Intelligent Regulation Method and System of Virtual Power Plant Based on Dynamic Operation Monitoring

Abstract

The present invention discloses an intelligent regulation method and system for a virtual power plant based on dynamic operation monitoring. The method specifically includes: integrating a real-time data acquisition network for distributed power sources, energy storage devices, and loads, preprocessing data through edge computing and AI, and setting multi-dimensional optimization objectives; using a fast non-dominated sorting multi-objective particle swarm algorithm with an elite strategy to solve the constructed comprehensive optimization model to obtain an optimal energy efficiency improvement plan; deploying the optimal energy efficiency improvement plan, constructing an integrated intelligent distribution network, applying blockchain technology to record the operation status, establishing an intelligent monitoring system, using the Internet of Things and machine learning to predict the energy efficiency trend, dynamically adjusting the optimization plan, and evaluating the effect; through a user feedback mechanism and big data analysis, optimizing the load side management and tapping the energy-saving potential; the present invention improves the energy efficiency of the distribution network and realizes intelligent and efficient energy management.

Description

Technical Field

[0001] The present invention belongs to the technical field of virtual power plants, and specifically relates to an intelligent regulation method and system for virtual power plants based on dynamic operation monitoring. Background Art

[0002] With the increasing energy demand and the urgent requirement for the utilization of clean energy, virtual power plants, as an emerging power system solution, have gradually emerged. Virtual power plants integrate distributed energy resources, such as distributed photovoltaic power generation, wind power generation, small-scale hydropower, and various energy storage devices, controllable loads, etc., and regard them as a unified power plant for coordinated management. However, currently, virtual power plants face many challenges during operation. On the one hand, the output of distributed energy is intermittent and volatile. For example, photovoltaic power generation is greatly affected by light intensity and weather changes, and wind power generation fluctuates with unstable wind speed, which makes it difficult to stabilize the overall output power of virtual power plants. On the other hand, traditional regulation means are difficult to adapt to the complex and changeable operating conditions of virtual power plants in real time and accurately, and cannot give full play to the efficiency of each component, resulting in low energy utilization efficiency and even possibly affecting the safe and stable operation of the power grid.

[0003] For example, the Chinese patent application with the authorization announcement number CN112016838B discloses a calculation method, system and terminal device for the contribution rate of an energy efficiency index system for a distribution network. The method includes: establishing an energy efficiency index system from a medium-voltage distribution network, a flexible substation, and a low-voltage distribution network, calculating the second subjective weight of the third-level index in combination with the third-level index and the second-level index in the energy efficiency index system, and also calculating the second objective weight of the third-level index in the energy efficiency index system for the third-level index. The second subjective weight and the second objective weight of the third-level index are weighted and fused to obtain the contribution rate of the third-level index, and an improvement plan for improving the energy efficiency level of the power electronic distribution network is proposed based on the third-level index with a large contribution rate. This technical solution can establish a comprehensive and appropriate energy efficiency index system for energy efficiency influencing factors, and use combined weighting to calculate the contribution rate of the third-level index corresponding to the influencing factors more scientifically and effectively, providing accurate guidance and reasonable planning for improving the energy efficiency level of the power electronic distribution network and improving the distribution network planning, renovation and construction.

[0004] The above existing technologies all have the following problems: 1) Although it is proposed to calculate the contribution rate through the fusion processing of subjective and objective weights, it is more inclined to static analysis and lacks real-time and dynamic properties; 2) By calculating the contribution rate to identify the third-level index with a greater impact on energy efficiency and proposing an improvement plan based on this, this optimization process is relatively indirect and requires multiple iterations and adjustments to find the optimal energy efficiency improvement plan; 3) The system integration degree and the intelligent level are relatively low. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the purpose of the present invention is to provide an intelligent control method and system for a virtual power plant based on dynamic operation monitoring, which integrates a real-time data acquisition network for distributed power sources, energy storage devices, and loads, preprocesses data through edge computing and AI, and sets multi-dimensional optimization objectives; uses a fast non-dominated sorting multi-objective particle swarm optimization algorithm with an elite strategy to solve the constructed comprehensive optimization model to obtain the optimal energy efficiency improvement plan; deploys the optimal energy efficiency improvement plan to construct an integrated intelligent distribution network, and applies blockchain technology to record the operation status, establish an intelligent monitoring system, use the Internet of Things and machine learning to predict the energy efficiency trend, dynamically adjust the optimization plan, and evaluate the effect; through a user feedback mechanism and big data analysis, optimize the load side management and tap the energy-saving potential; the present invention improves the energy efficiency of the distribution network and realizes intelligent and efficient energy management.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent control method for a virtual power plant based on dynamic operation monitoring, comprising:

