System energy regulation and control method and device combined with solar power supply
By collecting and analyzing electricity consumption needs, weather information, and the location and life of the power generation unit, and optimizing the energy regulation plan, the complexity of solar power generation and low energy storage efficiency are solved, and efficient energy regulation and extended life of energy storage equipment are achieved.
Patent Information
- Application Number
- CN202411056369.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-08
AI Technical Summary
The existing technology relies on historical data analysis and prediction, and is difficult to meet the complexity and uncertainty of solar power generation, resulting in the difficulty of achieving high-precision energy regulation demand and low energy storage technology efficiency.
By collecting electricity demand, conventional and temporary weather information, combining the location and energy storage life of the power generation unit, a power generation power array is built, and energy regulation plans are optimized to improve the efficiency of energy storage equipment.
It has achieved decision-making and energy regulation based on weather changes, improved the efficiency and energy utilization rate of energy storage equipment, and met the needs of high-precision energy regulation.
Smart Images

Figure CN118917615A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of energy regulation technology, and specifically to a system energy regulation method and device combined with solar energy power supply. Background Art
[0002] Solar photovoltaic systems use solar energy to convert light energy into electrical energy. They have the advantages of being pollution-free, renewable, and energy-sufficient, and are of great significance in alleviating global climate change and the depletion of traditional energy resources. However, due to the instability and variability of solar power generation, it is difficult to stably supply enough electricity in the actual operation of photovoltaic power, which poses a challenge to the supply and demand balance of the power grid.
[0003] In summary, existing technologies rely on the analysis and prediction of historical data, and solar power generation is complex and uncertain, making it difficult to meet the needs of high-precision energy regulation. Existing energy storage technologies also have the technical problem of low efficiency. Summary of the invention
[0004] Based on this, it is necessary to provide a system energy control method and equipment combined with solar power supply to address the above-mentioned technical problems. This can solve the problems that the existing technology relies on the analysis and prediction of historical data, and that solar power generation is complex and uncertain, making it difficult to meet the needs of high-precision energy control. The existing energy storage technology has the technical problem of low efficiency. Energy control decisions are made based on weather trends, and the technical effect of improving the efficiency of energy storage equipment is achieved by considering energy demand, energy storage life, and time technology.
[0005] In a first aspect, a system energy control method combined with solar power supply is provided, the method comprising: collecting electricity demand data in historical time, and predicting electricity demand to obtain multiple predicted electricity demand information in multiple future time periods; indexing conventional weather parameter information based on a current timestamp to obtain multiple conventional weather information in multiple future time periods, and collecting temporary weather data in historical time, predicting temporary weather information, and obtaining multiple temporary weather information in multiple future time periods; collecting energy storage life information of multiple energy storage units corresponding to multiple power generation units in a solar power generation system, and performing power generation analysis based on the multiple conventional weather information and multiple temporary weather information, combined with multiple location information of multiple power generation units, to construct multiple power generation arrays; optimizing energy control schemes for the multiple future time periods based on the multiple predicted electricity demand information, the multiple power generation arrays, and the multiple energy storage life information to obtain an optimal energy control scheme, wherein the optimal energy control scheme includes multiple optimal time period energy control schemes, each of which includes a power generation unit that performs functions and stores energy in each time period; using the optimal energy control scheme, energy control is performed in the multiple future time periods.
[0006] In a second aspect, a system energy control device combined with solar power supply is provided, the device comprising: an electricity demand prediction module, the electricity demand prediction module is used to collect electricity demand data in historical time, and perform electricity demand prediction, and obtain multiple predicted electricity demand information in multiple future time periods; a regular weather information acquisition module, the regular weather information acquisition module is used to index regular weather parameter information based on a current timestamp, obtain multiple regular weather information in multiple future time periods, and collect temporary weather data in historical time, perform temporary weather information prediction, and obtain multiple temporary weather information in multiple future time periods; a power generation analysis module, the power generation analysis module is used to collect energy storage life of multiple energy storage units corresponding to multiple power generation units in a solar power generation system information, and based on the multiple conventional weather information and multiple temporary weather information, combined with multiple location information of multiple power generation units, perform power generation analysis and construct multiple power generation arrays; an optimal energy control scheme acquisition module, the optimal energy control scheme acquisition module is used to optimize the energy control schemes for the multiple future time periods according to the multiple predicted electricity demand information, multiple power generation arrays and multiple energy storage life information, and obtain the optimal energy control scheme, wherein the optimal energy control scheme includes multiple optimal time period energy control schemes, each optimal time period energy control scheme includes power generation units that perform functions and store energy in each time period; an energy control module, the energy control module is used to adopt the optimal energy control scheme to perform energy control in the multiple future time periods.
[0007] According to a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to the first aspect when executing the computer program.
[0008] The above-mentioned system energy control method and equipment combined with solar power supply solves the problem that the existing technology relies on the analysis and prediction of historical data, and solar power generation has complexity and uncertainty, and it is difficult to meet the needs of high-precision energy control. The existing energy storage technology has the technical problem of low efficiency. Energy control decisions are made according to weather trends, and the technical effect of improving the efficiency of energy storage equipment is achieved by considering energy demand, energy storage life and time technology.
