A water-solar-storage intelligent energy management method and system
By deploying data perception modules in the water photo storage system and performing parallel energy supply analysis, the problems of difficulty in coordination and lack of intelligent regulation in the water photo storage energy management are solved, and the energy utilization efficiency of the water photo storage system is improved .
Patent Information
- Application Number
- CN202410994942.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-24
AI Technical Summary
The existing water and photoelectric energy management methods cannot intelligently carry out energy production, storage and distribution, and it is difficult to meet the dynamic energy supply management needs, especially in the coordination of multi-energy systems and the lack of intelligent regulation.
Deploy data sensing modules in the water photo storage system, integrate water level sensors, light intensity sensors, temperature sensors and current voltage sensors, collect operating status data through real-time monitoring and collecting load demand prediction and energy supply parallel analysis, determine energy deviation parameters, and perform Energy supply allocation analysis and closed-loop control to achieve intelligent coordination of energy.
Through real-time monitoring, load demand forecasting and energy distribution analysis, combined with closed-loop control, the energy utilization efficiency of the water photo storage system is improved, and the problems of coordination difficulties in multi-energy systems and lack of intelligent regulation are solved.
Smart Images

Figure CN118539434B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of energy management technology, and in particular to a water-solar-energy storage smart energy management method and system. Background Art
[0002] In modern energy management, with the development of renewable energy technology, the comprehensive utilization of multiple energy resources has become a key strategy to improve energy efficiency and reduce carbon emissions. The hydro-photovoltaic storage smart energy management method and system is proposed in this context. This method combines hydropower, photovoltaic power generation and energy storage systems, and realizes efficient utilization and optimal allocation of multiple energy sources through intelligent energy management strategies. However, the existing hydro-photovoltaic storage energy management method has the problem of not being able to intelligently produce, store and distribute energy, and cannot meet the dynamic energy supply management needs. Summary of the invention
[0003] The present application provides a water-solar-storage smart energy management method and system, which is used to solve the technical problems of the existing technology such as difficulty in coordinating multiple energy systems and lack of intelligent regulation.
[0004] In view of the above problems, the present application provides a water-solar-storage intelligent energy management method and system.
[0005] The first aspect of the present application provides a water-solar-storage smart energy management method, the method comprising:
[0006] A data perception module is deployed in the water-photovoltaic storage system, the data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor, and the data perception module is used to monitor and collect the water-photovoltaic storage operation status data stream; load demand forecasting is performed on the water-photovoltaic storage system to obtain system power demand parameter information, and energy supply parallel analysis is performed on the water-photovoltaic storage operation status data stream through energy data processing multi-channel to determine the water-photovoltaic storage energy supply parameter information; according to the comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, the water-photovoltaic storage energy deviation parameter is determined, and based on the water-photovoltaic storage energy deviation parameter, energy supply distribution analysis is performed on the water-photovoltaic storage system to obtain the water-photovoltaic storage grid-connected energy supply distribution parameter; energy supply control analysis is performed based on the water-photovoltaic storage grid-connected energy supply distribution parameter to determine the water-photovoltaic storage energy supply coordination control parameter, and the water-photovoltaic storage system is energy closed-loop controlled through the water-photovoltaic storage energy supply coordination control parameter.
[0007] The second aspect of the present application provides a water-solar-storage smart energy management system, the system comprising:
[0008] An operation status data stream acquisition unit, wherein the operation status data stream acquisition unit deploys a data perception module in the water-photovoltaic storage system, wherein the data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor, and acquires the water-photovoltaic storage operation status data stream through monitoring and acquisition by the data perception module; an energy supply parallel analysis unit, wherein the energy supply parallel analysis unit predicts the load demand of the water-photovoltaic storage system, obtains the system power demand parameter information, performs energy supply parallel analysis on the water-photovoltaic storage operation status data stream through energy data processing multi-channel, and determines the water-photovoltaic storage energy supply parameter information. information; an energy supply allocation analysis unit, which determines the water-photovoltaic storage energy deviation parameter according to the comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, and performs energy supply allocation analysis on the water-photovoltaic storage system based on the water-photovoltaic storage energy deviation parameter to obtain the water-photovoltaic storage grid-connected energy supply allocation parameter; an energy supply control analysis unit, which performs energy supply control analysis based on the water-photovoltaic storage grid-connected energy supply allocation parameter to determine the water-photovoltaic storage energy supply coordination control parameter, and performs energy closed-loop control of the water-photovoltaic storage system through the water-photovoltaic storage energy supply coordination control parameter.
[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0010] The present application deploys a data perception module in a water-photovoltaic storage system. The data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor. The data perception module monitors and collects the data stream of the water-photovoltaic storage operation status; the load demand of the water-photovoltaic storage system is predicted to obtain the system power demand parameter information, and the water-photovoltaic storage operation status data stream is analyzed in parallel through energy data processing multi-channel to determine the water-photovoltaic storage energy supply parameter information; according to the comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, the water-photovoltaic storage energy deviation parameter is determined, and the water-photovoltaic storage system is analyzed for energy supply distribution based on the water-photovoltaic storage energy deviation parameter to obtain the water-photovoltaic storage grid-connected energy supply distribution parameter; based on the water-photovoltaic storage grid-connected energy supply distribution parameter, energy supply control analysis is performed to determine the water-photovoltaic storage energy supply coordination control parameter, and the water-photovoltaic storage system is controlled by the water-photovoltaic storage energy supply coordination control parameter. The present invention solves the technical problems of the existing technology that there are difficulties in coordinating multiple energy systems and lack of intelligent regulation, and achieves the technical effect of improving the energy utilization efficiency of the water-photovoltaic storage system through real-time monitoring, load demand prediction, and energy supply distribution analysis combined with closed-loop control. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0012] Figure 1 A schematic diagram of a water-solar-storage smart energy management method provided in an embodiment of the present application;
[0013] Figure 2 A schematic diagram of the structure of a water-solar-storage smart energy management system provided in an embodiment of the present application.
