Intelligent power generation control system

Abstract

This intelligent power generation control system ensures stable grid voltage and frequency by controlling power generation in a timely manner, guarantees that power generation meets demand during peak usage periods, and reduces power generation in a timely manner during off-peak usage periods to avoid power waste and ensure a balance between power supply and demand. [Solution] The intelligent power generation control system includes a data collection module for collecting data, a power data analysis module for determining power consumption quantitative relationship coefficients corresponding to random power consumption influencing factors, an available power prediction module for predicting the available power amount for the next control cycle, an influencing factor statistics module for statistically compiling all fixed power consumption influencing factors and random power consumption influencing factors and their duration of effect for the next control cycle in the power usage area, a power consumption prediction module for calculating the power consumption of the power usage area for the next control cycle, and a power generation control module for controlling the power generation amount of the solar power generation system.

Description

[Technical Field]

[0001] This invention belongs to the field of photovoltaic power generation system technology, and more specifically, relates to an intelligent power generation control system. [Background technology]

[0002] Solar power systems are clean energy devices that utilize the photovoltaic effect of solar cells to directly convert solar radiation energy into electrical energy. At their core are solar cells, generally made from semiconductor materials. When sunlight shines on the cell surface, photons excite and transition electrons within the semiconductor, generating a direct current. This direct conversion process from light energy to electrical energy is quiet and rapid, and because it involves no mechanical motion or chemical reactions, it produces virtually zero emissions and is silent during operation. With continuous technological advancements and steadily decreasing costs, the application range of solar power systems has already expanded from early large-scale power plants to commercial and industrial roofs, rural agricultural facilities, independent power supply in remote areas, and even the exterior walls and windows of urban buildings, demonstrating extremely high adaptability and flexibility. Solar power systems not only provide stable power supply in areas with abundant sunshine, but can also maintain some power output during cloudy or rainy weather by relying on previously stored energy. Its operation is free of exhaust gases, wastewater, and mechanical noise, and relies on inexhaustible solar energy resources. It plays an essential role in alleviating the pressure of conventional fossil fuel shortages, reducing carbon emissions, and promoting a shift towards a low-carbon energy structure, and has already become one of the mainstream directions for the development of the global new energy industry.

[0003] However, conventional solar power systems lack intelligent power generation control functions. If power generation is insufficient to meet demand during peak electricity usage, it can cause power shortages and affect users' normal electricity use. Conversely, during off-peak electricity usage, power generation may exceed demand, leading to power waste and an imbalance in electricity supply and demand. [Overview of the project] [Problems that the invention aims to solve]

[0004] To solve at least one of the above-mentioned technical problems, the present invention provides an intelligent power generation control system. [Means for solving the problem]

[0005] To solve the above technical problems, the present invention provides an intelligent power generation control system, A data collection module for collecting past annual power generation data for solar power generation systems, past annual power usage data for all power usage areas, and storage data for solar energy storage systems, and for forming a curve of past power usage change for all power usage areas based on the past annual power usage data for all power usage areas. Based on historical power consumption change curves for all power usage areas, this is used to determine historical power consumption change curves corresponding to each fixed power consumption influencing factor, historical power consumption change curves corresponding to all random power consumption influencing factors, and the quantitative relationship between each random power consumption influencing factor and power consumption. The quantitative relationship between each random power consumption influencing factor and power consumption is a power data analysis module, which uses a power consumption quantitative relationship coefficient corresponding to the random power consumption influencing factor. Based on past year-to-date power generation data of a solar power generation system, a solar power generation system power generation prediction matrix is ​​constructed; based on the energy storage data of a solar power energy storage system, a solar power energy storage system energy storage capacity prediction matrix is ​​constructed; based on the solar power generation system power generation prediction matrix and the solar power energy storage system energy storage capacity prediction matrix, an available power quantity prediction matrix is ​​obtained; and based on the available power quantity prediction matrix, an available power quantity prediction module is provided to predict the available power quantity for the next control cycle. A statistics module for statistically analyzing all fixed power consumption influencing factors and random power consumption influencing factors and their duration of effect in the next control cycle of a power usage area, A power consumption prediction module for calculating the power consumption of a power consumption area for the next control cycle, based on all fixed power consumption influencing factors and random power consumption influencing factors and their durations, the historical power consumption change curve corresponding to each fixed power consumption influencing factor, and the power consumption quantitative relation coefficient corresponding to each random power consumption influencing factor. The present invention discloses an intelligent power generation control system, which includes a power generation control module for controlling the amount of power generated by a photovoltaic power generation system based on the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle.

[0006] Preferably, the power data analysis module is A first data determination submodule for determining all fixed power consumption influencing factors in all power usage areas, and for obtaining a past power consumption change curve corresponding to each fixed power consumption influencing factor based on all fixed power consumption influencing factors in all power usage areas and the past power consumption change curves for all power usage areas, A second data determination submodule for determining the historical power consumption change curve corresponding to all random power consumption influencing factors, based on the historical power consumption change curves for all power consumption areas and the historical power consumption change curves corresponding to each fixed power consumption influencing factor, It includes a quantitative analysis submodule for determining all random power consumption influencing factors and their time periods of action in all power usage areas, and for matching all random power consumption influencing factors with historical power consumption change curves corresponding to all random power consumption influencing factors based on time series, thereby determining the quantitative relationship between each random power consumption influencing factor and power consumption.