[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1A schematic diagram of a flow chart of a system energy control method combined with solar power supply in one embodiment;
[0011] Figure 2 A schematic diagram of a process for obtaining predicted electricity demand information in a system energy control method combined with solar power supply in one embodiment;
[0012] Figure 3 It is a structural block diagram of a system energy control device combined with solar power supply in one embodiment.
[0013] Explanation of the reference numerals: electricity demand prediction module 11 , conventional weather information acquisition module 12 , power generation analysis module 13 , optimal energy regulation scheme acquisition module 14 , energy regulation module 15 . DETAILED DESCRIPTION
[0014] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0015] like Figure 1 As shown, the present application provides a system energy control method combined with solar power supply, the method comprising:
[0016] Collect electricity demand data over historical time periods and make electricity demand forecasts to obtain multiple predicted electricity demand information for multiple future time periods.
[0017] A solar power supply system is a green energy system that converts solar energy into electrical energy. Its core components include solar cell groups, solar controllers, batteries (groups), etc. System energy regulation refers to the planned and purposeful control and regulation of the energy acquisition, conversion, storage, distribution and use processes in an energy supply and use system to achieve efficient energy utilization, reduce waste, meet user needs and comply with environmental protection requirements. In a solar power supply system, it involves how to maximize the use of solar energy resources, ensure stable operation of the system, and meet user energy needs at different times and under different load conditions. The present application provides a system energy regulation method combined with solar power supply, which significantly improves the energy utilization, stability and intelligence of the solar power supply system, and makes a positive contribution to the development of sustainable energy.
[0018] Use smart meters or power grid monitoring systems to collect electricity consumption data in real time or at regular intervals over historical time. These data can include daily electricity consumption, monthly electricity consumption, quarterly electricity consumption, and related parameters such as voltage, current, and power factor, i.e., historical electricity consumption data. Based on historical electricity consumption data, select appropriate prediction methods to predict electricity demand, and obtain multiple electricity demand information in multiple time periods in the future. Through the above method, the electricity demand for power supply directly through the solar power generation system in the historical time is collected, and then the electricity demand in multiple time periods in the future is predicted, which lays the foundation for subsequent system energy scheduling.
[0019] like Figure 2 As shown, based on the electricity consumption data records at the electricity consumption end in the solar power generation system, a set of sample electricity demand information sequences is collected, and a set of sample predicted electricity demand information sequences is collected; the sample electricity demand information sequence set and the sample predicted electricity demand information sequence set are used to train a power demand predictor; historical electricity demand information sequences within a historical time are collected; the power demand predictor is used to perform power demand forecasting on the historical electricity demand information sequences to obtain a predicted electricity demand information sequence, which is divided according to multiple future time periods to obtain multiple predicted electricity demand information.
[0020] Collect electricity consumption data records in the historical time from the electricity consumption end of the solar power generation system. These records should include the actual electricity demand information at each time point. From the collected electricity consumption data records, extract a sample electricity demand information sequence set, which includes electricity demand data in the past period of time, for training the prediction model. If there is available prediction data, such as electricity demand based on other models or expert predictions, these data can also be collected as a sample prediction electricity demand information sequence set. These prediction data will be used as labels or target values for prediction model training. Use the preprocessed sample electricity demand information sequence set and the sample prediction electricity demand information sequence set to train a power demand predictor. This predictor can be a machine learning model or a deep learning model, such as a neural network. During the training process, the prediction performance can be optimized by adjusting the parameters and structure of the model. Collect the historical electricity demand information sequence of the solar power generation system in the historical time. This sequence should contain a time range and format similar to the training data set. Use the trained electricity demand predictor to predict the collected historical electricity demand information sequence to obtain the predicted electricity demand information sequence. According to actual needs, the prediction results can be divided into multiple future time periods, such as 24 hours a day, 7 days a week, etc., to obtain the predicted electricity demand information for each time period, that is, to obtain multiple predicted electricity demand information. Through the above method, the solar power generation system can adjust its power generation plan, energy storage strategy, etc. to better meet the electricity demand and optimize energy utilization.
[0021] Based on the current timestamp, regular weather parameter information is indexed to obtain multiple regular weather information in multiple future time periods, and temporary weather data in historical time is collected to predict temporary weather information and obtain multiple temporary weather information in multiple future time periods.
[0022] Get the current timestamp and use it as a benchmark to determine the future time range that needs to be queried or predicted. Index regular weather information based on time. Regular weather is only related to time. For example, the sunshine intensity at a certain time of a day in a year without cloud cover belongs to sunshine data that only changes with time. And predict future temporary weather information based on historical temporary weather data. Temporary weather data refers to sudden and unconventional weather events such as storms, hail, lightning, etc. Temporary weather information is temporary weather information that changes temporarily, such as rain, cloudy, overcast, etc., which belongs to meteorological data. Based on the collected historical temporary weather data, use machine learning or statistical models to predict temporary weather information. Analyze the frequency, intensity, duration and other meteorological parameters of weather events in historical data, select the electricity demand predictor, and predict temporary weather information in multiple future time periods based on the current timestamp and regular weather information. The prediction of temporary weather information is usually more challenging than the prediction of regular weather information because temporary weather events often have higher uncertainty and complexity.