[0008] Step S1: Establish an intelligent data acquisition system based on the Internet of Things, integrate the sensor networks of distributed power sources, energy storage devices, and loads, collect data in real time, and preprocess the collected data through edge computing and AI algorithms. Based on the preprocessed data, set multi-dimensional optimization objectives and decision variables for the distribution network;

[0009] Step S2: According to the set multi-dimensional optimization objectives and decision variables of the distribution network, construct a comprehensive optimization model for the distribution network, use a fast non-dominated sorting multi-objective particle swarm optimization algorithm with an elite strategy to solve the comprehensive optimization model of the distribution network, and obtain the optimal energy efficiency improvement plan according to the optimal solution set;

[0010] Step S3: Deploy the obtained optimal energy efficiency improvement plan to the distribution network for infrastructure construction, construct an integrated intelligent distribution network system, and use blockchain technology to record the operation status of the facilities;

[0011] Step S4: Establish an intelligent monitoring system, use Internet of Things sensors and AI analysis algorithms to monitor the energy efficiency of the distribution network in real time, use machine learning algorithms to construct an energy efficiency prediction model, predict the energy efficiency change trend, through an adaptive learning mechanism, dynamically adjust the optimal energy efficiency improvement plan in combination with the monitoring data and prediction results, and use neural network algorithms to regularly evaluate the energy efficiency improvement effect, compare it with the set target for analysis, and adjust the optimal energy efficiency improvement plan according to the comparison result;

[0012] Step S5: Establish a user feedback mechanism, and use big data analysis methods to deeply explore the user's electricity consumption behavior, identify electricity consumption patterns and energy-saving potential, and optimize the load side management according to the identification results.

[0013] Specifically, the specific steps of step S2 include:

[0014] S2.1: Set multi-dimensional optimization objectives and construct a comprehensive objective optimization function , and at the same time, establish constraint conditions, x representing decision variables;

[0015] S2.2: Set the parameters of the particle swarm algorithm and randomly initialize the positions and velocities of the particles;

[0016] S2.3: Calculate the objective function value of each particle according to the position, and apply fast non-dominated sorting to stratify the population, and calculate the crowding distance of each particle i .

[0017] Specifically, the specific steps of step S2 further include:

[0018] S2.4: Update according to the velocity and position update formulas of the particle swarm algorithm to obtain the updated positions and velocities, and perform fast non-dominated sorting on the updated population according to S2.3 to evaluate the quality of the updated particles;

[0019] S2.5: Combine the non-dominated solutions in the current population with the non-dominated solutions in the parent population to form an extended solution set, and select a new parent population according to fast non-dominated sorting and crowding distance to continue the next round of iteration;

[0020] S2.6: Save the found non-dominated solution set through an external archive, and update the external archive in each iteration, remove the old solutions dominated by the new solutions, and add new non-dominated solutions;

[0021] S2.7: Check whether the maximum number of iterations is reached. If the maximum number of iterations is reached, stop the iteration process and output the optimal solution set in the external archive.

[0022] Specifically, the specific formula of the constraint conditions in S2.1 is: , where represents the equality constraint condition, represents the inequality constraint condition, p represents the number of equality constraint conditions, q represents the number of inequality constraint conditions, represents the minimum value function, , .

[0023] Specifically, the specific steps of S2.3 include:

[0024] S2.31: Calculate each particle iObjective function value , where represents the objective function of particle n in the i th optimization objective;

[0025] S2.32: For each particle i , set the number of particles i dominated by and the set of particles i dominated by , and traverse all particle pairs in the population to update the and of each particle. Among them, if , it means a non-dominated particle and is also a non-dominated solution in the current population.

[0026] Specifically, the specific steps of S2.3 further include:

[0027] S2.33: Put all particles into the first layer F and update the of each particle in . Repeat this process until all particles are stratified;

[0028] S2.34: Initialize the crowding distance of each particle i such that . For each optimization objective, sort . Among them, represents the objective function value of particle k in the same layer.