[0007] Preferably, the quantitative analysis submodule is A random power consumption influencing factor determination unit for determining all random power consumption influencing factors and their operating time periods in all power usage areas, A time-series matching unit for matching all random power usage influencing factors with the past power usage change curves corresponding to all random power usage influencing factors based on the time series, and a quantitative relationship determination unit for finding any time period during which various random power usage influencing factors act alone in the past power usage change curves corresponding to all random power usage influencing factors, and for statistically calculating the change amount of the ordinate in the past power usage change curves corresponding to all random power usage influencing factors within the time period during which various random power usage influencing factors act alone, and using the quotient of the change amount of the ordinate and the corresponding change amount of the abscissa as the power usage quantitative relationship coefficient corresponding to the random power usage influencing factor.

[0008] Preferably, the available power amount prediction module includes a prediction matrix construction sub-module 1 for constructing a solar power generation system power generation amount prediction matrix based on the power generation amount of the solar power generation system in each control period in the past year's power generation data of the solar power generation system, a prediction matrix construction sub-module 2 for constructing a solar power generation energy storage system power storage amount prediction matrix based on the power storage amount of the solar power generation energy storage system in each control period in the power storage amount data of the solar power generation energy storage system, and a prediction matrix construction sub-module 3 for obtaining an available power amount prediction matrix based on the solar power generation system power generation amount prediction matrix and the solar power generation energy storage system power storage amount prediction matrix, and for predicting the available power amount value of the next control period based on the available power amount prediction matrix.

[0009] Preferably, constructing a solar power generation system power generation amount prediction matrix based on the power generation amount of the solar power generation system in each control period in the past year's power generation data of the solar power generation system Performing a time series arrangement on the power generation amounts of the photovoltaic power generation system in the i-th control cycle and each control cycle before the i-th control cycle in the past-year power generation data of the photovoltaic power generation system, and forming a sequence of power generation amounts of the control cycle photovoltaic power generation system based on the time series; Constructing a current predicted matrix of the photovoltaic power generation system power generation amount after the end of the i-th control cycle based on the sequence of power generation amounts of the control cycle photovoltaic power generation system: [Number] (1) (In the formula, A i is the current predicted matrix of the photovoltaic power generation system power generation amount after the end of the i-th control cycle, a1 is the power generation amount of the photovoltaic power generation system in the first control cycle, a2 is the power generation amount of the photovoltaic power generation system in the second control cycle, a3 is the power generation amount of the photovoltaic power generation system in the third control cycle, a4 is the power generation amount of the photovoltaic power generation system in the fourth control cycle, a i―1 is the power generation amount of the photovoltaic power generation system in the i-1-th control cycle, and a i is the power generation amount of the photovoltaic power generation system in the i-th control cycle.) is included.

[0010] Preferably, constructing a predicted matrix of the electricity storage amount of the photovoltaic power generation energy storage system based on the electricity storage amounts of the photovoltaic power generation energy storage system in each control cycle in the electricity storage amount data of the photovoltaic power generation energy storage system means Performing a time series arrangement on the electricity storage amounts of the photovoltaic power generation energy storage system in the i-th control cycle and each control cycle before the i-th control cycle in the electricity storage amount data of the photovoltaic power generation energy storage system, and forming a sequence of electricity storage amounts of the control cycle photovoltaic power generation energy storage system based on the time series; Constructing a current predicted matrix of the electricity storage amount of the photovoltaic power generation energy storage system after the end of the i-th control cycle based on the sequence of electricity storage amounts of the control cycle photovoltaic power generation energy storage system: [Number] (2) (where B i is the current solar power generation energy storage system power storage prediction matrix after the end of the i-th control cycle, b1 is the power storage of the solar power generation energy storage system in the first control cycle, b2 is the power storage of the solar power generation energy storage system in the second control cycle, b3 is the power storage of the solar power generation energy storage system in the third control cycle, b4 is the power storage of the solar power generation energy storage system in the fourth control cycle, b i―1 is the power storage of the solar power generation energy storage system in the (i - 1)-th control cycle, and i is the power storage of the solar power generation energy storage system in the b i -th control cycle.) is included.

[0011] Preferably, obtaining an available power prediction matrix based on the solar power generation system power generation prediction matrix and the solar power generation energy storage system power storage prediction matrix, and predicting the available power numerical value for the next control cycle based on the available power prediction matrix is constructing the current available power prediction matrix after the end of the i-th control cycle based on the current solar power generation system power generation prediction matrix after the end of the i-th control cycle and the current solar power generation energy storage system power storage prediction matrix after the end of the i-th control cycle: C i =A i +Bi (3) (where C i is the current available power prediction matrix after the end of the i-th control cycle, is the current solar power generation system power generation prediction matrix after the end of the i-th control cycle, and B i is the current solar power generation energy storage system power storage prediction matrix after the end of the i-th control cycle.) This includes obtaining the average value of all matrix elements in any row except the first row of the current available power prediction matrix after the i-th control cycle, and setting the numerical value of any column in the current available power prediction matrix after the i-th control cycle to a numerical value equal to the average value of all matrix elements in any row except the first row, thereby obtaining a new matrix, and setting the rank of the new matrix to the available power value for the (i+1)th control cycle.