[0023] Acquire the timestamp information of the current time point; perform indexing in the regular weather change table according to the timestamp information to obtain multiple regular weather information in multiple future time periods, wherein the regular weather change table includes the index relationship between time and regular weather; collect historical temporary weather information sequences within the historical time; based on the temporary weather monitoring data records, collect a sample temporary weather information set, and collect a sample predicted temporary weather information sequence set to train a temporary weather predictor; use the temporary weather predictor to predict the historical temporary weather information sequence to obtain a predicted temporary weather information sequence, and obtain multiple temporary weather information according to the multiple future time periods.
[0024] Use the time library in the programming language to obtain the timestamp of the current time point, index the regular weather change table to obtain future regular weather information, use the current timestamp as the starting point, and index multiple future time periods in the regular weather change table, such as regular weather information for the next 24 hours, the next 7 days, etc. Collect temporary weather information sequences in the past period from a historical database or data source. Temporary weather information refers to sudden, unconventional weather events, such as storms, hail, lightning, etc. Based on temporary weather monitoring data records, collect sample temporary weather information sets, including actual observed temporary weather events and their related parameters. Collect sample predicted temporary weather information sequence sets, and use the sample predicted temporary weather information sequence sets to train a temporary weather predictor. The predictor can be a model based on statistical models, machine learning, or deep learning. Select a suitable model architecture and parameters, and use training data to train the model, then evaluate the model performance of the temporary weather predictor and adjust the parameters based on the sample predicted temporary weather information sequence set, and use the trained temporary weather predictor to predict the previously collected historical temporary weather information sequence. Using the trained temporary weather predictor, temporary weather information for multiple future time periods is predicted based on the current timestamp and regular weather information. The prediction results should include possible temporary weather events and their related parameters in each future time period. The prediction results are divided into multiple future time periods, and temporary weather information for each time period is extracted. Through the above method, multiple temporary weather information is obtained, which provides a basis for subsequent resource and energy scheduling.
[0025] The energy storage life information of multiple energy storage units corresponding to multiple power generation units in the solar power generation system is collected, and based on the multiple conventional weather information and multiple temporary weather information, combined with multiple location information of multiple power generation units, power generation power analysis is performed to construct multiple power generation arrays.
[0026] Solar power generation systems are usually equipped with energy storage units, such as battery packs, to store excess energy for use during non-sunny periods. Energy storage life information refers to the duration and efficiency of these energy storage units in storing and releasing electrical energy. The location information of the power generation unit includes the latitude and longitude, altitude, and orientation of the power generation unit, such as the solar panel. This information is essential for analyzing the lighting conditions and power generation efficiency at different locations. It can be obtained through a geographic information system or a global positioning system. The power generation analysis is performed by combining the energy storage life information, regular weather information, temporary weather information, and the location information of the power generation unit. This includes predicting the light intensity, shadow shading, temperature effects, etc. of each power generation unit under different weather conditions, so as to estimate the power generation of each power generation unit. Light intensity is one of the main factors affecting power generation. In addition, shadow shading, temperature effects, the state of the energy storage unit, etc. will also affect the power generation. The power generation array is a two-dimensional or three-dimensional data structure used to represent the distribution of power generation at different times and locations. Each element represents the power generation of a power generation unit at a specific time and under specific conditions. The construction method includes arranging the power generation of each power generation unit according to time, such as hours and days, and location, such as longitude and latitude, according to the results of power generation analysis to construct a power generation array. According to the above method, by analyzing the power generation array, inefficient or redundant parts in the system can be identified, so as to carry out targeted optimization and improvement. The power generation array can be used as an input of the energy management system to predict and schedule the energy production and consumption of the system. By monitoring abnormal changes in power generation, potential faults in the system can be discovered in a timely manner, and early warnings and repairs can be carried out.
[0027] According to the power generation data logs of multiple power generation units, multiple sample regular weather information sets, multiple sample temporary weather information sets and multiple sample power generation sets are collected; the multiple sample regular weather information sets, multiple sample temporary weather information sets and multiple sample power generation sets are respectively used to train to obtain multiple power generation prediction branches, obtain a power generation predictor, and perform power generation prediction on the multiple regular weather information and multiple temporary weather information respectively to obtain multiple predicted power generation sets; collect multiple location information of the multiple power generation units, and construct multiple power generation arrays in combination with the multiple predicted power generation sets.
