Hierarchical scheduling method for low-carbon building photovoltaic storage and charging system based on artificial intelligence

Abstract

The present application provides a hierarchical scheduling method for a low-carbon building photovoltaic storage and charging system. The method obtains weather data in a preset future period through the photovoltaic management layer, and determines the predicted photovoltaic power generation data in the preset future period based on the weather data, determines the predicted power load data in the preset future period based on the historical load monitoring data through the equipment load layer, and obtains the current remaining power data of the energy storage device through the energy storage management layer. Then, the intelligent scheduling layer uses the preset power transmission scheduling model, and determines the power scheduling strategy in the preset future period based on the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, thereby indicating the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer in the preset future period, thereby effectively matching photovoltaic power generation with the building power load, and realizing real-time optimization scheduling of power.

Description

Technical Field

[0001] The present application relates to data processing technology, and in particular to a hierarchical scheduling method for a low-carbon building photovoltaic storage and charging system based on artificial intelligence. Background Art

[0002] With the continuous growth of global energy demand and the increasing awareness of environmental protection, low-carbon, energy-saving and efficient energy management systems have become an important direction for modern building construction. Traditional building energy management systems often have problems such as low energy utilization efficiency, inflexible scheduling, and poor adaptability to environmental changes, making it difficult to meet the energy management needs of modern buildings.

[0003] In building energy management systems, photovoltaic power generation, as a clean and renewable energy form, has great application potential. However, photovoltaic power generation is greatly affected by weather conditions, and its power generation is uncertain and volatile. At the same time, the power load inside the building also changes over time, with peak and valley differences. Therefore, how to effectively match photovoltaic power generation with building power load and achieve optimal scheduling of electric energy has become a technical problem that needs to be solved in the field of building energy management. Summary of the invention

[0004] The present application provides a hierarchical scheduling method for a low-carbon building photovoltaic storage and charging system based on artificial intelligence, which is used to solve the problem of how to effectively match photovoltaic power generation with building power load and achieve optimal scheduling of electric energy, which has become a technical problem that needs to be urgently solved in the field of building energy management.

[0005] In a first aspect, the present application provides a hierarchical scheduling method for a low-carbon building photovoltaic storage and charging system based on artificial intelligence, which is applied to a building photovoltaic storage and charging management system, wherein the building photovoltaic storage and charging management system includes an intelligent scheduling layer, a photovoltaic management layer, an energy storage management layer, a power grid management layer, and an equipment load layer, wherein the intelligent scheduling layer is connected to the photovoltaic management layer, the energy storage management layer, and the equipment load layer, respectively; the method includes:

[0006] The photovoltaic management layer obtains weather data within a preset future period, determines predicted photovoltaic power generation data for the preset future period based on the weather data, and sends the predicted photovoltaic power generation data to the intelligent scheduling layer;

[0007] The equipment load layer determines the predicted power load data for the preset future period according to the historical load monitoring data, and sends the predicted power load data to the intelligent scheduling layer;

[0008] The energy storage management layer obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer;

[0009] The intelligent scheduling layer utilizes a preset power transmission scheduling model, and determines the power scheduling strategy within the preset future time period based on the predicted photovoltaic power generation data, the predicted power load data and the remaining power data. The power scheduling strategy is used to indicate the direction of power transmission between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer.

[0010] In the above scheme, the intelligent management of the building photovoltaic storage and charging system is realized by introducing the intelligent scheduling layer, wherein the intelligent scheduling layer can comprehensively process the data from the photovoltaic management layer, the equipment load layer and the energy storage management layer, and formulate an efficient power scheduling strategy based on these data, thereby significantly improving the automation and intelligence level of the system. In addition, the above power scheduling strategy fully considers multiple factors such as photovoltaic power generation, power load and remaining power of energy storage equipment. Through reasonable power distribution and transmission, efficient energy utilization is achieved and unnecessary energy waste is avoided. Through the hierarchical design, each management layer performs its duties and cooperates with each other to ensure the stable operation of the building photovoltaic storage and charging system. At the same time, the intelligent scheduling layer can adjust the scheduling strategy in real time to cope with various situations, further improving the stability and reliability of the system. It can be seen that through the optimized power scheduling in the above scheme, not only the energy cost of the building is reduced, but also the energy utilization efficiency is improved.

[0011] Optionally, the photovoltaic management layer obtains weather data in a preset future period, and determines predicted photovoltaic power generation data for the preset future period according to the weather data, including:

[0012] Determine a temperature influence factor curve according to the ambient temperature data in the weather data;

[0013] Determine an illumination angle influencing factor curve according to the illumination angle data in the weather data;

[0014] The predicted photovoltaic power generation data is determined according to the light intensity data in the weather data, the temperature influence factor curve, and the light angle influence factor curve.

[0015] In the above scheme, by comprehensively considering multiple factors such as ambient temperature, light intensity and light angle in weather data, and using these factors to determine the temperature influence factor curve and the light angle influence factor curve respectively, and then combining the light intensity data to determine the predicted photovoltaic power generation data, it can more comprehensively reflect the complexity and dynamics of the actual photovoltaic power generation process, thereby significantly improving the accuracy of photovoltaic power generation prediction and making the power scheduling of building solar storage and charging systems more accurate and scientific.

[0016] Accurately forecasting photovoltaic power generation data provides an important basis for decision-making at the intelligent dispatching layer. In terms of energy distribution and management, the use and storage of electricity can be reasonably arranged according to the predicted photovoltaic power generation, avoiding energy waste and over-reliance on external power grids. This helps to improve the overall energy utilization efficiency of the building photovoltaic storage and charging system, reduce operating costs, and achieve the goal of low-carbon and environmental protection.

[0017] Moreover, in the process of photovoltaic power generation, changes in environmental factors (such as temperature, light intensity and angle) have a significant impact on power generation. By accurately predicting the impact of these factors on photovoltaic power generation, the working state of the system can be adjusted in time to reduce the sudden drop or excess of power generation caused by sudden environmental changes, thereby enhancing the stability and reliability of the system.

[0018] In addition, the intelligent dispatching layer can use these accurate prediction data to formulate power dispatching strategies more scientifically. In different situations, it can accurately determine whether the photovoltaic power generation can meet the power load demand, and decide whether it is necessary to obtain power supplement from the energy storage management layer or the grid management layer, or transmit excess power to the energy storage management layer or the grid management layer. This intelligent dispatching decision-making capability helps to realize the automated and intelligent management of the building photovoltaic storage and charging system.

[0019] Optionally, the equipment load layer determines the predicted power load data for the preset future period according to the historical load monitoring data, including:

[0020] The equipment load layer obtains the load power consumption corresponding to each time node in the historical load monitoring data to generate a historical load power consumption sequence;

[0021] The prediction feature weight value is determined according to the historical load power consumption sequence, so as to determine the predicted power load power consumption corresponding to the preset future time period according to the historical load power consumption sequence, the prediction feature weight value and the predicted power load power consumption of the previous prediction cycle, and the predicted power load data of the preset future time period includes the predicted power load power consumption.

[0022] In the above scheme, by obtaining the load power consumption at each time node in the historical load monitoring data, a complete historical load power consumption sequence is generated. This step provides a solid foundation for subsequent forecasting analysis. Furthermore, the prediction feature weight value is determined based on historical data, so that the prediction model can automatically learn and identify the key factors affecting the power load and their weights, thereby more accurately predicting the power load in future periods. This historical data-driven prediction method significantly improves the prediction accuracy and provides a reliable basis for the power scheduling of building photovoltaic storage and charging systems.

[0023] Since the power load characteristics of different buildings may vary due to factors such as building type, purpose, and human activities, traditional fixed parameter prediction methods often have difficulty adapting to these changes. This method can dynamically adapt to the changes in power load of different buildings by automatically learning and adjusting the prediction feature weight values, thereby enhancing the adaptability and flexibility of the system.