[0012] Preferably, the power consumption of the power consumption area for the next control cycle is calculated based on all fixed power consumption influencing factors and random power consumption influencing factors and their duration of action for the next control cycle, the past power consumption change curve corresponding to each fixed power consumption influencing factor, and the power consumption quantitative relation coefficient corresponding to each random power consumption influencing factor.

number

number

number

number

[0013] Preferably, the power generation control module is A difference value determination unit for calculating the difference between the available power value for the next control cycle and the power consumption of the power usage area for the next control cycle, A rating unit for calculating the response coefficient of a photovoltaic power generation system based on the difference between the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle, Includes a solar power generation system control unit for controlling the amount of power generated by a solar power generation system based on the response coefficient of the solar power generation system.

[0014] Preferably, the response coefficient of the photovoltaic power generation system is calculated based on the difference between the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle.

number

[0015] Compared to conventional technology, the present invention has the following beneficial effects.

[0016] This invention provides an intelligent power generation control system that utilizes a multi-module cooperative architecture to acquire historical power generation data of a solar power generation system, historical power usage data of an area, and energy storage data via a data acquisition module, providing fundamental support for prediction. Furthermore, it clarifies the quantitative relationships between fixed power usage influencing factors and random power usage influencing factors via a power data analysis module, combines statistics of influencing factors and duration of effects for the next cycle by an influencing factor statistics module, and works in conjunction with the matrix prediction method of the available power amount prediction module and the precise calculation of the power usage prediction module to achieve dual precise predictions of available power amount and power usage for the next control cycle. Based on these prediction results, the power generation control module controls the power generation of the solar power generation system in a timely manner. By accurately predicting power usage and power generation, this invention ensures stable grid voltage and frequency by controlling power generation in a timely manner, guarantees that power generation meets demand during peak power usage periods, and reduces power generation in a timely manner during off-peak power usage periods, avoiding power waste and ensuring a balance between power supply and demand. [Brief explanation of the drawing]

[0017] The drawings are intended to aid in understanding the present invention and constitute part of the specification, and are used together with the embodiments of the present invention to interpret the present invention, but do not limit the present invention. [Figure 1] This is a schematic diagram of the intelligent power generation control system according to the present invention. [Modes for carrying out the invention]

[0018] Preferred embodiments of the present invention will be described below with reference to the drawings, but it should be understood that these preferred embodiments are merely for the purpose of explaining and interpreting the present invention and do not limit it.

[0019] Furthermore, in this invention, descriptions such as "first" and "second" are used solely for descriptive purposes and do not specifically indicate an order or rank, nor are they intended to limit the invention. They are merely used to distinguish components or operations described using the same technical terminology, and should not be understood as indicating or suggesting relative importance, or suggesting the number of technical features being referred to. Therefore, features to which "first" and "second" are limited may explicitly or implicitly include at least one such feature. In addition, while the technical ideas and technical features of each embodiment can be combined with each other, this must be based on the fact that they are feasible for a person skilled in the art. If a combination of technical ideas is mutually contradictory or impossible to implement, such a combination of technical ideas should be considered nonexistent and not within the scope of protection claimed by this invention.

[0020] The present invention provides the following embodiments.

[0021] (Example 1) An embodiment of the present invention provides an intelligent power generation control system, as shown in Figure 1, A data collection module for collecting past annual power generation data from solar power generation systems, past annual power usage data from all power usage areas, and storage data from solar energy storage systems, and for forming a curve of past power usage changes for all power usage areas based on the past annual power usage data from all power usage areas. Based on historical power consumption change curves for all power usage areas, this is used to determine historical power consumption change curves corresponding to each fixed power consumption influencing factor, historical power consumption change curves corresponding to all random power consumption influencing factors, and the quantitative relationship between each random power consumption influencing factor and power consumption. The quantitative relationship between each random power consumption influencing factor and power consumption is a power data analysis module, which uses a power consumption quantitative relationship coefficient corresponding to the random power consumption influencing factor. Based on past year-to-date power generation data of a solar power generation system, a solar power generation system power generation prediction matrix is ​​constructed; based on the energy storage data of a solar power energy storage system, a solar power energy storage system energy storage capacity prediction matrix is ​​constructed; based on the solar power generation system power generation prediction matrix and the solar power energy storage system energy storage capacity prediction matrix, an available power quantity prediction matrix is ​​obtained; and based on the available power quantity prediction matrix, an available power quantity prediction module is provided to predict the available power quantity for the next control cycle. A statistics module for statistically analyzing all fixed power consumption influencing factors and random power consumption influencing factors and their duration of effect in the next control cycle of a power usage area, A power consumption prediction module for calculating the power consumption of a power consumption area for the next control cycle, based on all fixed power consumption influencing factors and random power consumption influencing factors and their durations, the historical power consumption change curve corresponding to each fixed power consumption influencing factor, and the power consumption quantitative relation coefficient corresponding to each random power consumption influencing factor. Includes a power generation control module for controlling the amount of power generated by a solar power generation system based on the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle.