[0014] Explanation of the reference numerals: operating status data stream acquisition unit 11 , energy supply parallel analysis unit 12 , energy supply distribution analysis unit 13 , energy supply control analysis unit 14 . DETAILED DESCRIPTION
[0015] The present application provides a method and system for intelligent energy management of water-solar-energy storage, aiming to solve the technical problems of difficulty in coordinating multiple energy systems and lack of intelligent regulation in the prior art. Through real-time monitoring, load demand forecasting, and energy supply distribution analysis combined with closed-loop control, the technical effect of improving the energy utilization efficiency of the water-solar-energy storage system is achieved.
[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.
[0018] Embodiment 1
[0019] like Figure 1 As shown, the present application provides a water-solar-storage smart energy management method, the method comprising:
[0020] Step S100: deploy a data perception module in the water-solar storage system, wherein the data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor, and monitors and collects the water-solar storage operation status data stream through the data perception module.
[0021] In the embodiment of the present application, the data sensing module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor. The water level sensor is used to monitor the water level of the water body; the light intensity sensor is used to measure the intensity of sunlight; the temperature sensor is used to monitor the ambient temperature; and the current and voltage sensor monitors the current and voltage in real time.
[0022] By deploying a data perception module in the water-solar storage system for data collection, the water-solar storage operation status data stream is obtained, including water level data, light intensity data, ambient temperature data, and current and voltage data.
[0023] Step S200: forecast the load demand of the hydro-solar-storage system to obtain the system power demand parameter information, perform energy supply parallel analysis on the hydro-solar-storage operation status data stream through energy data processing multi-channel, and determine the hydro-solar-storage energy supply parameter information.
[0024] In an embodiment of the present application, when predicting the load demand of a water-photovoltaic-storage system, first collect information on various factors that affect the system load, and classify and divide these data into time series. Next, use a recurrent neural network model to train these data, build a system load prediction model, and use this model to predict future load demands and obtain system power demand parameter information. Then, by configuring the data processing channels of photovoltaic power generation, hydropower generation, and energy storage systems, collect energy supply data from each channel, and use a deep neural network to train the data for energy supply analysis and build a corresponding energy supply analysis network. In the process of multi-channel parallel processing, the energy supply data of the photovoltaic, hydraulic, and energy storage systems are comprehensively analyzed to determine the energy supply parameter information of the water-photovoltaic-storage system.
[0025] Furthermore, in the method provided in the embodiment of the application, the obtaining of system power demand parameter information further includes:
[0026] Acquire information on factors influencing system load, wherein the information on factors influencing system load includes historical load consumption, weather and environmental conditions, and standby regulation requirements; classify and identify a historical load data set of a water-solar-energy storage system based on the information on factors influencing system load, and obtain a system load factor data set; perform sequence division on the system load factor data set according to a preset time window, and obtain a system factor sequence load data set; use a recurrent neural network structure to train and fuse the system factor sequence load data set, and construct a system load prediction network; perform load demand prediction on the water-solar-energy storage system based on the system load prediction network, and obtain the system power demand parameter information.
[0027] In the embodiment of the present application, the historical load consumption, weather and environmental conditions, and standby regulation requirements are first extracted from the historical database, and these data are used as the system load influencing factor information. Next, the historical load data set of the water-light storage system is also extracted from the historical database, and classified and identified. When identifying, the system load influencing factor information is first feature extracted, and the load data is extracted by time period, such as hour, day, week, and month, and the statistics in each time period are calculated, such as the average value, maximum value, minimum value, and standard deviation. At the same time, weather characteristics such as sunshine duration, maximum temperature, minimum temperature, precipitation, etc. are extracted. After completing the feature extraction, the historical load data set of the water-light storage system is classified and identified. Using label encoding technology, the classified data, such as weather conditions and load peaks / troughs, are converted into numerical data, and cluster analysis algorithms, such as K-means clustering, are used to identify load patterns and group similar load patterns. Based on the clustering results, each type of load pattern is identified to form a load pattern label, such as peak load, valley load, and stable load. By integrating the extracted features and load pattern labels, a system load factor data set is generated.
[0028] Next, the system load factor data set is divided into sequences according to preset time windows, such as hours, days, and weeks, to generate a system factor sequence load data set.
[0029] Then, the recurrent neural network structure is used to train and fuse the system factor sequence load data set, and the system factor sequence load data set is input into the RNN model for training. The RNN captures the temporal dependencies in the time series data. Through multiple iterative training, the model learns the potential patterns and rules in the data and constructs a system load prediction network.