[0024] Accurate forecasting of electricity load data enables the building photovoltaic storage and charging system to plan the use and distribution of electricity in advance. When the system is running, the proportion of photovoltaic power generation, energy storage and grid power supply can be reasonably adjusted according to the forecast data to ensure the balance of electricity supply and demand, reduce energy waste and grid pressure. This helps to optimize resource allocation and improve the economy and environmental protection of the system.

[0025] The equipment load layer provides important decision support for the intelligent dispatching layer by accurately predicting the power load in the future period. The intelligent dispatching layer can formulate a more scientific and reasonable power dispatching strategy based on the predicted data to ensure that the system can maintain efficient and stable operation under different operating conditions. This intelligent decision-making ability helps to improve the automation and intelligence level of the building photovoltaic storage and charging system.

[0026] Optionally, the intelligent scheduling layer uses a preset power transmission scheduling model and determines the power scheduling strategy in the preset future period according to the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, including:

[0027] If a first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than a first ratio threshold, and the remaining power data is less than a preset remaining power, the power dispatch strategy is used to instruct the photovoltaic management layer to transmit power to the equipment load layer and the energy storage management layer, wherein the first ratio threshold is a value greater than 1;

[0028] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than a first ratio threshold, and the remaining power data is greater than the preset remaining power, the power dispatch strategy is used to instruct the photovoltaic management layer to transmit power to the equipment load layer and the power grid management layer;

[0029] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, and the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is greater than the first ratio threshold, then the electric energy dispatching strategy is used to instruct the photovoltaic management layer and the energy storage management layer to transmit electric energy to the equipment load layer;

[0030] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is less than the first ratio threshold, and the remaining electric energy data is greater than the preset remaining power, then the electric energy dispatching strategy is used to instruct the photovoltaic management layer, the energy storage management layer and the power grid management layer to transmit electric energy to the equipment load layer;

[0031] If the first ratio between the predicted photovoltaic power generation data and the predicted electricity load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted electricity load data is less than the first ratio threshold, and the remaining electric energy data is less than the preset remaining power, then the electric energy scheduling strategy is used to instruct the photovoltaic management layer and the power grid management layer to transmit electric energy to the equipment load layer and the energy storage management layer.

[0032] In the above scheme, the intelligent dispatching layer formulates the power dispatching strategy based on multiple data (predicted photovoltaic power generation data, predicted power load data, and remaining power data) and preset conditions (such as the first ratio threshold and preset remaining power), so as to ensure that the system can make the best power allocation decision under different circumstances, thereby maximizing energy utilization efficiency. Specifically, by setting multiple condition judgment logics, different energy supply and demand scenarios can be flexibly responded to. For example, when photovoltaic power generation is sufficient but the energy storage device is insufficient, the device load layer and the energy storage management layer are given priority to supply power; when both photovoltaic power generation and energy storage power are insufficient to meet the load demand, the grid management layer is introduced to participate in the power supply. When the energy storage device has sufficient power, the above scheme can reasonably utilize energy storage resources and reduce unnecessary grid power supply, thereby reducing energy costs and carbon emissions. At the same time, when the energy storage device is insufficient, by reasonably arranging the priority of photovoltaic power generation and grid power supply, it is ensured that the energy storage device is replenished in time to meet future energy needs. By optimizing the power dispatching strategy, the above scheme can reduce unnecessary energy waste and cost expenditure. For example, when photovoltaic power generation is sufficient, clean energy is used first to supply electricity, reducing the cost of purchasing electricity from the power grid; when the energy storage device has sufficient power, the reliance on power supply from the power grid is reduced, reducing the cost of purchasing electricity from the power grid. These measures together improve the economy of the system. By formulating an energy dispatching strategy based on a comprehensive consideration of multiple factors, the above scheme can ensure the stable operation of the system under various circumstances, especially in the case of tight energy supply and demand or emergencies. Through reasonable energy distribution and transmission, it can effectively alleviate the contradiction between supply and demand and improve the reliability and stability of the system.

[0033] Optionally, the electric energy dispatching strategy is used to instruct the photovoltaic management layer to transmit electric energy to the equipment load layer and the energy storage management layer, including:

[0034] The intelligent scheduling layer generates first predicted power supply data to be transmitted to the equipment load layer according to the predicted power load data, so as to instruct the photovoltaic management layer to transmit the power of the first predicted power supply data to the equipment load layer within the preset future period;

[0035] The intelligent scheduling layer generates second predicted power supply data to be transmitted to the energy storage management layer based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer to transmit the power of the second predicted power supply data to the energy storage management layer within the preset future time period.

[0036] In the above scheme, by generating the first predicted power supply data transmitted to the equipment load layer according to the predicted power load data, and generating the second predicted power supply data transmitted to the energy storage management layer according to the predicted photovoltaic power generation data and the first predicted power supply data, the reasonable distribution and efficient use of electric energy are ensured. When transmitting electric energy to the energy storage management layer, the intelligent scheduling layer reasonably determines the charging amount of the energy storage device according to the actual situation of photovoltaic power generation and the predicted power load demand. This helps to optimize the charging strategy of the energy storage device, ensure that the energy storage device can provide sufficient power support when needed, and avoid energy waste and equipment loss caused by overcharging. In addition, through the preset power transmission scheduling model and predicted data, the intelligent scheduling layer can quickly formulate and execute the power scheduling strategy. This efficient response speed helps the system to quickly adapt to changes in energy supply and demand, and ensure the stable operation and efficient operation of various equipment in the building. In addition, the intelligent scheduling layer can flexibly adjust the power distribution strategy according to different energy supply and demand conditions to meet the different needs of the equipment load layer and the energy storage management layer. This flexibility helps the system better cope with various complex situations and improve the overall operation efficiency. It can be seen that by giving priority to the use of clean energy such as photovoltaic power generation and rationally optimizing the charging strategy of energy storage equipment, the above solution can help reduce fossil energy consumption and carbon emissions.

[0037] Optionally, the electric energy dispatching strategy is used to instruct the photovoltaic management layer to transmit electric energy to the equipment load layer and the power grid management layer, including:

[0038] The intelligent scheduling layer generates first predicted power supply data to be transmitted to the equipment load layer according to the predicted power load data, so as to instruct the photovoltaic management layer to transmit the power of the first predicted power supply data to the equipment load layer within the preset future period;

[0039] The intelligent scheduling layer generates third predicted power supply data for transmission to the power grid management layer based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer to transmit the power of the third predicted power supply data to the power grid management layer within the preset future time period.

[0040] In the above scheme, by transmitting excess power to the grid management layer, it helps to balance the overall load of the grid and reduce the pressure on the grid during peak hours, thereby helping to improve the stability and reliability of the grid and reduce the risk of power outages caused by excessive grid load. In addition, transmitting excess power to the grid management layer not only helps to balance the grid load, but also may bring certain economic benefits to the building. By participating in the power trading of the grid or obtaining subsidies, the building can further reduce operating costs and improve overall economic benefits. In addition, the intelligent scheduling layer can quickly adjust the power transmission strategy based on real-time data and prediction results to meet the different needs of the equipment load layer and the grid management layer.

[0041] Optionally, the electric energy dispatching strategy is used to instruct the photovoltaic management layer and the energy storage management layer to transmit electric energy to the equipment load layer, including:

[0042] The intelligent scheduling layer generates fourth predicted power supply data to be transmitted to the equipment load layer according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within the preset future time period;

[0043] The intelligent scheduling layer generates fifth predicted power supply data for transmission to the energy storage management layer based on the predicted power load data and the predicted photovoltaic power generation data, so as to instruct the energy storage management layer to transmit the electric energy of the fifth predicted power supply data to the equipment load layer within the preset future time period.