[0022] In this embodiment, the data acquisition module acquires data in real time by integrating various sensors and smart measuring instruments. For solar power generation systems, it collects historical power generation data for past years using the inverter and smart meters installed at the grid connection points. For power usage areas, a smart meter network located on the user side (e.g., industrial production areas, commercial sales areas, residential areas, public service areas) collects power usage data and corresponding time data for each time period throughout the year, forming historical power usage year data. For solar energy storage systems, a storage amount monitoring unit acquires storage amount data and corresponding time data for each control cycle throughout the year, and simultaneously generates historical power usage change curves for all power usage areas based on the power usage year data. All data is uploaded to a central server via a communication network (e.g., Ethernet, dedicated wireless line) for unified storage and processing, providing a data basis for subsequent analysis and prediction.

[0023] In this embodiment, the past year's power generation data for the solar power generation system consists of data comprising the instantaneous power generation amount of the solar power generation system for each year and the corresponding time.

[0024] In this embodiment, the historical electricity usage data for all electricity usage areas consists of instantaneous electricity usage for each electricity usage area throughout the year and the corresponding time. All electricity usage areas include all geographical areas where electricity consumption demand exists, including residential and surrounding lifestyle-related facility areas, commercial business areas (e.g., shopping malls, stores, and other commercial activity areas), industrial production areas (e.g., factory sites, construction sites, and other industrial-related areas), and public service areas (e.g., roads with public lighting, public heat supply service areas, public transport hubs, and surrounding areas).

[0025] In this embodiment, the energy storage data of the solar power generation energy storage system consists of the instantaneous energy storage amount of the solar power generation energy storage system over a calendar year and the corresponding time.

[0026] In this embodiment, the curve of past power consumption changes for all power usage areas is a curve constructed with the instantaneous power consumption in past yearly power usage data for all power usage areas as the vertical coordinate and the time corresponding to the instantaneous power consumption as the horizontal coordinate.

[0027] In this embodiment, the factors influencing fixed power consumption include public lighting factors in the power consumption area, public heat supply factors in the power consumption area, public transportation factors in the power consumption area, and power consumption of resident households / shopping malls.

[0028] In this embodiment, the factors influencing random electricity usage are the production volume change index of factories in the electricity usage area, the scale of new construction sites in the electricity usage area, and the number of new residents moving into the electricity usage area.

[0029] In this embodiment, the control period can be set to 1 hour, and the past year can be three consecutive calendar years.

[0030] In this embodiment, past power consumption change curves corresponding to fixed power consumption influencing factors are matched in time series with all fixed power consumption influencing factors and past power consumption change curves for all power usage areas. The average value of the vertical coordinates of the past power consumption change curves for all power usage areas corresponding to each fixed power consumption influencing factor acting individually is calculated, and the average value of the vertical coordinates is taken as the power consumption corresponding to the fixed power consumption influencing factor. The vertical coordinates of all time periods in which all fixed power consumption influencing factors appear are set to this average value, and the curve formed by connecting the left and right coordinate points is taken as the past power consumption change curve corresponding to the fixed power consumption influencing factor.

[0031] In this embodiment, the past power consumption change curves corresponding to random power consumption influencing factors are arranged in a one-to-one correspondence with the past power consumption change curves corresponding to each fixed power consumption influencing factor in chronological order. The values ​​obtained by subtracting the corresponding coordinates of the past power consumption change curves corresponding to fixed power consumption influencing factors from each y-coordinate of the past power consumption change curves of all power consumption influencing factors are used as the y-coordinates of the past power consumption change curves corresponding to all random power consumption influencing factors, and all y-coordinates are connected to form the past power consumption change curves corresponding to all random power consumption influencing factors.

[0032] In this embodiment, the power consumption quantitative relationship coefficient corresponding to the random power consumption influencing factor represents the degree of change in power consumption under the influence of the random power consumption influencing factor within a unit time.

[0033] In this embodiment, controlling the power generation of the photovoltaic system based on the available power value for the next control cycle and the power consumption of the power usage area for the next control cycle includes controlling the maximum power point tracking algorithm of the photovoltaic array to ensure that the photovoltaic system is always in a state of maximum power generation efficiency, controlling the output characteristics of the inverter to adapt to different grid demands, cleaning the surfaces of the photovoltaic components, adjusting the power generated by the photovoltaic system, adjusting the charging and discharging power of the energy storage system, and performing load shifting (reducing the use of non-essential loads during peak power usage hours and shifting the load to off-peak hours, and introducing time-of-use charges to encourage users to use electricity during off-peak hours).

[0034] Principle of Operation and Beneficial Effects of the above-mentioned Technical Proposal: By accurately predicting electricity consumption and generation, the present invention ensures stable grid voltage and frequency by controlling generation in a timely manner, guaranteeing that generation meets demand during peak electricity consumption periods, and reducing generation in a timely manner during off-peak electricity consumption periods, thereby avoiding electricity waste and ensuring a balance between electricity supply and demand.

[0035] (Example 2) Based on Example 1, the power data analysis module includes a first data determination submodule for determining all fixed power consumption influencing factors in all power usage areas and obtaining a past power consumption change curve corresponding to each fixed power consumption influencing factor based on all fixed power consumption influencing factors in all power usage areas and the past power consumption change curves for all power usage areas, A second data determination submodule for determining the historical power consumption change curve corresponding to all random power consumption influencing factors, based on the historical power consumption change curves for all power consumption areas and the historical power consumption change curves corresponding to each fixed power consumption influencing factor, It includes a quantitative analysis submodule for determining all random power consumption influencing factors and their time periods of action in all power usage areas, and for matching all random power consumption influencing factors with historical power consumption change curves corresponding to all random power consumption influencing factors based on time series, thereby determining the quantitative relationship between each random power consumption influencing factor and power consumption.