[0028] Collect power generation data from historical power generation data logs of multiple power generation units, collect regular weather information corresponding to the timestamps of the power generation data, and form multiple sample regular weather information sets. Collect temporary weather information corresponding to the timestamps of the power generation data to form multiple sample temporary weather information sets. Extract power generation data corresponding to the weather information timestamps from the power generation data logs to form multiple sample power generation sets. Preprocess the collected sample weather information sets and sample power generation sets, and extract meaningful features based on the characteristics of the power generation units and the impact of weather information on power generation. This may include regular weather features such as temperature, humidity, wind speed, wind direction, and signs of whether temporary weather events have occurred. Select a suitable machine learning or deep learning model to build a power generation predictor, and use the sample regular weather information set and the corresponding sample power generation set to train one or more power generation prediction branches under regular weather conditions. Use the sample temporary weather information set and the corresponding sample power generation set to train one or more power generation prediction branches under temporary weather conditions. Use the validation set to evaluate the trained prediction branches, and make necessary optimizations and adjustments based on the evaluation results. Multiple regular weather information and multiple temporary weather information are used as inputs to the trained power generation predictor, and the input weather information is predicted using the power generation predictor to obtain multiple predicted power generation sets. Multiple location information of multiple power generation units is collected, such as longitude and latitude, altitude, orientation, etc., and the location information of each power generation unit is combined with the corresponding predicted power generation. A two-dimensional or three-dimensional power generation array is constructed based on the location information and predicted power generation. Each element represents the predicted power generation of a power generation unit at a specific location and time. By monitoring abnormal changes in the power generation array, potential faults in the system can be discovered in a timely manner, and early warnings and repairs can be carried out.
[0029] According to the multiple predicted electricity demand information, multiple power generation arrays and multiple energy storage life information, the energy control plans for the multiple future time periods are optimized to obtain an optimal energy control plan, wherein the optimal energy control plan includes multiple optimal time period energy control plans, and each optimal time period energy control plan includes a power generation unit that performs functions and stores energy in each time period.
[0030] Each array in the power generation array set contains power generation at different time periods and locations, and a collection of energy storage life information, which may include the remaining capacity of the energy storage unit, the charging and discharging efficiency, etc. The objective function should reflect the total cost, efficiency or reliability of the energy control scheme. For example, it can be to minimize energy waste, maximize energy self-sufficiency, or minimize energy storage unit loss. Define constraints, the power generation should meet or exceed the predicted power demand, and the charging and discharging of the energy storage unit should be within its life and efficiency limits. There may be other operational or physical constraints to obtain the optimal energy control scheme. Optimization algorithms such as linear programming, integer programming, dynamic programming, and genetic algorithms can be used to analyze the optimization results to ensure that they meet all constraints and evaluate their performance, including multiple optimal time period energy control schemes, each of which includes power generation units that perform functions and store energy in each time period. Through the above method, the optimal energy control scheme is obtained, and according to the multiple optimal time period energy control schemes, it is helpful to improve energy utilization efficiency, reduce operating costs, and extend the life of energy storage units.
[0031] Construct an energy control function for optimizing energy control schemes in multiple time periods, as follows:
[0032]
[0033] Among them, ERF is the regulation fitness, w1 and w2 are weights, M is the number of power generation units used for power supply, N is the number of power generation units used for energy storage, K i is the power generation ranking of the i-th power generation unit supplying power within the energy control plan of the time period, Z is the number of multiple power generation units, the sum of M and N is Z, T j is the energy storage life information of the i-th energy storage unit in the energy control scheme of the time period, T z The energy storage life information is preset; based on the energy control function, in the first future time period among multiple future time periods, according to the first predicted electricity demand information, the first power generation power array and multiple energy storage life information, the time period energy storage control plan is optimized to obtain the first optimal time period energy control plan; the time period energy control plans of other multiple future time periods are continuously optimized to obtain multiple optimal time period energy control plans as the optimal energy control plan.
[0034] Construct an energy control function for optimizing energy control schemes in multiple time periods, as follows:
[0035]
[0036] Among them, ERF is the regulation fitness, which is the target value to be optimized. The larger the value, the better the solution. w1 and w2 are weights, which are the weights of the ranking of power generation and energy storage life information, respectively, to balance the importance of the two in the optimization process. Their values can be adjusted according to actual needs. M is the number of power generation units used for power supply, N is the number of power generation units used for energy storage, and K is the number of power generation units used for energy storage. i is the power generation ranking of the i-th power generation unit supplying power within the energy control plan of the time period, Z is the number of multiple power generation units, the sum of M and N is Z, T j T is the energy storage life information of the i-th energy storage unit in the energy control scheme for the time period, which can usually be expressed as the percentage of the energy storage unit's used life or the estimated value of its remaining life. z To preset the energy storage life information, usually a reference value, such as the design life or expected remaining life of the energy storage unit, for the first future period, according to the first predicted electricity demand information, the first power generation array (i.e., the predicted power generation of each power generation unit in the period) and multiple energy storage life information, calculate the ERF value of each possible time period energy control scheme. From all possible time period energy control schemes, select the scheme with the largest ERF value as the first optimal time period energy control scheme. Repeat the above steps to optimize the time period energy control schemes for other multiple future time periods to obtain the optimal time period energy control scheme for each time period. Combine all the optimal time period energy control schemes to form a complete optimal energy control scheme. Through the above method, it is ensured that the energy control scheme can achieve higher efficiency and longer energy storage unit life in multiple future time periods, thereby achieving global optimal energy control.