[0029] Specifically, the specific steps of S2.3 further include:

[0030] S2.35: For the sorted boundary particles, set their crowding distance to ;

[0031] For the sorted non-boundary particles, calculate their crowding distance through the formula . Among them, represents the accumulated crowding distance, represents the scaling factor, and respectively represent the objective function values of the adjacent front and rear particles of particle j in the optimization objective i , and respectively represent the maximum and minimum values of the objective function of the optimization objective j in the current layer, represents a positive number, represents the time variation factor, t represents the number of iterations, represents a particle i and its adjacent particles h the interaction strength between them, represents the influence factor of the constraint condition.

[0032] The intelligent regulation and control system of the virtual power plant based on dynamic operation monitoring includes: a data processing module, a model solving module, a system recording module, an intelligent monitoring module, and an optimization module;

[0033] The data processing module is used to collect data of distributed power sources, energy storage devices, and loads in real time and perform preprocessing;

[0034] The model solving module constructs a comprehensive optimization model of the distribution network according to the set multi-dimensional optimization objectives and decision variables, and solves to obtain the optimal energy efficiency improvement plan;

[0035] The system recording module deploys the obtained optimal energy efficiency improvement plan to the distribution network, constructs an integrated intelligent distribution network system, and records the operation status of the facilities;

[0036] The intelligent monitoring module is used to monitor the energy efficiency of the distribution network in real time, predict the energy efficiency change trend, and dynamically adjust the optimal energy efficiency improvement plan according to the monitoring data and prediction results;

[0037] The optimization module is used to collect user opinions and suggestions, optimize the performance of the intelligent distribution network system, and deeply mine the user's electricity consumption behavior to optimize the load side management.

[0038] Specifically, the model solving module includes: a model construction unit and a solving unit;

[0039] The model construction unit sets the optimization objectives and decision variables according to the preprocessed data and constructs a comprehensive optimization model of the distribution network;

[0040] The solving unit uses the fast non-dominated sorting multi-objective particle swarm algorithm with an elite strategy to solve the comprehensive optimization model of the distribution network and obtain the optimal solution set.

[0041] Specifically, the intelligent monitoring module includes: an intelligent monitoring unit, an energy efficiency prediction unit, and an optimization adjustment unit;

[0042] The intelligent monitoring unit uses Internet of Things sensors and AI analysis algorithms to monitor the energy efficiency of the distribution network in real time;

[0043] The energy efficiency prediction unit uses machine learning algorithms to construct an energy efficiency prediction model and predict the energy efficiency change trend;

[0044] The optimization and adjustment unit dynamically adjusts the optimal energy efficiency improvement plan through an adaptive learning mechanism, combining monitoring data and prediction results, and regularly evaluates the energy efficiency improvement effect using a neural network algorithm.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] 1. The present invention proposes an intelligent control method for a virtual power plant based on dynamic operation monitoring. Through real-time data collection and intelligent analysis, it can accurately identify the energy efficiency bottlenecks and optimization potential in the distribution network. Combining multi-dimensional optimization objectives and decision variables, the constructed comprehensive optimization model can find the optimal energy efficiency improvement plan, thereby improving the energy efficiency level of the distribution network; the Internet of Things technology is used to realize real-time data collection, and preprocessing is carried out through edge computing and AI algorithms, enabling the system to quickly respond to changes in the distribution network. At the same time, the intelligent monitoring system and adaptive learning mechanism can dynamically adjust the energy efficiency improvement plan according to real-time monitoring data and prediction results to ensure that the system always maintains the optimal operating state.

