corresponding cost function, constraint condition example, power generation capacity constraint: P i ,min≤P i,t ≤P i,max , energy storage capacity constraint: S j,min ≤S j,t ≤S j,max , grid supply and demand balance:∑ i P i,t -∑ j (S j,t -S j,t-1 )=∑ k L k,t ; Local sub-problems: Among them, z t is the Lagrange multiplier related to the balance of power grid supply and demand, ρ is the penalty parameter, and the Lagrange multiplier is updated: Among them, α is the step size parameter, k is the number of iterations, simulation experiments and small-scale pilots. After designing the algorithm, it is necessary to verify its effectiveness and reliability through simulation experiments or small-scale pilots. This usually involves building a simulation environment, deploying the algorithm in it, and observing its performance in actual operation. According to the experimental results, the algorithm can be adjusted and optimized as necessary.

5. The photovoltaic power generation system optimization management system based on intelligent scheduling according to claim 1 is characterized in that: The information sharing and trading platform supported by the blockchain technology shall clarify the functions that the platform needs to support, including but not limited to the access of photovoltaic power generation systems, real-time acquisition of electricity market prices, automated trading, energy storage strategy adjustment, user account management, data security and privacy protection, design the overall architecture of the platform, including the front-end user interface, back-end service system, blockchain network, smart contract layer, and data storage and processing system, select the appropriate blockchain platform, determine the smart contract programming language, as well as database and cache technology, according to the platform scale and needs; Set up a sufficient number of blockchain nodes, configure the communication protocol, consensus mechanism, and block generation speed parameters of the blockchain network, develop smart contracts according to business needs, deploy smart contracts on the blockchain network, and conduct functional testing, performance testing, and security testing. Develop the interface between the photovoltaic power generation system and the blockchain platform to achieve real-time uploading of power generation data and receiving of transaction instructions, integrate the power market data interface, obtain market price information in real time, provide decision-making basis for smart contracts, connect the energy storage system to the platform, realize automatic adjustment of energy storage strategies, and develop a user-friendly front-end interface for energy producers and consumers to view account information, transaction records, market prices, and conduct transaction operations; According to market price fluctuations and preset trading strategies, smart contracts automatically trigger trading processes. The photovoltaic power generation system automatically adjusts the power generation plan according to market prices and energy storage status through smart contracts. According to trading needs and electricity market price forecasts, smart contracts automatically adjust the charging and discharging strategies of the energy storage system to maximize economic benefits. Sensitive data is encrypted for storage and transmission, and strict access control strategies are implemented. Smart contracts are regularly audited for security, potential security vulnerabilities are discovered and fixed in a timely manner, and the entire system is integrated and tested. Some users are invited to test the platform, feedback is collected and optimized, and after confirming that the platform is stable and reliable, it is officially put online and continuously monitored and maintained.

6. The photovoltaic power generation system optimization management system based on intelligent scheduling according to claim 1 is characterized in that: The intelligent scheduling and optimization engine analyzes in detail the characteristics of the energy system, the existing operation mode, the future development needs and the specific goals of scheduling and optimization, designs the overall architecture of the intelligent scheduling and optimization engine, determines and integrates all relevant data sources, removes outliers, duplicate data and incomplete records, standardizes and normalizes the data, selects prediction algorithms according to business needs and data characteristics, trains prediction models using historical data, evaluates model performance through cross-validation, adjusts model parameters according to the evaluation results, optimizes model performance, deploys the trained model to the production environment, performs short-term and long-term energy demand forecasts based on real-time data, clarifies optimization goals, builds corresponding optimization models based on optimization goals and system constraints, uses algorithms to solve the optimization models, and obtains optimal and suboptimal scheduling solutions; Based on the prediction results and optimization plans, design intelligent scheduling strategies, dynamically adjust the scheduling strategies according to real-time data and system status, integrate the prediction model, optimization algorithm and scheduling strategy into the intelligent scheduling and optimization engine, and connect it with the existing energy management system. Conduct comprehensive testing on the integrated system, formulate a detailed deployment plan, deploy the intelligent scheduling and optimization engine to the production environment according to the deployment plan, continuously monitor the system operation, collect feedback, adjust and optimize the system performance in a timely manner, evaluate the system performance regularly, pay attention to the development of new technologies and algorithms, update and optimize the system in a timely manner, and maintain its competitiveness and advancement.

7. The photovoltaic power generation system optimization management system based on intelligent scheduling according to claim 1 is characterized in that: The smart grid deep integration analyzes the needs of the smart grid in detail, clarifies the role that the photovoltaic power generation system should play and the expected effect therein, formulates a detailed plan for the deep integration of the smart grid and the photovoltaic power generation system based on the results of the demand analysis, selects communication protocols and data exchange formats that meet industry standards, develops interfaces that meet the selected standards in the photovoltaic power generation system, and conducts strict testing on the developed interfaces. According to the needs of the smart grid, the photovoltaic power generation system is upgraded as necessary to improve its flexibility and rapid response capabilities, and the upgraded photovoltaic power generation system is connected to the smart grid control center through a standard interface to complete the establishment of physical connections and data channels, configures relevant parameters of the photovoltaic power generation system in the smart grid control center, develops or configures corresponding functional modules in the photovoltaic power generation system, conducts comprehensive testing on the developed functions, and conducts joint debugging with the smart grid control center; The integrated photovoltaic power generation system will be formally deployed to the smart grid and start actual operation. The operating status of the photovoltaic power generation system will be continuously monitored, operating data will be collected, and its performance will be evaluated. According to the operating data and feedback, the performance of the photovoltaic power generation system will be optimized to enhance its support and regulation capabilities. Emergency plans will be formulated to deal with possible power grid failures or photovoltaic power generation system failures. Pay attention to the latest developments in smart grid and photovoltaic power generation technologies, understand the application of new technologies and algorithms, and regularly upgrade the photovoltaic power generation system and the smart grid control center according to technological development trends and actual needs to maintain the system's advancement and competitiveness. Based on operating data and user feedback, the integration solution of the smart grid and photovoltaic power generation system will be continuously optimized to improve overall operating efficiency and reliability.

8. The photovoltaic power generation system optimization management system based on intelligent scheduling according to claim 1 is characterized in that: The user interaction and visualization interface collects users' needs and preferences through questionnaires and interviews to understand their concerns and expectations about system operation status, energy trading, and economic benefit analysis. According to the user survey results, the core functions that the visualization interface needs to support are clarified, and the layout, color, and icon elements of the user interaction interface are designed. Responsive design is adopted to adapt to different devices and screen sizes. The appropriate front-end technology stack and back-end technology, as well as database and cache technology are selected to support the development of the visualization interface. The development environment is built, and the data interface is developed. The system operation status and energy trading status data are obtained from the system back-end or third-party data source in real time. The basic framework of the interface is implemented, and a real-time monitoring module is developed to display the current operation status of the system. The historical data query function is implemented, and users can query historical data according to time range and energy type conditions, and use the chart library to display data; Develop remote control functions to allow users to control the start and stop of equipment and adjust parameters through the interface, display economic benefit analysis information, interactively optimize the interface, perform functional tests on the interface to meet user needs, test the performance of the interface, invite users to conduct actual operation tests, collect user feedback, iteratively optimize the interface, prepare the deployment environment, deploy the developed interface to the production environment, perform final debugging and testing, and after confirming that the system is stable and reliable, officially put the user interaction and visualization interface online, perform daily monitoring and maintenance on the interface, and regularly upgrade and optimize the interface based on user feedback and technological development to maintain its advancement and competitiveness.

Images