[0037] In the first power generation array, several power generation units are randomly selected to supply power, and other power generation units are used to store energy, to generate multiple energy control schemes for initial time periods, wherein the sum of the power generation powers of the several power generation units that supply power is greater than or equal to the first predicted electricity demand information; according to the first power generation array and multiple energy storage life information, based on the energy control function, multiple initial control fitness of the multiple initial time period energy control schemes are analyzed and calculated; according to the multiple initial control fitness, the multiple initial time period energy control schemes are optimized and updated to obtain multiple updated time period energy control schemes, and then optimized; the optimization is continued until convergence to obtain multiple convergence time period energy control schemes, and the convergence time period energy control scheme with the largest control fitness is output to obtain the first optimal time period energy control scheme.
[0038] In the first power generation array, several power generation units are randomly selected for power supply, ensuring that the sum of the power generation of these power generation units is greater than or equal to the first predicted power demand information, and the remaining power generation units are set to perform energy storage mode. This process is repeated to generate multiple different energy control schemes for initial time periods. For each initial time period energy control scheme, the energy control function is used to calculate its initial control fitness. Based on the initial control fitness, several time period energy control schemes with lower fitness are selected for optimization and update. The optimization and update method can be to randomly adjust the power supply / energy storage state of some power generation units, or to use heuristic search algorithms such as genetic algorithms and simulated annealing algorithms to find a better solution. For each updated time period energy control scheme, its control fitness is recalculated. Repeat the optimization and update process, and each iteration improves the time period energy control scheme based on the current control fitness. As the iteration proceeds, the control fitness of the time period energy control scheme will gradually increase and tend to be stable, that is, converge. When the preset convergence conditions are met, such as the control fitness does not change much for multiple consecutive iterations, the maximum number of iterations is reached, etc., the iteration is stopped. Among all the converged time period energy control schemes, the one with the largest control fitness is selected as the first optimal time period energy control scheme. The scheme is output, including a list of power generation units for power supply, a list of power generation units for energy storage, and corresponding control parameters. Through the above method, the optimal energy control scheme can be found in the first future period, ensuring that the power supply demand is met while also extending the life of the energy storage unit as much as possible and optimizing energy utilization efficiency.
[0039] According to the multiple initial control fitnesses, the multiple initial time period energy control schemes are divided to obtain the stage optimal solution and multiple stage common solutions; with the stage optimal solution as the adjustment direction, a preset adjustment quantity is used to adjust and update the power generation units that generate electricity or store energy in other multiple stage common solutions to obtain multiple updated time period energy control schemes; according to the first power generation power array and multiple energy storage life information, based on the energy control function, analyze and calculate to obtain multiple updated control fitnesses of the multiple updated time period energy control schemes; according to the multiple updated control fitnesses, the stage optimal solution and the multiple stage common solutions are distinguished and updated, and the optimization is continued.
[0040] According to the initial regulation fitness, multiple energy regulation schemes for the initial period are sorted, the scheme with the highest fitness is selected as the optimal solution for the stage, and other schemes are regarded as ordinary solutions for the stage. A preset adjustment number is set, and the number of adjustments borrowed from the optimal solution for the stage and applied to the ordinary solution for the stage is defined. For each ordinary solution for the stage, the power generation unit for power generation or energy storage is adjusted according to the optimal solution for the stage. This can be done by random selection, local search or other heuristic algorithms. For example, a power generation unit can be randomly selected. If the unit is in the power supply state in the optimal solution for the stage, it is also set to the power supply state in the ordinary solution for the stage. The adjustment process is repeated until the preset adjustment number is reached, and one or more energy regulation schemes for the updated period are generated for each ordinary solution for the stage. For each energy regulation scheme for the updated period, the first power generation array and multiple energy storage life information are used to calculate its updated regulation fitness based on the energy regulation function. According to the updated regulation fitness, the optimal solution for the stage and the ordinary solution for the stage are re-evaluated. If the fitness of the energy regulation scheme for a certain updated period is higher than the optimal solution for the current stage, the optimal solution for the stage is updated. For the ordinary solution for the stage, it can be sorted or selected according to the new fitness for further optimization in subsequent iterations. If the optimization termination condition is reached, such as the maximum number of iterations, the fitness improvement is less than the threshold, etc., the optimization is stopped, otherwise it returns to continue the optimization. Through the advantages of clear optimization goals, iterative optimization, heuristic search and easy implementation, an effective and flexible solution is provided for the optimization of time-slot energy control schemes.
[0041] The optimal energy regulation scheme is adopted to perform energy regulation in the multiple future time periods.
[0042] After determining the optimal energy control scheme, energy control can be carried out in multiple time periods in the future according to the scheme. It involves the control of power generation units, energy storage equipment, etc. to ensure the balance between energy supply and demand, while optimizing energy efficiency and cost. Through the above method, the use of the optimal energy control scheme for energy control in multiple time periods in the future has the advantages of high optimization efficiency, high reliability, good cost-effectiveness, strong flexibility, high predictability, high degree of automation and strong sustainability. It helps to achieve the rational use of energy and improve the overall performance and economic benefits of the system.