[0036] In this embodiment, first, all fixed power consumption influencing factors and past power consumption change curves for all power consumption areas are matched in time series to identify time periods in which each fixed factor acts independently. Then, the average value of the y-coordinate (power consumption) of the past power consumption change curve within the time period in which each fixed factor acts independently is calculated, the y-coordinate of that time period is set to this average value, and finally, by connecting the left and right coordinate points of the time period, the past power consumption change curve for the corresponding fixed factor is obtained.

[0037] In this embodiment, first, the past power consumption change curves for all power usage areas are matched one-to-one along the time axis with the past power consumption change curves corresponding to each fixed power consumption influencing factor. Furthermore, for each same time point, the value obtained by subtracting the sum of the vertical coordinates of all fixed factor curves for that time point from the vertical coordinate of the total past power consumption change curve (total power consumption) is used as the vertical coordinate of the random power consumption influencing factor curve. Finally, by connecting the difference values ​​for all time points, the past power consumption change curve corresponding to all random power consumption influencing factor curves is determined.

[0038] Principle of operation and beneficial effects of the above proposed technology: By subdividing the fixed and random power usage influencing factors, the accuracy of predictions is improved, and the predicted results become closer to actual power usage.

[0039] (Example 3) Based on Example 2, the quantitative analysis submodule is: A random power consumption influencing factor determination unit for determining all random power consumption influencing factors and their operating time periods in all power usage areas, It is used to match all random power consumption influencing factors with historical power consumption change curves corresponding to all random power consumption influencing factors, based on time series data. Specifically, First, the time periods in which each random power consumption influencing factor acts (e.g., changes in factory production volume, specific time ranges for the operation of new construction sites) are determined. Furthermore, these time periods are aligned with the time axis (horizontal coordinate) of the past power consumption change curve corresponding to the random power consumption influencing factor. Finally, the power change intervals corresponding to the time periods in which each random factor acts on the curve are found, and the time-series matching between the two is completed, ensuring a one-to-one correspondence between the random factor and the power change intervals it caused on the curve. The system includes a quantitative relationship determination unit for finding any time period in the historical power consumption change curve corresponding to all random power consumption influencing factors where each random power consumption influencing factor acts independently, statistically calculating the change in the vertical coordinate in the historical power consumption change curve corresponding to all random power consumption influencing factors within the time period where each random power consumption influencing factor acts independently, and using the quotient between the change in the vertical coordinate and the corresponding change in the horizontal coordinate as a quantitative relationship coefficient for power consumption corresponding to the random power consumption influencing factor.

[0040] The time-series matching unit is a data processing component within the system whose core function is to accurately match two types of information based on chronological order: time points recorded in historical data curves and the specific time periods in which various known random power usage events occurred. This unit identifies the power usage characteristics of a single event from mixed historical data by associating abstract events with specific power usage fluctuation patterns on the time axis and establishing an event-time-power usage curve correspondence.

[0041] The operating principle and beneficial effects of the above proposed technology: Detailed statistical analysis improves the accuracy of the quantitative correlation coefficient for electricity consumption. The introduction of the quantitative correlation coefficient makes the prediction model more scientific and rational, increasing the reliability of the prediction.

[0042] (Example 4) Based on Example 1, the available power prediction module is: A prediction matrix construction submodule 1 for constructing a prediction matrix for the amount of power generated by a solar power generation system based on the amount of power generated by the solar power generation system for each control cycle in past year-to-date power generation data of the solar power generation system, A prediction matrix construction submodule 2 for constructing a prediction matrix for the amount of energy stored in a solar power generation energy storage system based on the amount of energy stored in the solar power generation energy storage system for each control cycle in the energy storage data of the solar power generation energy storage system, The system includes a prediction matrix construction submodule 3 for obtaining an available energy prediction matrix based on a solar power generation system power generation prediction matrix and a solar energy storage system energy storage prediction matrix, and for predicting the available energy value for the next control cycle based on the available energy prediction matrix.

[0043] The available power prediction module is the core computing unit of the system and is responsible for predicting the total amount of power that the entire photovoltaic system can actually use to meet the load within the next control cycle. This module combines two sources: the amount of power the photovoltaic system itself is about to generate, and the amount of reserve power that can be safely released from the photovoltaic system's energy storage system. By constructing a mathematical prediction model and analyzing historical power generation data and energy storage states over time, it calculates the total power resources that the system can dispatch within a future cycle.

[0044] Principle of operation and beneficial effects of the above proposed technology: By constructing a detailed prediction matrix, the accuracy of predictions for available power is improved, and power control can be performed more effectively based on accurate prediction results, reducing power waste.