[0044] In the above scheme, the intelligent scheduling layer generates the fifth predicted power supply data transmitted to the energy storage management layer based on the predicted power load data and the predicted photovoltaic power generation data. This strategy can accurately control the discharge process of the energy storage management layer, thereby optimizing the utilization rate of the energy storage equipment and improving the overall energy utilization efficiency. When the photovoltaic power generation is not enough to fully meet the needs of the equipment load layer, through the coordination of the intelligent scheduling layer, the photovoltaic management layer and the energy storage management layer can jointly provide electricity for the equipment load layer, maximizing the use of photovoltaic power generation as a clean energy, reducing dependence on the power grid, and improving energy utilization efficiency. The above scheme realizes the refined control of power transmission between photovoltaic power generation, energy storage equipment and equipment load layer, which helps to improve the intelligence level of the building photovoltaic storage and charging system, so that it can better adapt to changes in energy supply and demand and achieve efficient and energy-saving operation.

[0045] Optionally, the electric energy dispatching strategy is used to instruct the photovoltaic management layer, the energy storage management layer, and the power grid management layer to transmit electric energy to the device load layer, including:

[0046] The intelligent scheduling layer generates fourth predicted power supply data to be transmitted to the equipment load layer according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within the preset future time period;

[0047] The intelligent scheduling layer generates sixth predicted power supply data to be transmitted to the device load layer according to the remaining power data and the preset remaining power threshold, so as to instruct the energy storage management layer to transmit the power of the sixth predicted power supply data to the device load layer within the preset future time period;

[0048] The intelligent scheduling layer determines the seventh predicted power supply data based on the predicted power load data, the predicted photovoltaic power generation data and the sixth predicted power supply data to instruct the power grid management layer to transmit the electric energy of the seventh predicted power supply data to the equipment load layer within the preset future time period.

[0049] In the above scheme, the intelligent dispatching layer determines and allocates the proportion of power supply from each energy source based on the predicted photovoltaic power generation data, the remaining power data, and the predicted power load data, making energy utilization more efficient and avoiding energy waste and the risk of over-reliance on a certain energy source. By making full use of photovoltaic power generation, rationally dispatching energy storage equipment, and optimizing power grid power supply, this strategy helps reduce the electricity bill of buildings, improve energy utilization efficiency, and thus improve overall economic benefits.

[0050] Optionally, the electric energy dispatching strategy is used to instruct the photovoltaic management layer and the power grid management layer to transmit electric energy to the equipment load layer and the energy storage management layer, including:

[0051] The intelligent scheduling layer generates fourth predicted power supply data to be transmitted to the equipment load layer according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within the preset future time period;

[0052] The intelligent scheduling layer determines the eighth predicted power supply data based on the predicted power load data and the predicted photovoltaic power generation data to instruct the power grid management layer to transmit the electric energy of the eighth predicted power supply data to the equipment load layer within the preset future time period.

[0053] In the above scheme, when photovoltaic power generation is insufficient, the intelligent dispatching layer can determine the amount of power that the grid management layer needs to transmit to the equipment load layer (i.e., the eighth predicted power supply data) based on the predicted power load data and predicted photovoltaic power generation data. This optimized power supply strategy helps reduce the load pressure of the grid while ensuring the balance of power supply and demand within the building.

[0054] In a second aspect, the present application provides a building photovoltaic storage and charging management system, including: an intelligent scheduling layer, a photovoltaic management layer, an energy storage management layer, a power grid management layer and an equipment load layer, wherein the intelligent scheduling layer is connected to the photovoltaic management layer, the energy storage management layer and the equipment load layer respectively;

[0055] The photovoltaic management layer obtains weather data within a preset future period, determines predicted photovoltaic power generation data for the preset future period based on the weather data, and sends the predicted photovoltaic power generation data to the intelligent scheduling layer;

[0056] The equipment load layer determines the predicted power load data for the preset future period according to the historical load monitoring data, and sends the predicted power load data to the intelligent scheduling layer;

[0057] The energy storage management layer obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer;

[0058] The intelligent scheduling layer determines the power scheduling strategy within the preset future time period based on the predicted photovoltaic power generation data, the predicted power load data and the remaining power data. The power scheduling strategy is used to indicate the direction of power transmission between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer.

[0059] In a third aspect, the present application provides an electronic device, including:

[0060] processor; and,

[0061] A memory, configured to store executable instructions of the processor;

[0062] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.

[0063] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0064] The hierarchical scheduling method for a low-carbon building photovoltaic storage and charging system provided in the present application obtains weather data within a preset future time period through the photovoltaic management layer, and determines the predicted photovoltaic power generation data for the preset future time period based on the weather data, determines the predicted power load data for the preset future time period based on the historical load monitoring data through the equipment load layer, and obtains the current remaining power data of the energy storage device through the energy storage management layer. Then, the intelligent scheduling layer uses the preset power transmission scheduling model, and determines the power scheduling strategy within the preset future time period based on the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, thereby indicating the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer within the preset future time period, thereby effectively matching the photovoltaic power generation with the building power load, realizing real-time optimized scheduling of power to cope with various situations, which not only reduces the energy cost of the building, but also improves the energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0066] Figure 1 This is a flowchart of a hierarchical scheduling method for a low-carbon building solar storage and charging system according to an example embodiment of the present application;

[0067] Figure 2 is a flow chart of a hierarchical scheduling method for a low-carbon building solar-storage-charging system according to another exemplary embodiment of the present application;

[0068] Figure 3 is a structural schematic diagram of a building solar energy storage and charging management system according to an exemplary embodiment of the present application;

[0069] Figure 4 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application.

[0070] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0072] In order to solve the above problems, the embodiment provided in this application designs a building photovoltaic storage and charging management system, which includes an intelligent scheduling layer, a photovoltaic management layer, an energy storage management layer, a power grid management layer, and an equipment load layer. This hierarchical design enables each management layer to perform its duties and cooperate with each other to jointly achieve efficient management and scheduling of electric energy in the building. Among them, the specific ideas for hierarchical scheduling of each system are as follows:

[0073] The photovoltaic management team obtains weather data (including light intensity, ambient temperature, light angle, etc.) in a preset future period and combines it with a preset algorithm model to accurately predict the photovoltaic power generation in that period. This prediction mechanism fully considers the impact of environmental factors on photovoltaic power generation and improves the accuracy of the prediction.

[0074] The equipment load layer uses data analysis and prediction algorithms based on historical load monitoring data to predict future power loads. By generating historical load power consumption sequences and determining prediction feature weight values, the prediction accuracy is further improved, providing a reliable basis for power dispatch.

[0075] As the core management layer, the intelligent dispatching layer comprehensively processes data from the photovoltaic management layer, the equipment load layer, and the energy storage management layer, and uses the preset power transmission dispatching model to formulate efficient power dispatching strategies. These strategies take into account multiple factors such as photovoltaic power generation, power load, and remaining power of energy storage equipment, and achieve efficient use of energy through reasonable power distribution and transmission. Specific strategies include:

[0076] When photovoltaic power generation is sufficient, priority is given to meeting the needs of the equipment load layer, and excess electricity is transmitted to the energy storage management layer or the grid management layer as appropriate.

[0077] When photovoltaic power generation is insufficient, the intelligent scheduling layer will flexibly adjust the direction of power transmission according to the remaining power of the energy storage equipment and the power supply conditions of the grid to ensure the balance of power supply and demand in the building.

[0078] By introducing the intelligent scheduling layer, intelligent management of the building solar storage and charging system is realized. The intelligent scheduling layer can adjust the scheduling strategy in real time to cope with various changes in energy supply and demand, and improve the stability and reliability of the system. At the same time, this automated management significantly reduces labor costs and improves the efficiency of energy management.

[0079] By optimizing the power dispatch, the embodiments provided in this application not only reduce the energy cost of the building, but also improve the energy utilization efficiency, achieving the goal of low carbon and environmental protection. In addition, by reasonably arranging the proportion of photovoltaic power generation, energy storage and power grid power supply, the electricity bill expenditure of the building is further reduced, and the overall economic benefits are improved.