[0030] Finally, based on the constructed system load forecasting network, the future load demand is predicted. By inputting the current and historical load influencing factor data, the system load forecasting network outputs the load demand in a specific time period in the future and obtains the system power demand parameter information.
[0031] Furthermore, in the method provided in the embodiment of the application, the determining of the water-solar energy storage parameter information further includes:
[0032] According to the water-photovoltaic-storage system, a photovoltaic power generation data processing channel, a hydroelectric power generation data processing channel and an energy storage system data processing channel are determined; an energy supply data set of the water-photovoltaic-storage system is collected and acquired, and energy supply analysis training is performed on the energy supply data set of the water-photovoltaic-storage system using a deep neural network structure to obtain a photovoltaic power generation energy supply analysis network, a hydroelectric power generation energy supply analysis network and an energy storage system energy supply analysis network; the photovoltaic power generation energy supply analysis network, the hydroelectric power generation energy supply analysis network and the energy storage system energy supply analysis network are respectively configured for the photovoltaic power generation data processing channel, the hydroelectric power generation data processing channel and the energy storage system data processing channel to construct the energy data processing multi-channel; based on the energy data processing multi-channel, the water-photovoltaic-storage operation status data stream is mapped and analyzed in parallel to determine the water-photovoltaic-storage energy supply parameter information.
[0033] In the embodiment of the present application, firstly, three independent data processing channels are determined according to the structure and function of the water-photovoltaic-storage system, namely, the photovoltaic power generation data processing channel, the hydropower generation data processing channel and the energy storage system data processing channel.
[0034] Next, sensors such as current and voltage sensors are used to collect data such as the power output of photovoltaic power generation, the power output of hydropower generation, and the charging and discharging status of the energy storage system in real time to obtain photovoltaic power generation data sets, hydropower generation data sets, and energy storage system data sets. These data sets are collectively referred to as the water-photovoltaic-storage system energy supply data sets. Then, the energy supply data sets of the water-photovoltaic-storage system are trained for energy supply analysis using a deep neural network structure. Specifically, the photovoltaic power generation data sets, the hydropower generation data sets, and the energy storage system data sets are trained respectively to construct photovoltaic power generation energy supply analysis networks, hydropower generation energy supply analysis networks, and energy storage system energy supply analysis networks. During the training process, the deep neural network learns the complex patterns and relationships in the data through multi-layer nonlinear transformations and back propagation algorithms, thereby improving the accuracy of energy supply analysis. The trained photovoltaic power generation energy supply analysis networks, hydropower generation energy supply analysis networks, and energy storage system energy supply analysis networks are respectively configured to the photovoltaic power generation data processing channel, the hydropower generation data processing channel, and the energy storage system data processing channel to complete the construction of multiple channels for energy data processing.
[0035] Based on the configured energy data processing multi-channel, parallel computing technology is used to analyze the operating status data streams of photovoltaic power generation, hydropower generation and energy storage systems in parallel. Each data processing channel runs independently, analyzes the corresponding energy supply data, and maps the results to the overall energy supply status of the system. Finally, by integrating the analysis results of each channel and using data fusion technology, the water-solar-storage energy supply parameter information is determined, including the real-time energy supply capacity, efficiency and status of photovoltaic power generation, hydropower generation and energy storage systems.
[0036] Step S300: Determine the hydro-photovoltaic storage energy deviation parameter according to the comparison difference between the hydro-photovoltaic storage energy supply parameter information and the system power demand parameter information, perform energy supply distribution analysis on the hydro-photovoltaic storage system based on the hydro-photovoltaic storage energy deviation parameter, and obtain the hydro-photovoltaic storage grid-connected energy supply distribution parameter.
[0037] In an embodiment of the present application, the real-time energy supply parameter information is first compared with the electric energy demand parameter information, and the difference between the two is calculated, and this difference is the water-photovoltaic-storage energy deviation parameter. Next, the energy supply priority of different energy sources is set according to the water-photovoltaic-storage energy deviation parameter, such as limited use of renewable energy photovoltaic power generation, followed by hydropower generation, and the energy storage system is used to adjust the peaks and valleys, and considers factors such as the power generation capacity, efficiency, cost and response speed of each energy system, and sets corresponding constraints. An optimization algorithm is used to optimize the energy supply distribution. Under the constraints, according to the optimization objectives, such as minimizing the energy supply cost and maximizing the energy utilization efficiency, the optimal energy supply distribution ratio of each energy system is calculated, and the power supply required for photovoltaic power generation, hydropower generation and energy storage systems is determined to form the water-photovoltaic-storage grid-connected energy supply distribution parameters.
[0038] Furthermore, in the method provided in the embodiment of the application, the obtaining of the water-solar-storage grid-connected energy supply allocation parameters further includes:
[0039] Perform energy supply priority analysis on the hydro-photovoltaic storage system to determine the energy supply priority of the hydro-photovoltaic storage; collect and obtain environmental parameter information of the hydro-photovoltaic storage system, calculate the power generation capacity of the hydro-photovoltaic storage system based on the environmental parameter information, and obtain the power generation capacity parameters of the hydro-photovoltaic storage; use the energy supply priority of the hydro-photovoltaic storage and the power generation capacity parameters of the hydro-photovoltaic storage as constraints, use the particle swarm algorithm to optimize the energy supply allocation of the hydro-photovoltaic storage energy deviation parameters, and obtain the grid-connected energy supply allocation parameters of the hydro-photovoltaic storage.