[0047] 2. The present invention proposes an intelligent control method for a virtual power plant based on dynamic operation monitoring, integrating multiple methods such as the Internet of Things, edge computing, AI algorithms, machine learning, and neural networks, and constructing an intelligent data collection, analysis, prediction, and optimization system, which not only reduces intervention and errors, improves work efficiency, but also enables the automated management and optimization of the distribution network; by integrating the sensor networks of distributed power sources and energy storage devices, this method can real-time monitor and optimize the power generation and energy storage processes of clean energy, improving the consumption capacity of clean energy and the utilization efficiency of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 Schematic diagram of the intelligent control method for a virtual power plant based on dynamic operation monitoring of the present invention;

[0049] Figure 2 Principle flow chart of the intelligent control method for a virtual power plant based on dynamic operation monitoring of the present invention;

[0050] Figure 3 Flow chart for realizing the optimal energy efficiency improvement plan of the intelligent control method for a virtual power plant based on dynamic operation monitoring of the present invention;

[0051] Figure 4 Flow chart for obtaining the crowding distance of the intelligent control method for a virtual power plant based on dynamic operation monitoring of the present invention;

[0052] Figure 5 System architecture diagram of the intelligent control method for a virtual power plant based on dynamic operation monitoring of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Embodiment 1

[0054] Please refer to Figure 1 - Figure 2 , an embodiment provided by the present invention: a virtual power plant intelligent regulation method based on dynamic operation monitoring, comprising the following steps:

[0055] Step S1: Establish an intelligent data acquisition system based on the Internet of Things, integrate the sensor networks of distributed power sources, energy storage devices, and loads, collect data in real time, and perform preprocessing on the collected data through edge computing and AI algorithms. Based on the preprocessed data, set multi-dimensional optimization objectives and decision variables for the distribution network. Among them, the edge computing method is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here. The AI algorithm uses a supervised learning algorithm. At the same time, the supervised learning algorithm is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0056] Step S2: According to the set multi-dimensional optimization objectives and decision variables of the distribution network, construct a comprehensive optimization model of the distribution network, use the fast non-dominated sorting multi-objective particle swarm algorithm with an elite strategy to solve the comprehensive optimization model of the distribution network, and obtain the optimal energy efficiency improvement plan according to the optimal solution set;

[0057] Step S3: Deploy the obtained optimal energy efficiency improvement plan to the distribution network for infrastructure construction, construct an integrated intelligent distribution network system, and use blockchain technology to record the operation status of the facilities;

[0058] Step S4: Establish an intelligent monitoring system, use Internet of Things sensors and AI analysis algorithms to monitor the energy efficiency of the distribution network in real time, use machine learning algorithms to construct an energy efficiency prediction model, predict the energy efficiency change trend, through an adaptive learning mechanism, dynamically adjust the optimal energy efficiency improvement plan in combination with the monitoring data and prediction results, and use neural network algorithms to regularly evaluate the energy efficiency improvement effect, compare it with the set target for analysis, and adjust the optimal energy efficiency improvement plan according to the comparison result;

[0059] Further, the specific steps of Step S4 include:

[0060] (1) Deployment and data collection of Internet of Things sensors: Deploy Internet of Things sensors at key nodes of the distribution network, such as distributed power sources, energy storage devices, and load terminals, to collect various energy efficiency-related data in real time, and transmit the collected data to the data processing center or edge computing device through the sensor network;

[0061] (2) Data preprocessing and storage: Perform preprocessing operations such as cleaning, denoising, and filtering on the collected raw data to improve data quality, and store the preprocessed data in the database;

[0062] (3)AI analysis algorithm application: Using supervised learning algorithms to deeply mine the stored data, identify key points for energy efficiency improvement and potential problems, and perform pattern recognition, anomaly detection, etc. through supervised learning algorithms to provide decision-making support for energy efficiency optimization;

[0063] (4)Construction of energy efficiency prediction model: Adopting machine learning algorithms, such as time series prediction algorithms, to construct an energy efficiency prediction model. Use historical data to train the supervised learning algorithm so that it can accurately predict the energy efficiency change trend in a future period. Among them, the specific construction process of using the time series prediction algorithm to construct the energy efficiency prediction model is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0064] (5)Adaptive learning mechanism and dynamic adjustment: Design an adaptive learning mechanism to dynamically adjust the optimal energy efficiency improvement plan according to real-time monitoring data and prediction results. If it is found that the energy efficiency index deviates from the preset target, automatically trigger the adjustment mechanism to optimize the distributed power generation scheduling, charge and discharge strategies of energy storage devices, and load management;

[0065] (6)Neural network algorithm evaluation and comparative analysis: Regularly evaluate the energy efficiency improvement effect using neural network algorithms, and compare the evaluation results with the set energy efficiency targets to identify gaps and potential improvement points;

[0066] (7)Optimization plan adjustment and feedback: Adjust the optimal energy efficiency improvement plan according to the comparative analysis results, and feedback the adjusted plan to the distribution network control system to execute the new control strategy, forming a closed-loop optimization process.