[0080] In summary, the embodiments provided in this application provide a comprehensive solution for the efficient and stable operation of the building photovoltaic storage and charging system through an intelligent system architecture, an efficient prediction mechanism, a flexible power scheduling strategy and automated management means, thereby promoting efficient energy utilization and low carbon emissions.

[0081] Figure 1 FIG. 1 is a flow chart of a method for hierarchical scheduling of a low-carbon building solar-storage-charging system according to an exemplary embodiment of the present application. Figure 1 As shown, the hierarchical scheduling method of the low-carbon building photovoltaic storage and charging system provided in this embodiment includes:

[0082] S101. The photovoltaic management layer obtains weather data for a preset future period, and determines predicted photovoltaic power generation data for the preset future period based on the weather data.

[0083] The method provided in the embodiment of the present application can be applied to a building photovoltaic storage and charging management system. The building photovoltaic storage and charging management system includes an intelligent scheduling layer, a photovoltaic management layer, an energy storage management layer, a power grid management layer and an equipment load layer. The intelligent scheduling layer is connected to the photovoltaic management layer, the energy storage management layer and the equipment load layer respectively. It can be seen that the building photovoltaic storage and charging management system is mainly composed of five levels: the intelligent scheduling layer, the photovoltaic management layer, the energy storage management layer, the power grid management layer and the equipment load layer. As the core, the intelligent scheduling layer is responsible for receiving data from each management layer, formulating an electric energy scheduling strategy based on these data, and then sending scheduling instructions to each management layer.

[0084] In this step, the photovoltaic management layer obtains weather data within a preset future period, determines the predicted photovoltaic power generation data for the preset future period based on the weather data, and sends the predicted photovoltaic power generation data to the intelligent scheduling layer.

[0085] Specifically, before the start of a preset future period (such as the next day, the next week, etc.), the photovoltaic management layer first obtains weather data for that period through a meteorological interface or a local meteorological station, including but not limited to solar radiation intensity, temperature, cloud cover, etc. Subsequently, the photovoltaic power generation forecasting model trained in advance is used to calculate the forecast photovoltaic power generation data for that period based on these weather data, and these data are sent to the intelligent scheduling layer in real time.

[0086] S102. The equipment load layer determines the predicted power load data for a preset future period based on the historical load monitoring data.

[0087] In this step, the equipment load layer determines the predicted power load data for a preset future period based on the historical load monitoring data, and sends the predicted power load data to the intelligent scheduling layer.

[0088] Specifically, the equipment load layer uses load forecasting algorithms (such as time series analysis, machine learning models, etc.) based on historical load monitoring data to estimate the predicted power load data for future periods. These data reflect the power demand of various types of equipment in the building in the future period, which is crucial for formulating power scheduling strategies. After the prediction is completed, the equipment load layer sends the predicted power load data to the intelligent scheduling layer.

[0089] S103: The energy storage management layer obtains the current remaining power data of the energy storage device.

[0090] In this step, the energy storage management layer obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer.

[0091] Specifically, the energy storage management layer regularly detects the status of the energy storage equipment, including the remaining power of the battery, health status, etc. After receiving the query request from the intelligent scheduling layer, the energy storage management layer uploads the current remaining power data to the intelligent scheduling layer so that the energy storage capacity of the energy storage equipment can be considered when formulating the scheduling strategy.

[0092] S104, the intelligent scheduling layer uses a preset power transmission scheduling model and determines a power scheduling strategy within a preset future time period based on predicted photovoltaic power generation data, predicted power load data, and remaining power data.

[0093] In this step, the intelligent scheduling layer uses the preset power transmission scheduling model and determines the power scheduling strategy in the preset future period based on the predicted photovoltaic power generation data, predicted power load data and remaining power data. The power scheduling strategy is used to indicate the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer. The intelligent scheduling layer sends specific scheduling instructions to the photovoltaic management layer, the energy storage management layer, the power grid management layer and the equipment load layer according to the formulated power scheduling strategy. After receiving the instructions, each management layer performs the corresponding power transmission operation as required to achieve power balance and optimized scheduling within the building.

[0094] In the first case, if the first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than the first ratio threshold, and the remaining power data is less than the preset remaining power, the power scheduling strategy is used to instruct the photovoltaic management layer to transmit power to the equipment load layer and the energy storage management layer, wherein the first ratio threshold is a value greater than 1.

[0095] Furthermore, the intelligent scheduling layer generates first predicted power supply data to be transmitted to the equipment load layer based on the predicted power load data, so as to instruct the photovoltaic management layer to transmit the power of the first predicted power supply data to the equipment load layer within a preset future period. The intelligent scheduling layer generates second predicted power supply data to be transmitted to the energy storage management layer based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer to transmit the power of the second predicted power supply data to the energy storage management layer within a preset future period.

[0096] Specifically, after receiving the predicted power load data, the intelligent scheduling layer will determine the first predicted power supply data that needs to be directly supplied to the equipment load layer by the photovoltaic management layer based on the current power demand of the building and the predicted photovoltaic power generation. Then, the intelligent scheduling layer sends the first predicted power supply data to the photovoltaic management layer, and the photovoltaic management layer transmits the corresponding amount of power to the equipment load layer within the preset future time period based on the data. This process ensures that the photovoltaic power generation system can stably and reliably provide the required power to the equipment load layer through real-time monitoring and adjustment by the intelligent scheduling layer.

[0097] The intelligent dispatching layer calculates the remaining electric energy available for energy storage management based on the predicted photovoltaic power generation data and the first predicted electric energy supply data. The intelligent dispatching layer generates the second predicted electric energy supply data transmitted to the energy storage management layer based on the remaining predicted photovoltaic power generation data and the actual needs of the energy storage management layer (such as the current remaining electric energy of the energy storage equipment, energy storage efficiency, etc.). This data is intended to guide the photovoltaic management layer to transmit excess electric energy to the energy storage management layer for storage for subsequent use after meeting the needs of the equipment load layer.

[0098] The intelligent dispatching layer sends the second predicted power supply data to the photovoltaic management layer, and the photovoltaic management layer transmits power to the energy storage management layer according to the data in the preset future period. Through this process, the energy storage equipment can make full use of the surplus resources of photovoltaic power generation, realize the storage and reuse of power, and improve the overall efficiency of the building energy system.

[0099] In the above scheme, by generating the first predicted power supply data transmitted to the equipment load layer according to the predicted power load data, and generating the second predicted power supply data transmitted to the energy storage management layer according to the predicted photovoltaic power generation data and the first predicted power supply data, the reasonable distribution and efficient use of electric energy are ensured. When transmitting electric energy to the energy storage management layer, the intelligent scheduling layer reasonably determines the charging amount of the energy storage device according to the actual situation of photovoltaic power generation and the predicted power load demand. This helps to optimize the charging strategy of the energy storage device, ensure that the energy storage device can provide sufficient power support when needed, and avoid energy waste and equipment loss caused by overcharging. In addition, through the preset power transmission scheduling model and predicted data, the intelligent scheduling layer can quickly formulate and execute the power scheduling strategy. This efficient response speed helps the system to quickly adapt to changes in energy supply and demand, and ensure the stable operation and efficient operation of various equipment in the building. In addition, the intelligent scheduling layer can flexibly adjust the power distribution strategy according to different energy supply and demand conditions to meet the different needs of the equipment load layer and the energy storage management layer. This flexibility helps the system better cope with various complex situations and improve the overall operation efficiency. It can be seen that by giving priority to the use of clean energy such as photovoltaic power generation and rationally optimizing the charging strategy of energy storage equipment, the above solution can help reduce fossil energy consumption and carbon emissions.

[0100] In the second case, if the first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than the first ratio threshold, and the remaining power data is greater than the preset remaining power, the power scheduling strategy is used to instruct the photovoltaic management layer to transmit power to the equipment load layer and the grid management layer.