[0040] In an embodiment of the present application, an energy supply priority analysis is first performed to determine the energy supply priority of water, photovoltaic and energy storage. Then, environmental parameter information of the water, photovoltaic and energy storage system is collected through sensors deployed in the system, such as light intensity sensors, temperature sensors, and water level sensors, including data such as solar radiation intensity, temperature and water level. Next, the environmental parameter information is preprocessed to calculate the power generation capacity of the photovoltaic power generation system, the hydropower generation system and the energy storage system. Specifically, the existing photovoltaic cell output power model is used to calculate the real-time output power of photovoltaic power generation; the power calculation formula of hydropower generation is used to calculate the potential output power of hydropower generation. Through the above process, the power generation capacity parameters of the water, photovoltaic and energy storage are obtained.
[0041] Afterwards, the water-photovoltaic storage energy supply priority and the water-photovoltaic storage power generation capacity parameters are used as constraints, and the particle swarm algorithm is used to optimize the energy supply allocation of the water-photovoltaic storage energy deviation parameters. In this process, a group of particles are first randomly initialized in the solution space, and each particle represents a possible energy supply allocation scheme. Each particle contains the energy supply allocation amount of photovoltaic power generation, hydropower generation and energy storage system. The initial position and velocity of the particles are randomly generated, covering the entire solution space. Next, the fitness value is calculated for each particle, and the fitness function is designed to comprehensively evaluate the pros and cons of the energy supply allocation scheme. The fitness function is expressed as:
[0042]
[0043] in, is the energy cost empirical function, is the empirical function of energy efficiency, is the empirical function of response speed, is the weight coefficient, which is preset by technical experts.
[0044] Next, the historical optimal position and global optimal position of the particle are determined based on the calculated fitness, and the position and velocity of each particle are updated to gradually approach the optimal solution. The fitness evaluation and update steps are repeated until the preset number of iterations or fitness threshold is reached, and the optimal energy supply allocation scheme of the water-solar-storage system, that is, the grid-connected energy supply allocation parameters of the water-solar-storage system, is obtained.
[0045] Furthermore, in the method provided in the embodiment of the application, the determining of the priority of water-solar-storage energy supply also includes:
[0046] Obtain energy supply priority factor information, wherein the energy supply priority factor information includes energy reliability, energy supply cost, energy cleanliness and response speed; construct an energy supply priority coordinate system according to the energy supply priority factor information, wherein the energy supply priority coordinate system is a multidimensional coordinate system; evaluate and map the water-solar-storage system based on the energy supply priority coordinate system to obtain a water-solar-storage energy supply vector set; sort the water-solar-storage system for energy supply priority based on the modulus of the water-solar-storage energy supply vector set to determine the water-solar-storage energy supply priority.
[0047] In an embodiment of the present application, the energy supply priority factor information includes energy reliability, energy supply cost, energy cleanliness, and response speed. Energy reliability is defined here as the amount of energy supply reduction affected by the environment. For example, the reliability of photovoltaic power generation is affected by cloud cover and weather conditions, resulting in a reduction in its energy supply. The energy supply cost is the production cost per unit of electrical energy, the energy cleanliness is the carbon emissions of energy, and the response speed is the start-up time and adjustment speed of the photovoltaic power generation system, hydropower generation system, and energy storage system. These data are collected in real time by sensors and monitoring equipment in the system, and combined with historical data analysis to obtain information on each energy supply priority factor.
[0048] Next, the collected information on energy supply priority factors is standardized so that each factor is comparable. For example, the normalization method is used to standardize the values of all factors to a range of 0 to 1. Then an energy supply priority coordinate system is constructed. The energy supply priority coordinate system is a multidimensional coordinate system, and each dimension represents an energy supply priority factor. This multidimensional coordinate system includes four dimensions: energy reliability, energy supply cost, energy cleanliness, and response speed. The performance of each photovoltaic power generation system, hydropower generation system, and energy storage system in these dimensions is mapped to the coordinate system to form an energy supply vector. For example, the standardized performance of photovoltaic power generation in these four dimensions may be 0.6, 0.3, 0.9, and 0.7, respectively, forming a four-dimensional vector. Through the above process, a set of water, light, and energy storage energy supply vectors is obtained.
[0049] Then the modulus of each energy supply vector is calculated to quantify its comprehensive performance in the energy supply priority coordinate system. Vector modulus = ,in , , , Represent the coordinate values of the energy supply vector in each dimension. The smaller the vector modulus, the better the comprehensive performance of the water-solar-storage system in terms of energy supply priority. Based on the modulus of the calculated water-solar-storage energy supply vector set, the water-solar-storage system is prioritized to determine the water-solar-storage energy supply priority.
[0050] Step S400: Perform energy supply control analysis based on the water-solar-storage grid-connected energy supply allocation parameters, determine the water-solar-storage energy supply coordination control parameters, and perform energy closed-loop management and control of the water-solar-storage system through the water-solar-storage energy supply coordination control parameters.