[0043] like Figure 3 As shown, the embodiment of the present application includes a system energy control device combined with solar power supply, and the device includes:
[0044] The power demand forecasting module 11 is used to collect power demand data in the historical period, and forecast the power demand to obtain a plurality of forecast power demand information in a plurality of future periods;
[0045] A conventional weather information acquisition module 12, wherein the conventional weather information acquisition module 12 is used to index conventional weather parameter information based on a current timestamp, obtain multiple conventional weather information in multiple future time periods, collect temporary weather data in a historical time period, perform temporary weather information forecasting, and obtain multiple temporary weather information in multiple future time periods;
[0046] A power generation analysis module 13, the power generation analysis module 13 is used to collect energy storage life information of multiple energy storage units corresponding to multiple power generation units in the solar power generation system, and perform power generation analysis based on the multiple conventional weather information and multiple temporary weather information, combined with multiple location information of multiple power generation units, to construct multiple power generation arrays;
[0047] An optimal energy control scheme obtaining module 14, the optimal energy control scheme obtaining module 14 is used to optimize the energy control schemes of the multiple future time periods according to the multiple predicted electricity demand information, the multiple power generation arrays and the multiple energy storage life information, and obtain an optimal energy control scheme, wherein the optimal energy control scheme includes multiple optimal time period energy control schemes, and each optimal time period energy control scheme includes a power generation unit that performs functions and stores energy in each time period;
[0048] The energy control module 15 is used to adopt the optimal energy control scheme to perform energy control in the multiple future time periods.
[0049] Furthermore, the embodiment of the present application also includes:
[0050] A module for collecting sample electricity demand information sequence sets, wherein the module is used to collect sample electricity demand information sequence sets and sample prediction electricity demand information sequence sets according to electricity consumption data records of electricity consumption terminals in the solar power generation system;
[0051] A power demand predictor training module, the power demand predictor training module is used to train a power demand predictor using the sample power demand information sequence set and the sample predicted power demand information sequence set;
[0052] A historical electricity demand information sequence collection module, wherein the historical electricity demand information sequence collection module is used to collect historical electricity demand information sequences within a historical period;
[0053] The time period division module is used to use the power demand forecaster to predict the power demand of the historical power demand information sequence, obtain the predicted power demand information sequence, divide it into multiple future time periods, and obtain multiple predicted power demand information.
[0054] Furthermore, the embodiment of the present application also includes:
[0055] A timestamp information acquisition module, wherein the timestamp information acquisition module is used to acquire the timestamp information of the current time point;
[0056] A regular weather information acquisition module, the regular weather information acquisition module is used to index in a regular weather change table according to the timestamp information to obtain a plurality of regular weather information in a plurality of future time periods, wherein the regular weather change table includes an index relationship between time and regular weather;
[0057] A historical temporary weather information sequence acquisition module, the historical temporary weather information sequence acquisition module is used to acquire historical temporary weather information sequences within a historical period;
[0058] A temporary weather predictor training module, the temporary weather predictor training module is used to collect a sample temporary weather information set and a sample predicted temporary weather information sequence set based on temporary weather monitoring data records, and train a temporary weather predictor;
[0059] A prediction module is used to use the temporary weather predictor to predict the historical temporary weather information sequence to obtain a predicted temporary weather information sequence, and to obtain multiple temporary weather information according to the multiple future time periods.
[0060] Furthermore, the embodiment of the present application also includes:
[0061] A weather information set collection module, the weather information set collection module is used to collect multiple sample regular weather information sets, multiple sample temporary weather information sets and multiple sample power generation sets according to the power generation data logs of multiple power generation units;
[0062] A power generation prediction branch training module, the power generation prediction branch training module is used to respectively adopt the multiple sample conventional weather information sets, the multiple sample temporary weather information sets and the multiple sample power generation sets, train to obtain multiple power generation prediction branches, obtain a power generation predictor, perform power generation prediction on the multiple conventional weather information and the multiple temporary weather information, respectively, and obtain multiple predicted power generation sets;
[0063] A position information acquisition module is used to acquire multiple position information of the multiple power generation units, and to construct multiple power generation arrays in combination with the multiple predicted power generation sets.
[0064] Furthermore, the embodiment of the present application also includes:
[0065] A function construction module is used to construct an energy control function for optimizing energy control schemes for multiple time periods, as shown in the following formula:
[0066]
[0067] Among them, ERF is the regulation fitness, w1 and w2 are weights, M is the number of power generation units used for power supply, N is the number of power generation units used for energy storage, K i is the power generation ranking of the i-th power generation unit supplying power within the energy control plan of the time period, Z is the number of multiple power generation units, the sum of M and N is Z, T j is the energy storage life information of the i-th energy storage unit in the energy control scheme of the time period, T z To preset energy storage life information;
[0068] A time period energy storage control scheme optimization module, the time period energy storage control scheme optimization module is used to optimize the time period energy storage control scheme based on the energy control function in a first future period among multiple future periods, according to the first predicted electricity demand information, the first power generation power array and multiple energy storage life information, to obtain a first optimal time period energy control scheme;
[0069] The optimal control scheme obtaining module is used to continue to optimize the time period energy control schemes of other multiple future time periods, and obtain multiple optimal time period energy control schemes as the optimal energy control scheme.