[0067] Step S5: Establish a user feedback mechanism, and use big data analysis methods to deeply mine users' electricity consumption behaviors, identify electricity consumption patterns and energy-saving potentials, and optimize load-side management according to the identification results.

[0068] Embodiment 2

[0069] Please refer to Figure 3 - Figure 4 , in this embodiment, the specific steps of step S2 include:

[0070] S2.1: Set multi-dimensional optimization goals and construct a comprehensive objective optimization function , at the same time, establish constraint conditions, where n represents the number of categories of optimization goals, represents the n th objective function of the optimization goal, x represents the decision variable, represents 's weight, j ≤ n ;

[0071] Among them, the multi-dimensional optimization objectives include: the safe and stable operation of the distribution network, the minimization of the comprehensive cost of distributed power sources, the minimization of active power loss, and the minimization of node voltage deviation. The objective optimization functions include but are not limited to: the comprehensive cost of distributed power sources, the active power loss of the distribution network, and the node voltage deviation.

[0072] S2.2: Set the parameters of the particle swarm optimization algorithm and randomly initialize the positions and velocities of the particles. Among them, the parameters of the particle swarm optimization algorithm include: the number of particles, the number of iterations, the learning factor, and the inertia weight;

[0073] S2.3: Calculate the objective function value of each particle according to the position, and apply fast non-dominated sorting to stratify the population, and calculate the i crowding distance of each particle .

[0074] S2.4: Update according to the velocity and position update formulas of the particle swarm optimization algorithm to obtain the updated positions and velocities, and perform fast non-dominated sorting on the updated population according to S2.3 to evaluate the advantages and disadvantages of the updated particles. Among them, the velocity and position update formulas of the particle swarm optimization algorithm are the existing technical content in the art and are not the creative solutions of this application, so they will not be elaborated here;

[0075] S2.5: Combine the non-dominated solutions in the current population with the non-dominated solutions in the parent population to form an extended solution set, and select a new parent population according to fast non-dominated sorting and crowding distance to continue the next round of iteration;

[0076] Furthermore, the specific steps of S2.5 include:

[0077] (1) Combine populations: Combine the non-dominated solutions in the current offspring population with the non-dominated solutions in the parent population to form an extended solution set;

[0078] (2) Fast non-dominated sorting: Perform fast non-dominated sorting on the combined extended solution set, mainly dividing the solution set into multiple fronts. Each front contains a set of non-dominated solutions. The first front contains the optimal solutions, that is, there are no other solutions that can dominate these solutions, also called non-dominated solutions;

[0079] (3) Calculate the crowding distance: Calculate the crowding distance for the solutions in each front. The crowding distance is the distance between a solution and its adjacent solutions in the objective space, which is used to measure the diversity of solutions. The larger the crowding distance, the farther the solution is from other solutions in the objective space, which helps to maintain the diversity of the population;

[0080] (4) Select the new parent population: Select the new parent population from the extended solution set according to the results of the fast non-dominated sorting and the crowding distance. Usually, first select all the solutions in the first front, and then select the solutions in the subsequent fronts in turn until the required population size is reached. When selecting the solutions in the subsequent fronts, the solutions with larger crowding distances will be given priority to ensure the diversity of the population.

[0081] Further, the iterative process includes:

[0082] (1) Update the particle velocity and position: Update according to the velocity and position update formulas of the particle swarm algorithm;

[0083] (2) Crossover and mutation: Introduce the crossover and mutation operations of the genetic algorithm in the particle swarm algorithm to increase the diversity of the solutions;

[0084] (3) Fast non-dominated sorting: Perform fast non-dominated sorting on the updated population;

[0085] (4) Elitist retention strategy: Combine the non-dominated solutions, i.e., the optimal solutions, in the current population with the non-dominated solutions in the parent population, and select the new parent population according to the fast non-dominated sorting and the crowding distance.

[0086] S2.6: Save the found non-dominated solution set through the external archive, and update the external archive in each iteration, remove the old solutions dominated by the new solutions, and add the new non-dominated solutions;

[0087] S2.7: Check whether the maximum number of iterations is reached. If the maximum number of iterations is reached, stop the iterative process and output the optimal solution set in the external archive.