[0051] In the embodiment of the present application, when performing energy supply control analysis, first construct an energy supply parameter space, which contains all possible energy supply control parameter combinations. Then, based on the grid-connected energy supply allocation parameters of water-photovoltaic storage, the energy supply parameter space is parsed and divided to form an energy supply control parameter memory library. By defining the fitness function, each parameter combination in the memory library is searched and evaluated in all directions, the fitness value of each combination is calculated, and multiple parameter combinations with the highest fitness values are selected. Next, based on these parameter combinations with high fitness values, a local optimization analysis is performed. By gradient ascent calculation, the control parameter combination with the largest fitness value is determined. Compare multiple gradient ascent calculation results to select the optimal control parameter optimization direction and step size. According to these optimization directions and step sizes, the energy supply control parameter memory library is further locally optimized, and the coordinated control parameters of water-photovoltaic storage energy supply are finally determined, including specific water pump start-stop parameters, photovoltaic panel orientation and angle adjustment, and energy storage system charge and discharge plan. The coordinated control parameters of water-photovoltaic storage energy supply are used as input control signals, and the various components of the system are adjusted in real time through the intelligent controller to achieve energy closed-loop control of the water-photovoltaic storage system.
[0052] Furthermore, in the method provided in the embodiment of the application, the determination of the coordinated control parameters of water-solar-storage energy supply also includes:
[0053] Construct a water-solar energy storage parameter space, analyze and divide the water-solar energy storage parameter space based on the water-solar energy storage grid-connected energy supply allocation parameters, and obtain a water-solar energy storage control parameter memory bank; perform an omnidirectional search and evaluation in the water-solar energy storage control parameter memory bank through a water-solar energy storage energy supply effect fitness function to obtain multiple parameter energy supply effect fitnesses; perform a local optimization analysis on the water-solar energy storage control parameter memory bank based on the multiple parameter energy supply effect fitnesses to determine the water-solar energy storage coordination control parameters.
[0054] In an embodiment of the present application, a water-photovoltaic storage energy supply parameter space containing all energy supply control parameter combinations is first constructed. This space includes specific control parameters, such as the start and stop parameters of the water pump, the orientation and angle of the photovoltaic panel, the charging and discharging of the energy storage system, etc. Each dimension represents a specific control parameter combination. To achieve this, a discretization method is used to discretize the possible values of each control parameter. For example, the angle of the photovoltaic panel ranges from 0° to 90°, with a value every 5°, for a total of 19 possible values. By combining the possible values of all control parameters, a water-photovoltaic storage energy supply parameter space is generated.
[0055] Next, based on the grid-connected energy supply allocation parameters of hydro-solar-storage, the constructed hydro-solar-storage energy supply parameter space is analyzed and refined. Specifically, data mining technology and rule engines are used to analyze and filter the parameter space. By establishing a rule base, the current system state is matched with the conditions in the rule base to filter out parameter combinations that meet the current conditions. In addition, the constraint satisfaction problem technology is used to further filter the parameter combinations in combination with the physical constraints of the system, such as battery capacity and maximum charge and discharge rate, so as to form a hydro-solar-storage energy supply control parameter memory library.
[0056] Next, the water-solar-energy storage energy supply effect fitness function is used to conduct a full-directional search and evaluation in the water-solar-energy storage energy supply control parameter memory bank. The water-solar-energy storage energy supply effect fitness function is the same as the aforementioned fitness function, but the specific experience function is different. The specific experience function includes the energy supply cost experience function, the energy utilization rate experience function and the system reliability experience function. Each experience function has a different weight and is pre-set by technical experts. The fitness value of each parameter combination is calculated through the fitness function to obtain the fitness of multiple parameter energy supply effects. Finally, based on the fitness of multiple parameter energy supply effects, a local optimization analysis is performed on the water-solar-energy storage energy supply control parameter memory bank to determine the coordinated control parameters of the water-solar-energy storage energy supply.
[0057] Furthermore, in the method provided in the embodiment of the application, the determining of the water-solar-storage energy supply coordination control parameters also includes:
[0058] Based on the fitness of the energy supply effects of the multiple parameters, a gradient ascent calculation is performed to obtain a fitness gradient ascent calculation result; the fitness gradient ascent calculation results are compared and optimized to determine the optimization direction of the control parameters; a local optimization step length is set, and a local optimization is performed on the water-solar-energy storage energy supply control parameter memory bank according to the control parameter optimization direction and the local optimization step length to determine the water-solar-energy storage energy supply coordination control parameters.
[0059] In the embodiment of the present application, first, the fitness of multiple parameter energy supply effects is calculated by gradient ascent, and the control parameters of each dimension are slightly adjusted by the numerical gradient calculation method to calculate the fitness value change of each parameter combination. The gradient value of each dimension is calculated using these changes to obtain the fitness gradient ascent calculation result.
[0060] Next, the results of the fitness gradient increase calculation are compared and optimized. By comparing the gradient values in each direction, the control parameter optimization direction with the fastest fitness improvement is determined. The direction with the largest gradient value is selected as the main optimization direction to ensure that the fitness of the energy supply effect can be improved as quickly as possible when adjusting the control parameters. Then, according to the selected control parameter optimization direction, a suitable step size is selected for further optimization. The step size selection is based on the dynamic step size adjustment algorithm. The initial step size is large, and then gradually reduced to find the optimal point more precisely.