[0101] Furthermore, the intelligent dispatching layer generates first predicted power supply data to be transmitted to the equipment load layer based on the predicted power load data, so as to instruct the photovoltaic management layer to transmit the power of the first predicted power supply data to the equipment load layer within a preset future period. The intelligent dispatching layer generates third predicted power supply data to be transmitted to the power grid management layer based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer to transmit the power of the third predicted power supply data to the power grid management layer within a preset future period.

[0102] Specifically, after receiving the predicted power load data, the intelligent dispatching layer determines the first predicted power supply data that needs to be directly supplied to the equipment load layer by the photovoltaic management layer in the preset future period, based on factors such as the power consumption priority of the building and the predicted situation of photovoltaic power generation. This data is intended to ensure that the basic power demand of the equipment load layer is met while minimizing dependence on the traditional power grid.

[0103] The intelligent dispatching layer sends the first predicted power supply data to the photovoltaic management layer, which then transmits power to the equipment load layer stably within the preset future period based on the data. This process is monitored and adjusted in real time by the intelligent dispatching layer to ensure that the photovoltaic power generation system can efficiently and accurately meet the power demand of the equipment load layer.

[0104] The photovoltaic management layer sends the predicted photovoltaic power generation data to the intelligent dispatching layer, which reflects the power generation forecast of the photovoltaic power generation system in the future period. The intelligent dispatching layer calculates the remaining power that can be transmitted to the power grid management layer after meeting the needs of the equipment load layer based on the predicted photovoltaic power generation data and the first predicted power supply data.

[0105] The intelligent dispatching layer generates the third predicted power supply data for transmission to the grid management layer based on the remaining predicted photovoltaic power generation data and the actual needs of the grid management layer (such as the load situation of the grid, electricity price policy, etc.). This data is intended to guide the photovoltaic management layer to transmit excess power to the grid management layer after meeting the needs of the equipment load layer, so as to achieve optimal utilization of power and maximize benefits.

[0106] In the above scheme, by transmitting excess power to the grid management layer, it helps to balance the overall load of the grid and reduce the pressure on the grid during peak hours, thereby helping to improve the stability and reliability of the grid and reduce the risk of power outages caused by excessive grid load. In addition, transmitting excess power to the grid management layer not only helps to balance the grid load, but also may bring certain economic benefits to the building. By participating in the power trading of the grid or obtaining subsidies, the building can further reduce operating costs and improve overall economic benefits. In addition, the intelligent scheduling layer can quickly adjust the power transmission strategy based on real-time data and prediction results to meet the different needs of the equipment load layer and the grid management layer.

[0107] In the third case, if the first ratio between the predicted photovoltaic power generation data and the predicted electricity load data is less than the first ratio threshold, and the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted electricity load data is greater than the first ratio threshold, then the electric energy scheduling strategy is used to instruct the photovoltaic management layer and the energy storage management layer to transmit electric energy to the equipment load layer.

[0108] Furthermore, the intelligent scheduling layer generates fourth predicted power supply data for transmission to the equipment load layer based on the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within a preset future period. The intelligent scheduling layer generates fifth predicted power supply data for transmission to the energy storage management layer based on the predicted power load data and the predicted photovoltaic power generation data, so as to instruct the energy storage management layer to transmit the power of the fifth predicted power supply data to the equipment load layer within a preset future period.

[0109] Specifically, after receiving the predicted photovoltaic power generation data, the intelligent dispatching layer first determines the amount of electricity to be directly transmitted from the photovoltaic management layer to the equipment load layer in the preset future period based on the power demand of the building, the priority of the equipment load layer, and the predicted photovoltaic power generation, i.e., the fourth predicted power supply data. This data is intended to maximize the use of photovoltaic power generation, give priority to meeting the power demand of the equipment load layer, and reduce dependence on the traditional power grid.

[0110] The intelligent dispatching layer sends the fourth predicted power supply data to the photovoltaic management layer, and the photovoltaic management layer transmits power to the equipment load layer stably within the preset future period based on the data. Through real-time monitoring and adjustment, it ensures that the photovoltaic power generation system can efficiently and accurately meet the power demand of the equipment load layer.

[0111] The predicted power load data provided by the equipment load layer is another key factor in formulating a comprehensive power dispatch strategy. This data reflects the power demand of the building in the future period. When the intelligent dispatch layer generates power data to be transmitted to the energy storage management layer, it will comprehensively consider the predicted power load data and the predicted photovoltaic power generation data to ensure the rationality and effectiveness of power dispatch.

[0112] Based on the predicted power load data and predicted photovoltaic power generation data, the intelligent dispatching layer calculates the amount of electricity that will be supplemented and transmitted from the energy storage management layer to the equipment load layer in the preset future period, which is the fifth predicted power supply data. This data is intended to make up for the fact that photovoltaic power generation may not be able to meet all the needs of the equipment load layer during a specific period of time, and to ensure the stability of power supply through the discharge of energy storage equipment.

[0113] The intelligent scheduling layer sends the fifth predicted power supply data to the energy storage management layer, and the energy storage management layer transmits corresponding power to the equipment load layer within a preset future time period based on the data.

[0114] By working in collaboration with the photovoltaic management system, the energy storage management system can provide necessary power support when photovoltaic power generation is insufficient, ensuring the continuity and reliability of the building's power supply.

[0115] In the above scheme, the intelligent scheduling layer generates the fifth predicted power supply data transmitted to the energy storage management layer based on the predicted power load data and the predicted photovoltaic power generation data. This strategy can accurately control the discharge process of the energy storage management layer, thereby optimizing the utilization rate of the energy storage equipment and improving the overall energy utilization efficiency. When the photovoltaic power generation is not enough to fully meet the needs of the equipment load layer, through the coordination of the intelligent scheduling layer, the photovoltaic management layer and the energy storage management layer can jointly provide electricity for the equipment load layer, maximizing the use of photovoltaic power generation as a clean energy, reducing dependence on the power grid, and improving energy utilization efficiency. The above scheme realizes the refined control of power transmission between photovoltaic power generation, energy storage equipment and equipment load layer, which helps to improve the intelligence level of the building photovoltaic storage and charging system, so that it can better adapt to changes in energy supply and demand and achieve efficient and energy-saving operation.

[0116] In the fourth case, if the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is less than the first ratio threshold, and the remaining electric energy data is greater than the preset remaining power, then the electric energy scheduling strategy is used to instruct the photovoltaic management layer, the energy storage management layer and the power grid management layer to transmit electric energy to the equipment load layer.

[0117] Furthermore, the intelligent scheduling layer generates fourth predicted power supply data for transmission to the device load layer based on the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the device load layer within a preset future period. The intelligent scheduling layer generates sixth predicted power supply data for transmission to the device load layer based on the remaining power data and the preset remaining power threshold, so as to instruct the energy storage management layer to transmit the power of the sixth predicted power supply data to the device load layer within a preset future period. The intelligent scheduling layer determines the seventh predicted power supply data based on the predicted power load data, the predicted photovoltaic power generation data, and the sixth predicted power supply data, so as to instruct the power grid management layer to transmit the power of the seventh predicted power supply data to the device load layer within a preset future period.

[0118] Specifically, the intelligent dispatching layer first determines the power generation capacity of the photovoltaic power generation system in the future period based on the predicted photovoltaic power generation data, and generates the fourth predicted power supply data transmitted to the equipment load layer accordingly. This data is intended to maximize the use of photovoltaic power generation, directly meet part or all of the power demand of the equipment load layer, and reduce dependence on traditional power grids. The intelligent dispatching layer sends the fourth predicted power supply data to the photovoltaic management layer, and the photovoltaic management layer transmits power to the equipment load layer stably within the preset future period based on the data.

[0119] The energy storage management layer monitors the remaining power data of the energy storage device in real time and sends the data to the intelligent scheduling layer. The intelligent scheduling layer evaluates the amount of power that the energy storage device can provide in the future period based on the remaining power data and the preset remaining power threshold, and generates the sixth predicted power supply data transmitted to the equipment load layer. This data is intended to utilize the energy storage capacity of the energy storage device to provide necessary power support during periods of insufficient photovoltaic power generation or peak equipment load. The intelligent scheduling layer sends the sixth predicted power supply data to the energy storage management layer, and the energy storage management layer transmits the corresponding power to the equipment load layer in the preset future period based on the data.