[0088] The specific formula for the constraint conditions in S2.1 is: , where, represents the equality constraint conditions, including power balance and energy balance, represents the inequality constraint conditions, including voltage limit and line capacity limit, p represents the number of equality constraint conditions, q represents the number of inequality constraint conditions, represents the minimum value function, , .

[0089] The specific steps of S2.3 include:

[0090] S2.31: Calculate the objective function value i of each particle , where, represents the n th optimization objective of particle i ;

[0091] S2.32: For each particle i , set the number of particles i dominating and the set of particles i dominated , and traverse all particle pairs in the population to update the and of each particle. Among them, if , it means a non-dominated particle and is also a non-dominated solution in the current population.

[0092] S2.33: Put all particles into the first layer F, and update the of each particle in . Repeat this process until all particles are stratified;

[0093] S2.34: Initialize the crowding distance of each particle i such that . For each optimization objective, sort , where represents the objective function value of particle k in the same layer.

[0094] S2.35: For the sorted boundary particles, set their crowding distance to ;

[0095] For the sorted non-boundary particles, calculate their crowding distance through the formula , where represents the accumulated crowding distance, represents the scaling factor used to adjust the contribution degree of the difference part to . The scaling factor needs to be adjusted according to the specific requirements of the problem to balance the differences between different objectives or different particles. and respectively represent the objective function values of the adjacent front and rear particles of particle j on the optimization objective i . and respectively represent the maximum and minimum values of the objective function values of the optimization objective j in the current layer. represents a positive number used to prevent the denominator from being zero and increase the numerical stability of the formula. represents the time variation factor, which is a function of the number of iterations. This function is specifically designed according to the dynamics of the problem, such as linear, exponential, or periodic. t represents the number of iterations. Represents a particle i And its adjacent particles h The interaction strength between them is calculated based on factors such as the distance, direction, and velocity difference between particles to reflect the relative position relationship of particles in space. Represents the influence factor of the constraint condition, which is used to introduce limiting conditions or constraints, and the influence factor can be a Boolean value, taking values 0 or 1, indicating whether a specific condition is satisfied b , or it can be a continuous value, representing the condition b Satisfaction degree or influence strength Represents the normalization factor, reflecting the particle i And its adjacent particles in the target j Relative difference

[0096] Embodiment 3

[0097] Please refer to Figure 5 , an embodiment provided by the present invention: a virtual power plant intelligent regulation system based on dynamic operation monitoring, including:

[0098] Data processing module, model solving module, system recording module, intelligent monitoring module, optimization module;

[0099] The data processing module is used to collect data of distributed power sources, energy storage devices, and loads in real time and perform preprocessing to provide a basis for subsequent optimization decisions;

[0100] The model solving module constructs a comprehensive optimization model of the distribution network according to the set multi-dimensional optimization objectives and decision variables, and solves to obtain the optimal energy efficiency improvement plan;

[0101] The system recording module deploys the obtained optimal energy efficiency improvement plan to the distribution network, constructs an integrated intelligent distribution network system, and records the operating status of the facilities;

[0102] The intelligent monitoring module is used to monitor the energy efficiency of the distribution network in real time, predict the energy efficiency change trend, and dynamically adjust the optimal energy efficiency improvement plan according to the monitoring data and prediction results;

[0103] The optimization module is used to collect user opinions and suggestions, optimize the performance of the intelligent distribution network system, and deeply mine the user's electricity consumption behavior to optimize the load side management.

[0104] The model solving module includes: a model construction unit and a solving unit;

[0105] The model construction unit sets the optimization objectives and decision variables according to the preprocessed data and constructs a comprehensive optimization model of the distribution network;

[0106] The solution unit uses the fast non-dominated sorting multi-objective particle swarm optimization algorithm with an elite strategy to solve the integrated optimization model of the distribution network and obtain the optimal solution set.

[0107] The system record module includes: a system construction unit and an operating status recording unit;

[0108] The system construction unit transforms the optimal energy efficiency improvement plan into the actual construction of the distribution network infrastructure;

[0109] The operating status recording unit uses blockchain technology to record the operating status of the facilities to ensure the transparency and immutability of the data.