[0061] According to the determined control parameter optimization direction and local optimization step length, the water-solar-storage energy supply control parameter memory library is locally optimized. Specifically, the control parameters are gradually adjusted along the direction of gradient ascent, and new fitness values are continuously calculated and compared. Through multiple iterations and adjustments, the fitness value is gradually improved to ensure that the optimal energy supply control parameter combination is found. Finally, through these steps, the coordinated control parameters of water-solar-storage energy supply are determined.
[0062] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:
[0063] The present application deploys a data perception module in a water-photovoltaic storage system. The data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor. The data perception module monitors and collects the data stream of the water-photovoltaic storage operation status; the load demand of the water-photovoltaic storage system is predicted to obtain the system power demand parameter information, and the water-photovoltaic storage operation status data stream is analyzed in parallel through energy data processing multi-channel to determine the water-photovoltaic storage energy supply parameter information; according to the comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, the water-photovoltaic storage energy deviation parameter is determined, and the water-photovoltaic storage system is analyzed for energy supply distribution based on the water-photovoltaic storage energy deviation parameter to obtain the water-photovoltaic storage grid-connected energy supply distribution parameter; based on the water-photovoltaic storage grid-connected energy supply distribution parameter, energy supply control analysis is performed to determine the water-photovoltaic storage energy supply coordination control parameter, and the water-photovoltaic storage system is controlled by the water-photovoltaic storage energy supply coordination control parameter. The present invention solves the technical problems of the existing technology that there are difficulties in coordinating multiple energy systems and lack of intelligent regulation, and achieves the technical effect of improving the energy utilization efficiency of the water-photovoltaic storage system through real-time monitoring, load demand prediction, and energy supply distribution analysis combined with closed-loop control.
[0064] Embodiment 2
[0065] Based on the same inventive concept as the water-photovoltaic storage smart energy management method in the aforementioned embodiment, Figure 2 As shown, the present application provides a water-solar-storage smart energy management system, and the system and method embodiments in the present application embodiments are based on the same inventive concept. The system includes:
[0066] An operation status data stream acquisition unit 11, wherein the operation status data stream acquisition unit 11 deploys a data perception module in the water-photovoltaic storage system, wherein the data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor, and monitors and acquires the water-photovoltaic storage operation status data stream through the data perception module; an energy supply parallel analysis unit 12, wherein the energy supply parallel analysis unit 12 predicts the load demand of the water-photovoltaic storage system, obtains the system power demand parameter information, performs energy supply parallel analysis on the water-photovoltaic storage operation status data stream through the energy data processing multi-channel, and determines the water-photovoltaic storage energy supply parameter information. information; an energy supply allocation analysis unit 13, the energy supply allocation analysis unit 13 determines the water-photovoltaic storage energy deviation parameter according to the comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, performs energy supply allocation analysis on the water-photovoltaic storage system based on the water-photovoltaic storage energy deviation parameter, and obtains the water-photovoltaic storage grid-connected energy supply allocation parameter; an energy supply control analysis unit 14, the energy supply control analysis unit 14 performs energy supply control analysis based on the water-photovoltaic storage grid-connected energy supply allocation parameter, determines the water-photovoltaic storage energy supply coordination control parameter, and performs energy closed-loop control of the water-photovoltaic storage system through the water-photovoltaic storage energy supply coordination control parameter.
[0067] Furthermore, the system is also used to implement the following functions:
[0068] Acquire information on factors influencing system load, wherein the information on factors influencing system load includes historical load consumption, weather and environmental conditions, and standby regulation requirements; classify and identify a historical load data set of a water-solar-energy storage system based on the information on factors influencing system load, and obtain a system load factor data set; perform sequence division on the system load factor data set according to a preset time window, and obtain a system factor sequence load data set; use a recurrent neural network structure to train and fuse the system factor sequence load data set, and construct a system load prediction network; perform load demand prediction on the water-solar-energy storage system based on the system load prediction network, and obtain the system power demand parameter information.
[0069] Furthermore, the system is also used to implement the following functions:
[0070] According to the water-photovoltaic-storage system, a photovoltaic power generation data processing channel, a hydroelectric power generation data processing channel and an energy storage system data processing channel are determined; an energy supply data set of the water-photovoltaic-storage system is collected and acquired, and energy supply analysis training is performed on the energy supply data set of the water-photovoltaic-storage system using a deep neural network structure to obtain a photovoltaic power generation energy supply analysis network, a hydroelectric power generation energy supply analysis network and an energy storage system energy supply analysis network; the photovoltaic power generation energy supply analysis network, the hydroelectric power generation energy supply analysis network and the energy storage system energy supply analysis network are respectively configured for the photovoltaic power generation data processing channel, the hydroelectric power generation data processing channel and the energy storage system data processing channel to construct the energy data processing multi-channel; based on the energy data processing multi-channel, the water-photovoltaic-storage operation status data stream is mapped and analyzed in parallel to determine the water-photovoltaic-storage energy supply parameter information.
[0071] Furthermore, the system is also used to implement the following functions:
[0072] Perform energy supply priority analysis on the hydro-photovoltaic storage system to determine the energy supply priority of the hydro-photovoltaic storage; collect and obtain environmental parameter information of the hydro-photovoltaic storage system, calculate the power generation capacity of the hydro-photovoltaic storage system based on the environmental parameter information, and obtain the power generation capacity parameters of the hydro-photovoltaic storage; use the energy supply priority of the hydro-photovoltaic storage and the power generation capacity parameters of the hydro-photovoltaic storage as constraints, use the particle swarm algorithm to optimize the energy supply allocation of the hydro-photovoltaic storage energy deviation parameters, and obtain the grid-connected energy supply allocation parameters of the hydro-photovoltaic storage.