[0070] Furthermore, the embodiment of the present application also includes:
[0071] A random selection module, the random selection module is used to randomly select a number of power generation units in the first power generation array for power supply and other power generation units for energy storage, and generate multiple energy regulation schemes for initial time periods, wherein the sum of the power generation powers of the several power generation units for power supply is greater than or equal to the first predicted power demand information;
[0072] An initial control comfort calculation module, the initial control comfort calculation module is used to analyze and calculate to obtain multiple initial control fitness of the energy control schemes for the multiple initial time periods based on the energy control function according to the first power generation array and multiple energy storage life information;
[0073] An optimization and update module, the optimization and update module is used to optimize and update the energy control schemes for the multiple initial time periods according to the multiple initial control fitnesses, obtain multiple updated time period energy control schemes, and optimize them;
[0074] The maximum convergence period scheme output module is used to continue the optimization until convergence, obtain multiple convergence period energy control schemes, output the convergence period energy control scheme with the maximum control fitness, and obtain the first optimal period energy control scheme.
[0075] Furthermore, the embodiment of the present application also includes:
[0076] A division module, wherein the division module is used to divide the energy regulation schemes of the multiple initial time periods according to the multiple initial regulation fitnesses to obtain a stage optimal solution and multiple stage common solutions;
[0077] An adjustment and update module, wherein the adjustment and update module is used to adjust and update the power generation units that generate electricity or store energy in the common solutions of other multiple stages with the optimal solution of the stage as the adjustment direction and a preset adjustment amount, so as to obtain energy control schemes for multiple update periods;
[0078] An update control fitness calculation module, the update control fitness calculation module is used to analyze and calculate to obtain multiple update control fitness of the energy control schemes of the multiple update periods based on the energy control function according to the first power generation array and multiple energy storage life information;
[0079] The optimization module is used to distinguish and update the optimal solution of the stage and the common solutions of multiple stages according to multiple update adjustment fitness, and continue to optimize.
[0080] For the specific embodiments of the system energy control device combined with solar power supply, please refer to the embodiments of the system energy control method combined with solar power supply above, which will not be repeated here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0081] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time attenuation factors. The network interface of the computer device is used to communicate with an external terminal via a network connection. The computer program is executed by the processor to implement a system energy regulation method combined with solar power supply.
[0082] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, steps of a system energy regulation method combined with solar power supply are implemented.
[0083] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0084] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.
Claims
1. Combined with the energy control method of solar power supply system, It is characterized in that The method comprises: Collect electricity demand data in historical time and make electricity demand forecasts to obtain multiple predicted electricity demand information in multiple future time periods; Based on the current timestamp, regular weather parameter information is indexed to obtain multiple regular weather information in multiple future time periods, and temporary weather data in historical time is collected to predict temporary weather information to obtain multiple temporary weather information in multiple future time periods; Collecting energy storage life information of multiple energy storage units corresponding to multiple power generation units in the solar power generation system, and performing power generation analysis based on the multiple conventional weather information and multiple temporary weather information in combination with multiple location information of the multiple power generation units, and constructing multiple power generation arrays; According to the multiple predicted electricity demand information, multiple power generation arrays and multiple energy storage life information, the energy control schemes for the multiple future time periods are optimized to obtain an optimal energy control scheme, wherein the optimal energy control scheme includes multiple optimal time period energy control schemes, and each optimal time period energy control scheme includes a power generation unit that performs functions and stores energy in each time period; The optimal energy regulation scheme is adopted to perform energy regulation in the multiple future time periods.
2. The method according to claim 1, It is characterized in that Collect electricity demand data in historical time and make electricity demand forecasts to obtain multiple predicted electricity demand information in multiple future time periods, including: According to the electricity consumption data records of the electricity consumption end in the solar power generation system, a set of sample electricity demand information sequences is collected, and a set of sample predicted electricity demand information sequences is collected; Using the sample power demand information sequence set and the sample predicted power demand information sequence set to train a power demand predictor; Collect historical electricity demand information sequences within historical time; The electricity demand forecaster is used to forecast electricity demand for the historical electricity demand information sequence to obtain a forecast electricity demand information sequence, which is divided into multiple future time periods to obtain multiple forecast electricity demand information.
3. The method according to claim 1, It is characterized in that Based on the current timestamp, the conventional weather parameter information is indexed to obtain multiple conventional weather information in multiple future time periods, and the temporary weather data in the historical time is collected to predict the temporary weather information and obtain multiple temporary weather information in multiple future time periods, including: Get the timestamp information of the current time point; Indexing in a regular weather change table according to the timestamp information to obtain a plurality of regular weather information in a plurality of future time periods, wherein the regular weather change table includes an index relationship between time and regular weather; Collect historical temporary weather information sequences within historical time; Based on temporary weather monitoring data records, a sample temporary weather information set is collected, and a sample predicted temporary weather information sequence set is collected to train a temporary weather predictor; The temporary weather predictor is used to predict the historical temporary weather information sequence to obtain a predicted temporary weather information sequence, and multiple temporary weather information is obtained according to the multiple future time periods.