[0110] The intelligent monitoring module includes: an intelligent monitoring unit, an energy efficiency prediction unit, and an optimization and adjustment unit;

[0111] The intelligent monitoring unit uses Internet of Things sensors and AI analysis algorithms to monitor the energy efficiency of the distribution network in real time;

[0112] The energy efficiency prediction unit uses machine learning algorithms to construct an energy efficiency prediction model to predict the trend of energy efficiency changes;

[0113] The optimization and adjustment unit dynamically adjusts the optimal energy efficiency improvement plan through an adaptive learning mechanism, combining monitoring data and prediction results, and uses neural network algorithms to regularly evaluate the energy efficiency improvement effect.

[0114] The optimization module includes: a user feedback unit, a system performance optimization unit, and a management optimization unit;

[0115] The user feedback unit is used to establish a user feedback mechanism to collect user opinions and suggestions;

[0116] The system performance optimization unit optimizes the system performance according to user feedback;

[0117] The management optimization unit uses big data analysis methods to deeply mine the user's electricity consumption behavior, identify electricity consumption patterns and energy-saving potential, and optimize the load-side management according to the identification results.

[0118] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present invention, without departing from the spirit and scope of the present invention, can also make changes, modifications, substitutions, and variations to the above embodiments, and these all fall within the protection scope of the present invention.

Claims

1. A virtual power plant intelligent control method based on dynamic operation monitoring, characterized in that: include: Step S1: Establish an intelligent data acquisition system based on the Internet of Things, integrate the sensor network of distributed power sources, energy storage equipment, and loads, collect data in real time, and pre-process the collected data through edge computing and AI algorithms. Based on the pre-processed data, set the multi-dimensional optimization goals and decision variables of the distribution network; Step S2: According to the set multi-dimensional optimization objectives and decision variables of the distribution network, a comprehensive optimization model of the distribution network is constructed, and the fast non-dominated sorting multi-objective particle swarm algorithm with elite strategy is used to solve the comprehensive optimization model of the distribution network, and the optimal energy efficiency improvement plan is obtained according to the optimal solution set; Step S3: Deploy the obtained optimal energy efficiency improvement solution to the distribution network for infrastructure construction, build an integrated smart distribution network system, and use blockchain technology to record the operating status of the facilities; Step S4: Establish an intelligent monitoring system, use IoT sensors and AI analysis algorithms to monitor the energy efficiency of the distribution network in real time, use machine learning algorithms to build an energy efficiency prediction model, predict the trend of energy efficiency changes, and dynamically adjust the optimal energy efficiency improvement plan through an adaptive learning mechanism, combining monitoring data and prediction results. Use a neural network algorithm to regularly evaluate the energy efficiency improvement effect, compare and analyze it with the set target, and adjust the optimal energy efficiency improvement plan based on the comparison results; Step S5: Establish a user feedback mechanism and use big data analysis methods to deeply mine user electricity usage behaviors, identify electricity usage patterns and energy-saving potential, and optimize load-side management based on the identification results; The specific steps of step S2 include: S2.1: Set multi-dimensional optimization goals and construct a comprehensive goal optimization function F(x). At the same time, establish constraints, where x represents the decision variable; S2.2: Set the parameters of the particle swarm algorithm and randomly initialize the particle position x and velocity v; S2.3: According to the position x, calculate the objective function value of each particle, apply fast non-dominated sorting to stratify the population, and calculate the crowding distance d of each particle i i ; The specific steps of step S2 also include: S2.4: Update according to the speed and position update formula of the particle swarm algorithm to obtain the updated position and speed And perform fast non-dominated sorting on the updated population according to S2.3 to evaluate the quality of the updated particles; S2.5: Merge the non-dominated solutions in the current population with the non-dominated solutions in the parent population to form an extended solution set, and then sort them according to the fast non-dominated sorting and crowding distance d i Select a new parent population to continue the next round of iteration; S2.6: Save the set of non-dominated solutions found through an external archive, and update the external archive in each iteration, remove old solutions dominated by new solutions, and add new non-dominated solutions; S2.7: Check whether the maximum number of iterations has been reached. If so, stop the iteration process and output the optimal solution set in the external archive.