[0045] (Example 5) Based on Example 4, constructing a solar power generation prediction matrix based on the amount of power generated by the solar power generation system for each control cycle in the past year's power generation data of the solar power generation system is possible. This involves performing a time-series arrangement on the power generation amounts of the solar power generation system for the i-th control cycle and each control cycle prior to the i-th control cycle in the past year's power generation data of the solar power generation system, thereby forming a time-series sequence of power generation amounts for each control cycle of the solar power generation system. Based on the sequence of power generation values ​​of the controlled-cycle photovoltaic system, construct a prediction matrix of the current photovoltaic system power generation after the end of the i-th control cycle:

number

[0046] The operating principle and beneficial effects of the above proposed technology: Time-series sequencing simplifies the data processing flow, improves work efficiency, and, based on detailed time-series data, improves the accuracy of the current solar power generation prediction matrix after the i-th control cycle.

[0047] (Example 6) Based on Example 4, constructing a solar power energy storage system energy storage amount prediction matrix based on the amount of energy stored in the solar power energy storage system for each control cycle in the energy storage data of the solar power energy storage system is possible. The energy storage data of the solar power generation energy storage system is arranged in a time series for the ith control cycle and for each control cycle prior to the ith control cycle, thereby forming a time-series sequence of energy storage amounts for the control cycle of the solar power generation energy storage system. Based on the sequence of energy storage amounts of the controlled period photovoltaic energy storage system, the i To construct a prediction matrix of the current solar power energy storage system's energy storage capacity after the end of each control cycle:

number

[0048] The operating principle and beneficial effects of the above proposed technology: Time-series sequencing simplifies the data processing flow, improves work efficiency, and, based on detailed time-series data, improves the accuracy of the prediction matrix for the current solar power energy storage system's energy storage capacity after the i-th control cycle.

[0049] (Example 7) Based on Example 4, an available power quantity prediction matrix is ​​obtained based on the solar power generation amount prediction matrix and the solar energy storage amount prediction matrix, and the available power quantity value for the next control cycle is predicted based on the available power quantity prediction matrix. The i Prediction matrix of current solar power generation amount after the end of this control cycle and the i Based on the current solar power energy storage system storage capacity prediction matrix after the end of the i-th control cycle, construct the current available power quantity prediction matrix after the end of the i-th control cycle: C i =A i +Bi (3) (In the formula, C i B is the current available power prediction matrix after the i-th control cycle, and B is the current solar power generation system power prediction matrix after the i-th control cycle. iThis is the prediction matrix for the current solar power energy storage system's energy storage capacity after the i-th control cycle. This includes obtaining the average value of all matrix elements in any row except the first row of the current available power prediction matrix after the i-th control cycle, and setting the numerical value of any column in the current available power prediction matrix after the i-th control cycle to a numerical value equal to the average value of all matrix elements in any row except the first row, thereby obtaining a new matrix, and setting the rank of the new matrix to the available power value for the (i+1)th control cycle.

[0050] The operating principle and beneficial effects of the above proposed technology: By generating a detailed available power prediction matrix, the accuracy of predictions is improved, and power control can be performed more effectively based on accurate prediction results.

[0051] (Example 8) Based on Example 1, calculating the power consumption of the power consumption area for the next control cycle is possible based on all fixed power consumption influencing factors and random power consumption influencing factors and their duration of action for the next control cycle, the past power consumption change curve corresponding to each fixed power consumption influencing factor, and the power consumption quantitative relation coefficient corresponding to each random power consumption influencing factor.

number

number

number

number

[0052] Principle of operation and beneficial effects of the above proposed technology: The reliability of the prediction results is guaranteed by calculating the power consumption of the power consumption area for the (i+1)th control cycle using power consumption quantitative relation coefficients corresponding to each random power consumption influencing factor.

[0053] (Example 9) Based on Example 1, the power generation control module is: A difference value determination unit for calculating the difference between the available power value for the next control cycle and the power consumption of the power usage area for the next control cycle, A rating unit for calculating the response coefficient of a photovoltaic power generation system based on the difference between the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle, Includes a solar power generation system control unit for controlling the amount of power generated by a solar power generation system based on the response coefficient of the solar power generation system. Calculating the response coefficient of a solar power generation system based on the difference between the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle is possible.

number

[0054] The response coefficient of a photovoltaic system is a dimensionless control parameter that quantifies the urgency of the need to control the power output of the photovoltaic system. This coefficient is determined by the difference between the predicted available power and the predicted power load for the next control cycle. When there is a power surplus, the response coefficient approaches 0, and the photovoltaic system proportionally reduces its power output. When there is a power shortage, the response coefficient approaches 1, and the photovoltaic system increases its power output or operates at maximum power. This serves as an important input signal, directly instructing execution units such as inverters and energy storage systems to perform precise power output adjustments.

[0055] Principle of operation and beneficial effects of the above-mentioned technology: The present invention improves the accuracy of power generation control through detailed calculation of difference values ​​and response coefficients, enabling more effective power control and reducing power waste based on a precise control strategy.

[0056] Clearly, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the invention fall within the claims of the invention and its equivalent technical scope, the invention intentionally incorporates these modifications and variations.