4. The method according to claim 1, It is characterized in that According to the plurality of conventional weather information and the plurality of temporary weather information, combined with the plurality of location information of the plurality of power generation units, power generation analysis is performed to construct a plurality of power generation arrays, including: Collecting multiple sample regular weather information sets, multiple sample temporary weather information sets, and multiple sample power generation sets according to power generation data logs of multiple power generation units; The plurality of sample conventional weather information sets, the plurality of sample temporary weather information sets and the plurality of sample power generation sets are respectively used to train a plurality of power generation prediction branches, obtain a power generation predictor, and perform power generation prediction on the plurality of conventional weather information and the plurality of temporary weather information, respectively, to obtain a plurality of predicted power generation sets; A plurality of position information of the plurality of power generation units is collected, and a plurality of power generation arrays are constructed by combining the plurality of predicted power generation sets.
5. The method according to claim 1, It is characterized in that According to the plurality of predicted electricity demand information, the plurality of power generation arrays and the plurality of energy storage life information, the energy control schemes for the plurality of future time periods are optimized to obtain an optimal energy control scheme, including: Construct an energy control function for optimizing energy control schemes in multiple time periods, as follows: Among them, ERF is the regulatory fitness, w 1 and w 2 is the weight, M is the number of power generation units used for power supply, N is the number of power generation units used for energy storage, and K i is the power generation ranking of the i-th power generation unit supplying power within the energy control plan of the time period, Z is the number of multiple power generation units, the sum of M and N is Z, T j is the energy storage life information of the i-th energy storage unit in the energy control scheme of the time period, T z To preset energy storage life information; Based on the energy control function, in a first future time period among multiple future time periods, according to the first predicted electricity demand information, the first power generation power array and multiple energy storage life information, the time period energy storage control scheme is optimized to obtain a first optimal time period energy control scheme; Continue to optimize the energy control plans for other multiple future time periods to obtain multiple optimal energy control plans as the optimal energy control plan.
6. The method according to claim 5, It is characterized in that Based on the energy control function, in a first future time period among multiple future time periods, according to the first predicted electricity demand information, the first power generation array and multiple energy storage life information, the time period energy storage control scheme is optimized, including: In the first power generation array, a number of power generation units are randomly selected to supply power, and other power generation units are used to store energy, and a plurality of energy regulation schemes for initial time periods are generated, wherein the sum of the power generation powers of the power generation units is greater than or equal to the first predicted power demand information; According to the first power generation array and the plurality of energy storage life information, based on the energy control function, analyzing and calculating to obtain a plurality of initial control fitness of the energy control schemes for the plurality of initial time periods; According to the multiple initial control fitnesses, the multiple initial time period energy control schemes are optimized and updated to obtain multiple updated time period energy control schemes for optimization; Continue to optimize until convergence, obtain multiple convergence period energy control plans, output the convergence period energy control plan with the largest control fitness, and obtain the first optimal period energy control plan.
7. The method according to claim 6, It is characterized in that According to the multiple initial regulation fitnesses, the multiple initial time period energy regulation schemes are optimized and updated, including: According to the multiple initial control fitnesses, the multiple initial time period energy control schemes are divided to obtain a stage optimal solution and multiple stage common solutions; Taking the optimal solution of the stage as the adjustment direction, using the preset adjustment quantity, the power generation units that generate electricity or store energy in the common solutions of other multiple stages are adjusted and updated to obtain energy control plans for multiple update periods; According to the first power generation array and the plurality of energy storage life information, based on the energy control function, analyzing and calculating to obtain a plurality of update control fitness of the energy control schemes for the plurality of update periods; According to the fitness of multiple updates and adjustments, the optimal solution of the stage and the common solutions of multiple stages are updated and updated, and the optimization is continued.
8. Combined with solar powered system energy control equipment, It is characterized in that The device comprises: An electricity demand forecasting module, which is used to collect electricity demand data in historical time and conduct electricity demand forecasting to obtain multiple predicted electricity demand information in multiple future time periods; A conventional weather information acquisition module, which is used to index conventional weather parameter information based on a current timestamp, obtain multiple conventional weather information in multiple future time periods, collect temporary weather data in historical time, perform temporary weather information forecasting, and obtain multiple temporary weather information in multiple future time periods; A power generation analysis module, the power generation analysis module is used to collect energy storage life information of multiple energy storage units corresponding to multiple power generation units in the solar power generation system, and perform power generation analysis based on the multiple conventional weather information and multiple temporary weather information, combined with multiple location information of multiple power generation units, to construct multiple power generation arrays; An optimal energy control scheme acquisition module, the optimal energy control scheme acquisition module is used to optimize the energy control schemes of the multiple future time periods according to the multiple predicted electricity demand information, multiple power generation arrays and multiple energy storage life information to obtain an optimal energy control scheme, wherein the optimal energy control scheme includes multiple optimal time period energy control schemes, and each optimal time period energy control scheme includes a power generation unit that performs functions and stores energy in each time period; An energy control module is used to adopt the optimal energy control scheme to perform energy control in the multiple future time periods.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