[0073] Furthermore, the system is also used to implement the following functions:
[0074] Obtain energy supply priority factor information, wherein the energy supply priority factor information includes energy reliability, energy supply cost, energy cleanliness and response speed; construct an energy supply priority coordinate system according to the energy supply priority factor information, wherein the energy supply priority coordinate system is a multidimensional coordinate system; evaluate and map the water-solar-storage system based on the energy supply priority coordinate system to obtain a water-solar-storage energy supply vector set; sort the water-solar-storage system for energy supply priority based on the modulus of the water-solar-storage energy supply vector set to determine the water-solar-storage energy supply priority.
[0075] Furthermore, the system is also used to implement the following functions:
[0076] Construct a water-solar energy storage parameter space, analyze and divide the water-solar energy storage parameter space based on the water-solar energy storage grid-connected energy supply allocation parameters, and obtain a water-solar energy storage control parameter memory bank; perform an omnidirectional search and evaluation in the water-solar energy storage control parameter memory bank through a water-solar energy storage energy supply effect fitness function to obtain multiple parameter energy supply effect fitnesses; perform a local optimization analysis on the water-solar energy storage control parameter memory bank based on the multiple parameter energy supply effect fitnesses to determine the water-solar energy storage coordination control parameters.
[0077] Furthermore, the system is also used to implement the following functions:
[0078] Based on the fitness of the energy supply effects of the multiple parameters, a gradient ascent calculation is performed to obtain a fitness gradient ascent calculation result; the fitness gradient ascent calculation results are compared and optimized to determine the optimization direction of the control parameters; a local optimization step length is set, and a local optimization is performed on the water-solar-energy storage energy supply control parameter memory bank according to the control parameter optimization direction and the local optimization step length to determine the water-solar-energy storage energy supply coordination control parameters.
[0079] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0080] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
[0081] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.
Claims
1. A method for managing water-solar-storage smart energy. It is characterized in that The method comprises: Deploy a data perception module in the water-solar storage system, wherein the data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor, and monitors and collects the water-solar storage operation status data stream through the data perception module; Carry out load demand forecasting for the water-solar-energy storage system to obtain system power demand parameter information, perform energy supply parallel analysis on the water-solar-energy storage operation status data stream through energy data processing multi-channels to determine water-solar-energy storage energy supply parameter information; Determine the water-photovoltaic storage energy deviation parameter according to the comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, perform energy supply allocation analysis on the water-photovoltaic storage system based on the water-photovoltaic storage energy deviation parameter, and obtain the water-photovoltaic storage grid-connected energy supply allocation parameter; Perform energy supply control analysis based on the water-solar-storage grid-connected energy supply allocation parameters, determine the water-solar-storage energy supply coordination control parameters, and perform energy closed-loop control of the water-solar-storage system through the water-solar-storage energy supply coordination control parameters; Among them, the coordinated control parameters of water, photovoltaic, storage and energy supply are determined, including: Constructing a water-solar-energy storage energy supply parameter space, analyzing and dividing the water-solar-energy storage energy supply parameter space based on the water-solar-energy storage grid-connected energy supply allocation parameters, and obtaining a water-solar-energy storage energy supply control parameter memory library; Through the water-solar energy storage power supply effect fitness function, an all-directional search and evaluation is performed in the water-solar energy storage power supply control parameter memory library to obtain the fitness of multiple parameter power supply effects; Based on the fitness of the energy supply effects of the multiple parameters, a local optimization analysis is performed on the water-solar-energy storage energy supply control parameter memory bank to determine the water-solar-energy storage energy supply coordination control parameters; Determining the coordinated control parameters of the water-solar-storage energy supply includes: Performing a gradient rise calculation based on the fitness of the energy supply effects of the multiple parameters to obtain a fitness gradient rise calculation result; Compare and optimize the fitness gradient ascent calculation results to determine the optimization direction of the control parameters; The local optimization step length is set, and the water-solar-storage energy supply control parameter memory library is locally optimized according to the control parameter optimization direction and the local optimization step length to determine the water-solar-storage energy supply coordination control parameters.
2. A water-solar-energy storage smart energy management method as claimed in claim 1, It is characterized in that The obtaining of system power demand parameter information includes: Acquiring information on system load influencing factors, wherein the system load influencing factor information includes historical load consumption, weather and environmental conditions, and standby regulation requirements; Classify and identify the historical load data set of the hydro-photovoltaic-storage system based on the system load influencing factor information to obtain a system load factor data set; Sequentially dividing the system load factor data set according to a preset time window to obtain a system factor sequence load data set; Using a recurrent neural network structure to train and fuse the system factor sequence load data set to build a system load prediction network; The load demand of the water-solar-energy storage system is predicted based on the system load prediction network to obtain the system power demand parameter information.