Claims

1. An intelligent power generation control system, A data collection module for collecting past annual power generation data for solar power generation systems, past annual power usage data for all power usage areas, and storage data for solar energy storage systems, and for forming a curve of past power usage change for all power usage areas based on the past annual power usage data for all power usage areas. Based on historical power consumption change curves for all power usage areas, this is used to determine historical power consumption change curves corresponding to each fixed power consumption influencing factor, historical power consumption change curves corresponding to all random power consumption influencing factors, and the quantitative relationship between each random power consumption influencing factor and power consumption. The quantitative relationship between each random power consumption influencing factor and power consumption is a power data analysis module, which uses a power consumption quantitative relationship coefficient corresponding to the random power consumption influencing factor. Based on past year-to-date power generation data of a solar power generation system, a solar power generation system power generation prediction matrix is ​​constructed; based on the energy storage data of a solar power energy storage system, a solar power energy storage system energy storage capacity prediction matrix is ​​constructed; based on the solar power generation system power generation prediction matrix and the solar power energy storage system energy storage capacity prediction matrix, an available power quantity prediction matrix is ​​obtained; and based on the available power quantity prediction matrix, an available power quantity prediction module is provided to predict the available power quantity for the next control cycle. A statistics module for statistically analyzing all fixed power consumption influencing factors and random power consumption influencing factors and their duration of effect in the next control cycle of a power usage area, A power consumption prediction module for calculating the power consumption of a power consumption area for the next control cycle, based on all fixed power consumption influencing factors and random power consumption influencing factors and their durations, the historical power consumption change curve corresponding to each fixed power consumption influencing factor, and the power consumption quantitative relation coefficient corresponding to each random power consumption influencing factor. An intelligent power generation control system, characterized by including a power generation control module for controlling the amount of power generated by a solar power generation system based on the available power amount value for the next control cycle and the power consumption of the power usage area for the next control cycle.

2. The power data analysis module is, A first data determination submodule for determining all fixed power consumption influencing factors in all power usage areas, and for obtaining a past power consumption change curve corresponding to each fixed power consumption influencing factor based on all fixed power consumption influencing factors in all power usage areas and the past power consumption change curves for all power usage areas, A second data determination submodule for determining the past power consumption change curve corresponding to all random power consumption influencing factors, based on the past power consumption change curves for all power usage areas and the past power consumption change curves corresponding to each fixed power consumption influencing factor, The intelligent power generation control system according to claim 1, comprising a quantitative analysis submodule for determining all random power consumption influencing factors and their operating time periods in all power usage areas, matching all random power consumption influencing factors with past power consumption change curves corresponding to all random power consumption influencing factors based on time series, and determining the quantitative relationship between each random power consumption influencing factor and power consumption.

3. The quantitative analysis submodule is: A random power consumption influencing factor determination unit for determining all random power consumption influencing factors and their operating time periods in all power usage areas, A time-series matching unit for matching all random power consumption influencing factors with historical power consumption change curves corresponding to all random power consumption influencing factors, based on time series data, The intelligent power generation control system according to claim 2, comprising: a quantitative relationship determination unit for finding any time period in the past power consumption change curve corresponding to all random power consumption influencing factors in which various random power consumption influencing factors act independently; statistically calculating the change in the vertical coordinate in the past power consumption change curve corresponding to all random power consumption influencing factors in the time period in which various random power consumption influencing factors act independently; and using the quotient between the change in the vertical coordinate and the corresponding change in the horizontal coordinate as a power consumption quantitative relationship coefficient corresponding to the random power consumption influencing factor.

4. A prediction matrix construction submodule 1 for constructing a solar power generation system power generation prediction matrix based on the amount of power generated by the solar power generation system for each control cycle in past year-end power generation data of the solar power generation system, A prediction matrix construction submodule 2 for constructing a prediction matrix for the amount of energy stored in a solar power generation energy storage system based on the amount of energy stored in the solar power generation energy storage system for each control cycle in the energy storage data of the solar power generation energy storage system, The intelligent power generation control system according to claim 1, comprising a prediction matrix construction submodule 3 for obtaining an available power generation prediction matrix based on a solar power generation system power generation prediction matrix and a solar energy storage system storage amount prediction matrix, and for predicting the available power generation value for the next control cycle based on the available power generation prediction matrix.

5. Constructing a solar power generation prediction matrix based on the amount of power generated by the solar power generation system for each control cycle in past year-to-date power generation data of the solar power generation system is possible. This involves creating a time-series sequence of the power generation amounts of the solar power generation system for the ith control cycle and each control cycle prior to the ith control cycle in the past year's power generation data of the solar power generation system, thereby forming a time-series sequence of power generation amounts for each control cycle of the solar power generation system. Based on the sequence of power generation values ​​of the controlled-cycle photovoltaic system, construct a prediction matrix of the current photovoltaic system power generation after the end of the i-th controlled-cycle: [Math 1] （１） (In the formula, A ｉ This is the current solar power generation system power generation prediction matrix after the i-th control cycle has ended, and a １ is the amount of power generated by the first controlled-cycle photovoltaic power generation system, and a ２ is the power output of the second controlled-cycle photovoltaic power generation system, and a ３ is the power output of the third controlled-cycle photovoltaic power generation system, and a ４ This is the power output of the fourth controlled-cycle photovoltaic power generation system, and a ｉ―１ is the power output of the i-1 control cycle photovoltaic power generation system, and a ｉ The intelligent power generation control system according to claim 4, wherein is the power generation amount of the i-th controlled period photovoltaic power generation system.