2. The method for intelligent control of a virtual power plant based on dynamic operation monitoring according to claim 1, characterized in that: The specific formula of the constraint condition in S2.1 is: Among them, g r (x) = 0 represents the equality constraint, s e (x) ≥ 0 represents an inequality constraint, p represents the number of equality constraints, q represents the number of inequality constraints, min(·) represents the minimum function, r ≤ p, e ≤ q.

3. The method for intelligent control of a virtual power plant based on dynamic operation monitoring according to claim 2, characterized in that: The specific steps of S2.3 include: S2.31: Calculate the objective function value F for each particle i i =(f1(x i ),...,f n (x i )), where f n (x i ) represents the objective function of particle i in the nth optimization objective; S2.32: For each particle i, set the number of particles N that dominate i i and the set of particles M dominated by i i , and traverse all particle pairs in the population, updating N of each particle i and M i , where if N i =0, it indicates a non-dominated particle, which is also a non-dominated solution in the current population.

4. The method for intelligent control of a virtual power plant based on dynamic operation monitoring according to claim 3 is characterized in that: The specific steps of S2.3 also include: S2.33: All N i = 0 are placed in the first layer F, and the particle's M is updated i N of each particle in i , repeat this process until all particles are delaminated; S2.34: Initialize the crowding distance of each particle i so that d i = 0, for each optimization objective, for F k Sort by, where F k Represents the objective function value of particle k in the same layer.

5. The method for intelligent control of virtual power plants based on dynamic operation monitoring according to claim 4, characterized in that: The specific steps of S2.3 also include: S2.35: For the sorted boundary particles, set their crowding distance to d i =+∞; For the sorted non-boundary particles, the formula Calculate its crowding distance, where represents the accumulated crowding distance, α represents the scaling factor, and f j (i+1) and f j (i-1) represents the objective function values ​​of the neighboring particles before and after particle i on the optimization target j, and They represent the maximum and minimum values ​​of the objective function value of the optimization target j in the current layer, β represents a positive number, δ(t) represents the time change factor, t represents the number of iterations, and φ ih represents the interaction strength between particle i and its neighboring particle h, ε b Represents the impact factor of the constraint condition.

6. A virtual power plant intelligent control system based on dynamic operation monitoring, which is used to implement the virtual power plant intelligent control method based on dynamic operation monitoring as described in any one of claims 1 to 5, characterized in that: include: Data processing module, model solving module, system recording module, intelligent monitoring module, and optimization module; The data processing module is used to collect data of distributed power sources, energy storage devices and loads in real time and perform preprocessing; The model solving module constructs a comprehensive optimization model of the distribution network according to the set multi-dimensional optimization objectives and decision variables, and solves to obtain the optimal energy efficiency improvement solution; The system recording module deploys the obtained optimal energy efficiency improvement solution to the distribution network, builds an integrated intelligent distribution network system, and records the operating status of the facilities; The intelligent monitoring module is used to monitor the energy efficiency of the distribution network in real time, predict the energy efficiency change trend, and dynamically adjust the optimal energy efficiency improvement plan based on the monitoring data and prediction results; The optimization module is used to collect user opinions and suggestions, optimize the performance of the smart distribution network system, and conduct in-depth mining of user electricity consumption behavior to optimize load-side management.

7. The virtual power plant intelligent control system based on dynamic operation monitoring according to claim 6 is characterized in that: The model solving module includes: a model building unit and a solving unit; The model building unit sets optimization objectives and decision variables according to the preprocessed data to build a comprehensive optimization model for the distribution network; The solving unit uses a fast non-dominated sorting multi-objective particle swarm algorithm with an elite strategy to solve the comprehensive optimization model of the distribution network and obtain an optimal solution set.

8. The virtual power plant intelligent control system based on dynamic operation monitoring according to claim 7 is characterized in that: The intelligent monitoring module includes: an intelligent monitoring unit, an energy efficiency prediction unit, and an optimization and adjustment unit; The intelligent monitoring unit uses IoT sensors and AI analysis algorithms to monitor the energy efficiency of the distribution network in real time; The energy efficiency prediction unit uses a machine learning algorithm to build an energy efficiency prediction model to predict the energy efficiency change trend; The optimization and adjustment unit dynamically adjusts the optimal energy efficiency improvement plan through an adaptive learning mechanism in combination with monitoring data and prediction results, and uses a neural network algorithm to regularly evaluate the energy efficiency improvement effect.

Images