3. A water-solar-energy storage smart energy management method as claimed in claim 1, It is characterized in that The determination of water-solar-storage energy supply parameter information includes: According to the water-photovoltaic-storage system, a photovoltaic power generation data processing channel, a hydropower generation data processing channel and an energy storage system data processing channel are determined; Collect and obtain a water-photovoltaic-storage system energy supply data set, use a deep neural network structure to perform energy supply analysis training on the water-photovoltaic-storage system energy supply data set, and obtain a photovoltaic power generation energy supply analysis network, a hydropower power generation energy supply analysis network, and an energy storage system energy supply analysis network; The photovoltaic power generation energy supply analysis network, the hydropower power generation energy supply analysis network and the energy storage system energy supply analysis network are configured to the photovoltaic power generation data processing channel, the hydropower power generation data processing channel and the energy storage system data processing channel respectively to construct the energy data processing multi-channel; Based on the energy data processing multi-channel, the water-solar-energy storage operation status data stream is mapped and analyzed in parallel to determine the water-solar-energy storage energy supply parameter information.
4. A water-solar-energy storage smart energy management method as claimed in claim 1, It is characterized in that The obtaining of the water-solar-storage grid-connected energy supply allocation parameters comprises: Performing an energy supply priority analysis on the water-solar-storage system to determine the energy supply priority of the water-solar-storage system; Collect and obtain environmental parameter information of the water-photovoltaic storage system, calculate the power generation capacity of the water-photovoltaic storage system based on the environmental parameter information, and obtain the water-photovoltaic storage power generation capacity parameters; The water-solar-storage energy supply priority and the water-solar-storage power generation capacity parameters are used as constraints, and the particle swarm algorithm is used to optimize the energy supply allocation of the water-solar-storage energy deviation parameters to obtain the water-solar-storage grid-connected energy supply allocation parameters.
5. A water-solar-storage intelligent energy management method as claimed in claim 4, It is characterized in that Determining the priority of water, solar, and energy storage includes: Acquiring energy supply priority factor information, wherein the energy supply priority factor information includes energy reliability, energy supply cost, energy cleanliness, and response speed; According to the energy supply priority factor information, an energy supply priority coordinate system is constructed, and the energy supply priority coordinate system is a multi-dimensional coordinate system; Based on the energy supply priority coordinate system, the water-solar-storage system is evaluated and mapped to obtain a water-solar-storage energy supply vector set; The energy supply priority of the water-solar-storage system is sorted based on the modulus of the water-solar-storage energy supply vector set to determine the water-solar-storage energy supply priority.
6. A water-solar-storage smart energy management system, It is characterized in that The system comprises: An operation status data stream acquisition unit, wherein the operation status data stream acquisition unit deploys a data perception module in the water-photovoltaic storage system, wherein the data perception module integrates a water level sensor, a light intensity sensor, a temperature sensor, and a current and voltage sensor, and monitors and acquires the water-photovoltaic storage operation status data stream through the data perception module; An energy supply parallel analysis unit, which predicts the load demand of the water-solar-energy storage system, obtains system power demand parameter information, and performs energy supply parallel analysis on the water-solar-energy storage operation status data stream through energy data processing multi-channel to determine the water-solar-energy storage energy supply parameter information; An energy distribution analysis unit, which determines a water-photovoltaic storage energy deviation parameter according to a comparison difference between the water-photovoltaic storage energy supply parameter information and the system power demand parameter information, and performs energy distribution analysis on the water-photovoltaic storage system based on the water-photovoltaic storage energy deviation parameter to obtain a water-photovoltaic storage grid-connected energy distribution parameter; An energy supply control and analysis unit, which performs energy supply control analysis based on the water-solar-storage grid-connected energy supply allocation parameters, determines water-solar-storage energy supply coordination control parameters, and performs energy closed-loop control of the water-solar-storage system through the water-solar-storage energy supply coordination control parameters; The energy supply control and analysis unit is also used to implement the following steps: Constructing a water-solar-energy storage energy supply parameter space, analyzing and dividing the water-solar-energy storage energy supply parameter space based on the water-solar-energy storage grid-connected energy supply allocation parameters, and obtaining a water-solar-energy storage energy supply control parameter memory library; Through the water-solar energy storage power supply effect fitness function, an all-directional search and evaluation is performed in the water-solar energy storage power supply control parameter memory library to obtain the fitness of multiple parameter power supply effects; Based on the fitness of the energy supply effects of the multiple parameters, a local optimization analysis is performed on the water-solar-energy storage energy supply control parameter memory bank to determine the water-solar-energy storage energy supply coordination control parameters; Determining the coordinated control parameters of the water-solar-storage energy supply includes: Performing a gradient rise calculation based on the fitness of the energy supply effects of the multiple parameters to obtain a fitness gradient rise calculation result; Compare and optimize the fitness gradient ascent calculation results to determine the optimization direction of the control parameters; The local optimization step length is set, and the water-solar-storage energy supply control parameter memory library is locally optimized according to the control parameter optimization direction and the local optimization step length to determine the water-solar-storage energy supply coordination control parameters.
Citation Information
Patent Citations
Intelligent control method and system for wind-solar-diesel storage unit-level energy storage
CN117996816A
Hydro-photovoltaic complementary operation chart application method for clean energy base
US20240047971A1
Self-healing reconfiguration planning method and apparatus for power distribution network, and terminal
WO2022179302A1
Multi-energy capacity optimization configuration method for wind-solar-water-fire storage system
WO2023274425A1