6. Based on the amount of energy stored in the solar power energy storage system for each control cycle in the energy storage data of the solar power energy storage system, constructing a solar power energy storage system energy storage capacity prediction matrix is ​​possible. The energy storage data of the solar power generation energy storage system is arranged in a time series for the ith control cycle and for each control cycle prior to the ith control cycle, thereby forming a time-series sequence of energy storage amounts for the control cycle of the solar power generation energy storage system. Based on the sequence of energy storage amounts of the controlled-cycle photovoltaic energy storage system, construct a prediction matrix of the current energy storage amount of the photovoltaic energy storage system after the end of the i-th controlled-cycle: [Math 2] （２） (where B ｉ is the current predicted matrix of the power storage amount of the solar power generation energy storage system after the end of the i-th control cycle, and b １ is the power storage amount of the solar power generation energy storage system in the first control cycle, b ２ is the power storage amount of the solar power generation energy storage system in the second control cycle, b ３ is the power storage amount of the solar power generation energy storage system in the third control cycle, b ４ is the power storage amount of the solar power generation energy storage system in the fourth control cycle, b ｉ―１ is the power storage amount of the solar power generation energy storage system in the (i - 1)-th control cycle, and i is the power storage amount of the solar power generation energy storage system in the b ｉ -th control cycle.) The power generation intelligent control system according to claim 4, characterized by including this.

7. Based on the solar power generation system power generation prediction matrix and the solar energy storage system storage amount prediction matrix, an available power generation prediction matrix is ​​obtained, and based on the available power generation prediction matrix, the available power generation value for the next control cycle is predicted. Based on the current solar power generation prediction matrix after the ith control cycle and the current solar energy storage system storage prediction matrix after the ith control cycle, construct a current available power generation prediction matrix after the ith control cycle: C ｉ =A ｉ +Bi (3) (In the formula, C ｉ B is the current available power prediction matrix after the ith control cycle, and B is the current solar power generation system power prediction matrix after the ith control cycle. ｉ This is the prediction matrix for the current solar power energy storage system's energy storage capacity after the i-th control cycle. The power generation intelligent control system according to claim 4, characterized in that it includes obtaining the average value of all matrix elements in any row except the first row of the current available power prediction matrix after the end of the i-th control cycle, and setting the value of any column in the current available power prediction matrix after the end of the i-th control cycle to a value equal to the average value of all matrix elements in any row except the first row, thereby obtaining a new matrix, and setting the rank of the new matrix to the available power value for the (i+1)th control cycle.

8. Calculating the power consumption of the power consumption area for the next control cycle based on all fixed power consumption influencing factors and random power consumption influencing factors and their durations, the historical power consumption change curve corresponding to each fixed power consumption influencing factor, and the power consumption quantitative relationship coefficient corresponding to each random power consumption influencing factor, is: [Math 3] （４） （４） (In the formula, u ｉｊ This represents the change in power consumption per unit time when the j-type fixed power consumption influencing factor is acting, obtained based on the past power consumption change curve corresponding to the j-type fixed power consumption influencing factor before the end of the i-th control cycle, u ｊ (t ｕｉｊ ) represents the past power consumption change curve corresponding to the j-th type fixed power consumption influencing factor before the end of the i-th control cycle, u ｊ t represents the vertical coordinate of the past power consumption change curve corresponding to the j-th type fixed power consumption influencing factor before the end of the i-th control cycle, i.e., the past power consumption corresponding to the j-th type fixed power consumption influencing factor, ｕｉｊ (where is the horizontal coordinate of the past power consumption change curve corresponding to the j-th type fixed power consumption influencing factor before the end of the i-th control cycle, i.e., the time when the j-th type fixed power consumption influencing factor acts.) [Math 4] （５） (In the formula, Q ｉ+１ is the power consumption of the power usage area for the (i+1)th control cycle, and n is the number of types of fixed power consumption influencing factors for the (i+1)th control cycle. [Math 5] V is the duration of action of the j-th type fixed power consumption influencing factor in the (i+1)th control cycle, m is the total number of types of random power consumption influencing factors in the (i+1)th control cycle, and V ｋ This represents the quantitative relationship coefficient for power consumption corresponding to the k-th type random power consumption influencing factor, [Math 6] The intelligent power generation control system according to claim 1, characterized in that it includes the duration of action of the k-th type random power consumption influencing factor in the i+1th control cycle.

9. The power generation control module is A difference value determination unit for calculating the difference between the available power value for the next control cycle and the power consumption of the power usage area for the next control cycle, A rating unit for calculating the response coefficient of a photovoltaic power generation system based on the difference between the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle, The intelligent power generation control system according to claim 1, comprising a solar power generation system control unit for controlling the amount of power generated by a solar power generation system based on the response coefficient of the solar power generation system.

10. Calculating the response coefficient of a solar power generation system based on the difference between the available power amount for the next control cycle and the power consumption of the power usage area for the next control cycle is possible. [Number 7] （６） (In the formula, ε is the response coefficient of the photovoltaic power generation system, and P ｉ+１ Q is the available energy value for the (i+1)th control cycle. ｉ+１ The power generation intelligent control system according to claim 9, characterized in that it includes: ) where is the power consumption of the power usage area for the (i+1)th control cycle, and e is a natural number whose value is 2.71.

Images