[0120] After considering the power supply of the photovoltaic management layer and the energy storage management layer, the intelligent dispatching layer further comprehensively evaluates the power demand gap of the equipment load layer in the future period based on the predicted power load data, predicted photovoltaic power generation data and the sixth predicted power supply data. Based on this evaluation, the intelligent dispatching layer generates the seventh predicted power supply data to instruct the power grid management layer to transmit the corresponding power to the equipment load layer in the preset future period. This data is intended to ensure that when photovoltaic power generation and energy storage equipment cannot meet all power needs, stable power supplements are provided through the power grid management layer to ensure the continuity and reliability of the building's power supply. The intelligent dispatching layer sends the seventh predicted power supply data to the power grid management layer, and the power grid management layer transmits power to the equipment load layer in the preset future period based on the data.

[0121] In the above scheme, the intelligent dispatching layer determines and allocates the proportion of power supply from each energy source based on the predicted photovoltaic power generation data, the remaining power data, and the predicted power load data, making energy utilization more efficient and avoiding energy waste and the risk of over-reliance on a certain energy source. By making full use of photovoltaic power generation, rationally dispatching energy storage equipment, and optimizing power grid power supply, this strategy helps reduce the electricity bill of buildings, improve energy utilization efficiency, and thus improve overall economic benefits.

[0122] In the fifth case, if the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is less than the first ratio threshold, and the remaining electric energy data is less than the preset remaining power, then the electric energy scheduling strategy is used to instruct the photovoltaic management layer and the power grid management layer to transmit electric energy to the equipment load layer and the energy storage management layer.

[0123] Further, the intelligent dispatching layer generates fourth predicted power supply data to be transmitted to the equipment load layer based on the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within a preset future period. The intelligent dispatching layer determines the eighth predicted power supply data based on the predicted power load data and the predicted photovoltaic power generation data, so as to instruct the power grid management layer to transmit the power of the eighth predicted power supply data to the equipment load layer within a preset future period.

[0124] Specifically, the intelligent dispatching layer first evaluates the power generation potential of the photovoltaic power generation system in the future period based on the predicted photovoltaic power generation data, and generates the fourth predicted power supply data transmitted to the equipment load layer. This data is intended to ensure that the photovoltaic power generation system can give priority to meeting the basic power needs of the equipment load layer and reduce the immediate dependence on the traditional power grid. The intelligent dispatching layer sends the fourth predicted power supply data to the photovoltaic management layer, and the photovoltaic management layer uses it to stably transmit power to the equipment load layer in the preset future period.

[0125] While the photovoltaic management layer transmits electric energy to the equipment load layer, the intelligent dispatching layer also needs to consider the overall power supply and demand balance. The intelligent dispatching layer calculates the amount of electric energy that the equipment load layer still needs in the future period based on the predicted power load data and the allocated fourth predicted power supply data (i.e., the electric energy transmitted by the photovoltaic management layer to the equipment load layer).

[0126] Next, the intelligent dispatching layer combines the predicted photovoltaic power generation data to determine the eighth predicted power supply data that the grid management layer needs to transmit to the equipment load layer to ensure that the power demand of the equipment load layer is fully met. At the same time, if the remaining power data of the energy storage management layer is lower than the preset threshold, the intelligent dispatching layer will also consider allocating part of the grid power to the energy storage management layer for charging to enhance the system's energy storage capacity and prepare for future peak power demand. The intelligent dispatching layer sends the eighth predicted power supply data to the grid management layer, and the grid management layer transmits power to the corresponding target within the preset future period based on the data.

[0127] In this embodiment, weather data within a preset future time period is obtained through the photovoltaic management layer, and predicted photovoltaic power generation data for the preset future time period is determined based on the weather data. Predicted power load data for the preset future time period is determined through the equipment load layer based on historical load monitoring data, and the current remaining power data of the energy storage device is obtained through the energy storage management layer. Then, the intelligent scheduling layer uses a preset power transmission scheduling model and determines the power scheduling strategy within the preset future time period based on the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, thereby indicating the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer within the preset future time period, thereby effectively matching photovoltaic power generation with building power load, realizing real-time optimal scheduling of power to cope with various situations, which not only reduces the energy cost of the building, but also improves energy utilization efficiency.

[0128] Figure 2 FIG. 1 is a flow chart of a method for hierarchical scheduling of a low-carbon building solar-storage-charging system according to another exemplary embodiment of the present application. Figure 2 As shown, the hierarchical scheduling method of the low-carbon building photovoltaic storage and charging system provided in this embodiment includes:

[0129] S201. The photovoltaic management layer obtains weather data for a preset future period.

[0130] Before the start of a preset future period (such as the next day, the next week, etc.), the photovoltaic management system first obtains weather data for that period through a meteorological interface or a local meteorological station, including but not limited to solar radiation intensity, temperature, cloud cover, and light angle.

[0131] S202: determining a temperature influence factor curve according to the ambient temperature data in the weather data, and determining a light angle influence factor curve according to the light angle data in the weather data.

[0132] Optionally, the temperature influence factor curve may be determined using formula 1 according to the ambient temperature data in the weather data. , the formula 1 is:

[0133]

[0134] in, The ambient temperature data at the time node Ambient temperature is the preset reference ambient temperature, is the preset temperature attenuation coefficient.

[0135] Optionally, Formula 2 may be used to determine the illumination angle influence factor curve according to the illumination angle data in the weather data. , the formula 2 is:

[0136]

[0137] in, The illumination angle data at the time node The lighting angle is To calibrate the optimal illumination angle, Adjustment factor for preset angle.

[0138] Specifically, by comprehensively considering multiple factors such as ambient temperature, light intensity and light angle in weather data, the complexity and dynamics of the actual photovoltaic power generation process can be more comprehensively reflected. This multi-dimensional consideration makes the prediction results closer to the actual situation, thereby significantly improving the accuracy of photovoltaic power generation prediction.

[0139] Each parameter in the above formula (such as preset reference ambient temperature, preset temperature attenuation coefficient, calibrated optimal illumination angle and preset angle adjustment coefficient) can be flexibly adjusted according to different environmental conditions, thereby enhancing the system's adaptability to different environments. This allows the prediction model to maintain a high prediction accuracy in different regions, seasons and weather conditions.

[0140] It is worth noting that in the above formula 1, the impact of ambient temperature on photovoltaic power generation efficiency is accurately quantified by introducing a preset temperature attenuation coefficient and a preset reference ambient temperature. This quantification method enables the system to more accurately evaluate the changes in photovoltaic power generation performance under different ambient temperatures, providing a more scientific basis for predicting photovoltaic power generation. By adjusting the value of the preset temperature attenuation coefficient, the system can fine-tune the model according to specific application scenarios and environmental conditions to adapt to the temperature change characteristics of different regions and seasons. This flexibility enables the prediction model to maintain a high prediction accuracy under different conditions.

[0141] Moreover, the nonlinear effect of ambient temperature on photovoltaic power generation efficiency can be better simulated in the form of exponential function. Compared with simple linear models, this formula can better reflect the actual physical process, thereby reducing the prediction error introduced by model simplification. Accurate prediction of ambient temperature influencing factors helps the system to arrange photovoltaic power generation and energy storage plans more reasonably. Under high or low temperature conditions, the system can take measures in advance to reduce the decline in power generation efficiency caused by temperature, thereby avoiding unnecessary energy waste and improving the overall economy of the system. Therefore, by improving the prediction accuracy of photovoltaic power generation, the system can more effectively utilize renewable energy and reduce dependence on fossil fuels, thereby reducing carbon emissions and promoting low-carbon and environmentally friendly operation of buildings.

[0142] It is worth noting that in the above formula 2, by comprehensively considering the illumination angle and calibrating the optimal illumination angle, and introducing the preset angle adjustment coefficient, the influence of the illumination angle on the photovoltaic power generation efficiency is finely quantified. This quantification method can more accurately reflect the changes in photovoltaic power generation performance under different illumination angles, thereby improving the accuracy of predicting photovoltaic power generation. The introduction of the preset angle adjustment coefficient enables the model to be adjusted according to the illumination characteristics of different regions, seasons and times, and enhances the model's adaptability to different illumination conditions. This adaptability ensures the accuracy and reliability of the prediction model in different environments. Accurate prediction of the illumination angle influencing factor helps the system to plan photovoltaic power generation plans more accurately. When the illumination angle is not conducive to power generation, the system can take measures in advance (such as adjusting the angle of photovoltaic panels or increasing the use of energy storage equipment) to ensure maximum energy utilization and reduce power generation losses caused by poor illumination angles. Combined with the real-time data processing capabilities of the intelligent scheduling layer, the illumination angle influencing factor predicted by formula 3 can support a more dynamic power scheduling strategy. When the light angle changes, the system can respond quickly and adjust the power distribution plan to adapt to the new light conditions, ensuring the stable operation and efficient work of various equipment in the building.

[0143] S203: Determine predicted photovoltaic power generation data according to the light intensity data, the temperature influence factor curve, and the light angle influence factor curve in the weather data.

[0144] Specifically, the predicted photovoltaic power generation data may be determined using Formula 3 according to the light intensity data, the ambient temperature data, and the light angle data in the weather data, wherein the predicted photovoltaic power generation data includes the predicted photovoltaic power generation. Formula 3 is:

[0145]

[0146] in, To predict the predicted photovoltaic power generation in the photovoltaic power generation data, To preset the light intensity curve in the weather data for the future period, To preset the photoelectric conversion efficiency, It is the temperature influence factor curve in the weather data in the preset future period. It is the influence factor curve of the light angle in the weather data in the preset future period. is the current time node, The end time node of the preset future period.

[0147] Through the above formula 3, by comprehensively considering multiple key environmental factors (light intensity, ambient temperature, and light angle), and combining the photovoltaic system's photoelectric conversion efficiency and photovoltaic panel area, the photovoltaic power generation in the preset future period can be accurately predicted. This prediction method that comprehensively considers multiple environmental parameters is more accurate than a single factor prediction, which helps the building photovoltaic storage system to plan the use and storage of electricity more reasonably. In addition, accurate predicted photovoltaic power generation data provides an important decision-making basis for the intelligent scheduling layer. By updating environmental data in real time and recalculating the predicted photovoltaic power generation, the intelligent scheduling layer can dynamically adjust the power scheduling strategy to respond to real-time changes in lighting conditions, ambient temperature, and angle, and ensure the balance of power supply and demand in the building.

[0148] In addition, the above formula 1 can not only be used for prediction, but also guide the design and optimization of photovoltaic systems. For example, by comparing the predicted photovoltaic power generation under different illumination angles, photovoltaic panel layouts and areas, the optimal photovoltaic system configuration can be selected to achieve the best power generation effect.

[0149] S204. The equipment load layer obtains the load power consumption corresponding to each time node in the historical load monitoring data to generate a historical load power consumption sequence.

[0150] Specifically, the equipment load layer obtains historical load monitoring data ,in, The equipment load layer is the first in history The load power consumption obtained at each time node, The number of historical load power consumption is saved for preset.

[0151] The equipment load layer uses formula 4 and is based on historical load monitoring data. Determine the predicted power load power consumption in the predicted power load data for a preset future period , Formula 4 is:

[0152]

[0153] in, is the predicted feature weight value, is the predicted power load consumption in the previous forecast period, It is the preset speed change adjustment factor.

[0154] It is worth noting that the above formula 4 dynamically adjusts the weights of historical data and the last predicted value in predicting future load by calculating the predicted feature weight value. This dynamic weight adjustment mechanism enables the prediction model to adapt to the uncertainty of load changes in different time periods, improving the flexibility and accuracy of the prediction.

[0155] By introducing a preset speed change adjustment factor, Formula 4 can capture the speed and trend of load changes, making the prediction results closer to the actual load changes, which helps the building solar storage and charging system to more accurately estimate future electricity demand and thus formulate reasonable electricity scheduling strategies.

[0156] When historical load data Data from the previous time point When the difference between is large, it means that the load has changed significantly. At this time, the prediction feature weight value will tend to 1, that is, the weight of the new data point in the prediction increases, so that the model can quickly respond to sudden changes in load and adjust the prediction results in time to ensure the accuracy of the prediction.

[0157] Historical load data Data from the previous time point When the difference between is small, the prediction feature weight value will tend to 0, which means that the prediction result depends more on past data and, which helps to maintain the stability and accuracy of the prediction when the load changes little, and avoids the increase of system errors caused by the accumulation of multiple predictions.

[0158] By adaptively adjusting the weights of new and old data points in the prediction, Formula 4 can maintain high prediction accuracy in an environment with complex and uncertain load changes. This dynamic adjustment mechanism makes the prediction model more flexible and can better adapt to the diversity of actual load changes.

[0159] S205. Determine a prediction feature weight value based on the historical load power consumption sequence, so as to determine the predicted power load power consumption corresponding to the preset future time period based on the historical load power consumption sequence, the prediction feature weight value and the predicted power load power consumption of the previous prediction cycle.

[0160] Specifically, the prediction feature weight value is determined according to the historical load power consumption sequence, so as to determine the predicted power load power consumption corresponding to the preset future time period according to the historical load power consumption sequence, the prediction feature weight value and the predicted power load power consumption of the previous prediction cycle. The predicted power load data of the preset future time period includes the predicted power load power consumption.

[0161] S206: The energy storage management layer obtains the current remaining power data of the energy storage device.

[0162] In this step, the energy storage management layer obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer.

[0163] Specifically, the energy storage management layer regularly detects the status of the energy storage equipment, including the remaining power of the battery, health status, etc. After receiving the query request from the intelligent scheduling layer, the energy storage management layer uploads the current remaining power data to the intelligent scheduling layer so that the energy storage capacity of the energy storage equipment can be considered when formulating the scheduling strategy.

[0164] S207, the intelligent scheduling layer uses a preset power transmission scheduling model and determines a power scheduling strategy within a preset future time period based on predicted photovoltaic power generation data, predicted power load data, and remaining power data.

[0165] In this step, the intelligent scheduling layer uses the preset power transmission scheduling model and determines the power scheduling strategy in the preset future period based on the predicted photovoltaic power generation data, predicted power load data and remaining power data. The power scheduling strategy is used to indicate the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer. The intelligent scheduling layer sends specific scheduling instructions to the photovoltaic management layer, the energy storage management layer, the power grid management layer and the equipment load layer according to the formulated power scheduling strategy. After receiving the instructions, each management layer performs the corresponding power transmission operation as required to achieve power balance and optimized scheduling within the building.

[0166] Figure 3 FIG. 1 is a schematic diagram of a building solar energy storage and charging management system according to an exemplary embodiment of the present application. Figure 3 As shown, the building solar energy storage and charging management system 300 provided in this embodiment includes:

[0167] It includes an intelligent scheduling layer 310, a photovoltaic management layer 320, an energy storage management layer 330, a power grid management layer 340 and an equipment load layer 350, wherein the intelligent scheduling layer 310 is connected to the photovoltaic management layer 320, the energy storage management layer 330 and the equipment load layer 350 respectively;

[0168] The photovoltaic management layer 320 obtains weather data within a preset future period, determines predicted photovoltaic power generation data for the preset future period according to the weather data, and sends the predicted photovoltaic power generation data to the intelligent scheduling layer 310;

[0169] The equipment load layer 350 determines the predicted power load data for the preset future period according to the historical load monitoring data, and sends the predicted power load data to the intelligent scheduling layer 310;

[0170] The energy storage management layer 330 obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer 310;

[0171] The intelligent scheduling layer 310 utilizes a preset power transmission scheduling model, and determines the power scheduling strategy within the preset future time period based on the predicted photovoltaic power generation data, the predicted power load data and the remaining power data. The power scheduling strategy is used to indicate the power transmission direction between the photovoltaic management layer 320, the equipment load layer 350, the power grid management layer 340 and the energy storage management layer 330.

[0172] Optionally, the photovoltaic management layer 320 is specifically used for:

[0173] Determine a temperature influence factor curve according to the ambient temperature data in the weather data;

[0174] Determine an illumination angle influencing factor curve according to the illumination angle data in the weather data;

[0175] The predicted photovoltaic power generation data is determined according to the light intensity data in the weather data, the temperature influence factor curve, and the light angle influence factor curve.

[0176] Optionally, the equipment load layer 350 is specifically used for:

[0177] Obtaining the load power consumption corresponding to each time node in the historical load monitoring data to generate a historical load power consumption sequence;

[0178] The prediction feature weight value is determined according to the historical load power consumption sequence, so as to determine the predicted power load power consumption corresponding to the preset future time period according to the historical load power consumption sequence, the prediction feature weight value and the predicted power load power consumption of the previous prediction cycle, and the predicted power load data of the preset future time period includes the predicted power load power consumption.

[0179] Optionally, the intelligent scheduling layer 310 uses a preset power transmission scheduling model and determines a power scheduling strategy in the preset future period according to the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, including:

[0180] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than a first ratio threshold, and the remaining power data is less than the preset remaining power, the power scheduling strategy is used to instruct the photovoltaic management layer 320 to transmit power to the equipment load layer 350 and the energy storage management layer 330, wherein the first ratio threshold is a value greater than 1;

[0181] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than a first ratio threshold, and the remaining power data is greater than the preset remaining power, the power dispatch strategy is used to instruct the photovoltaic management layer 320 to transmit power to the equipment load layer 350 and the power grid management layer 340;

[0182] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, and the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is greater than the first ratio threshold, then the electric energy dispatching strategy is used to instruct the photovoltaic management layer 320 and the energy storage management layer 330 to transmit electric energy to the equipment load layer 350;

[0183] If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is less than the first ratio threshold, and the remaining electric energy data is greater than the preset remaining power, then the electric energy dispatching strategy is used to instruct the photovoltaic management layer 320, the energy storage management layer 330 and the power grid management layer 340 to transmit electric energy to the equipment load layer 350;

[0184] If the first ratio between the predicted photovoltaic power generation data and the predicted electricity load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted electricity load data is less than the first ratio threshold, and the remaining electric energy data is less than the preset remaining power, then the electric energy scheduling strategy is used to instruct the photovoltaic management layer 320 and the power grid management layer 340 to transmit electric energy to the equipment load layer 350 and the energy storage management layer 330.

[0185] Optionally, the intelligent scheduling layer 310 generates first predicted power supply data to be transmitted to the device load layer 350 according to the predicted power load data, so as to instruct the photovoltaic management layer 320 to transmit the power of the first predicted power supply data to the device load layer 350 within the preset future period;

[0186] The intelligent scheduling layer 310 generates second predicted power supply data to be transmitted to the energy storage management layer 330 based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer 320 to transmit the power of the second predicted power supply data to the energy storage management layer 330 within the preset future time period.

[0187] Optionally, the intelligent scheduling layer 310 generates first predicted power supply data to be transmitted to the device load layer 350 according to the predicted power load data, so as to instruct the photovoltaic management layer 320 to transmit the power of the first predicted power supply data to the device load layer 350 within the preset future period;

[0188] The intelligent scheduling layer 310 generates third predicted power supply data for transmission to the power grid management layer 340 based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer 320 to transmit the power of the third predicted power supply data to the power grid management layer 340 within the preset future time period.

[0189] Optionally, the intelligent scheduling layer 310 generates fourth predicted power supply data to be transmitted to the device load layer 350 according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer 320 to transmit the power of the fourth predicted power supply data to the device load layer 350 within the preset future period;

[0190] The intelligent scheduling layer 310 generates fifth predicted power supply data for transmission to the energy storage management layer 330 based on the predicted power load data and the predicted photovoltaic power generation data, so as to instruct the energy storage management layer 330 to transmit the electric energy of the fifth predicted power supply data to the equipment load layer 350 within the preset future time period.

[0191] Optionally, the intelligent scheduling layer 310 generates fourth predicted power supply data to be transmitted to the device load layer 350 according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer 320 to transmit the power of the fourth predicted power supply data to the device load layer 350 within the preset future period;

[0192] The intelligent scheduling layer 310 generates sixth predicted power supply data to be transmitted to the device load layer 350 according to the remaining power data and the preset remaining power threshold, so as to instruct the energy storage management layer 330 to transmit the power of the sixth predicted power supply data to the device load layer 350 within the preset future period;

[0193] The intelligent scheduling layer 310 determines the seventh predicted power supply data based on the predicted electricity load data, the predicted photovoltaic power generation data and the sixth predicted power supply data to instruct the power grid management layer 340 to transmit the electric energy of the seventh predicted power supply data to the equipment load layer 350 within the preset future time period.

[0194] Optionally, the intelligent scheduling layer 310 generates fourth predicted power supply data to be transmitted to the device load layer 350 according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer 320 to transmit the power of the fourth predicted power supply data to the device load layer 350 within the preset future period;

[0195] The intelligent scheduling layer 310 determines the eighth predicted power supply data based on the predicted power load data and the predicted photovoltaic power generation data to instruct the power grid management layer 340 to transmit the electric energy of the eighth predicted power supply data to the equipment load layer 350 within the preset future time period.

[0196] Figure 4 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 4 As shown, an electronic device 400 provided in this embodiment includes: a processor 401 and a memory 402; wherein:

[0197] The memory 402 is used to store computer programs, and the memory may also be a flash memory.

[0198] The processor 401 is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.

[0199] Optionally, the memory 402 may be independent or integrated with the processor 401 .

[0200] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include:

[0201] The bus 403 is used to connect the memory 402 and the processor 401 .

[0202] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0203] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.

[0204] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0205] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A hierarchical scheduling method for a low-carbon building photovoltaic storage and charging system based on artificial intelligence, characterized in that: Applied to a building photovoltaic storage and charging management system, the building photovoltaic storage and charging management system includes an intelligent scheduling layer, a photovoltaic management layer, an energy storage management layer, a power grid management layer and an equipment load layer, and the intelligent scheduling layer is connected to the photovoltaic management layer, the energy storage management layer, the power grid management layer and the equipment load layer respectively; the method includes: The photovoltaic management layer obtains weather data within a preset future period, determines predicted photovoltaic power generation data for the preset future period based on the weather data, and sends the predicted photovoltaic power generation data to the intelligent scheduling layer; The equipment load layer determines the predicted power load data for the preset future period according to the historical load monitoring data, and sends the predicted power load data to the intelligent scheduling layer; The energy storage management layer obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer; The intelligent scheduling layer uses a preset power transmission scheduling model and determines the power scheduling strategy within the preset future time period according to the predicted photovoltaic power generation data, the predicted power load data and the remaining power data. The power scheduling strategy is used to indicate the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer; The photovoltaic management layer obtains weather data in a preset future period, and determines predicted photovoltaic power generation data for the preset future period according to the weather data, including: Determine a temperature influence factor curve according to the ambient temperature data in the weather data; Determine an illumination angle influencing factor curve according to the illumination angle data in the weather data; Formula 3 is used to determine the predicted photovoltaic power generation data according to the light intensity data in the weather data, the temperature influence factor curve, and the light angle influence factor curve, wherein the predicted photovoltaic power generation data includes the predicted photovoltaic power generation, and Formula 3 is: in, is the predicted photovoltaic power generation in the predicted photovoltaic power generation data, is a light intensity curve in the weather data within the preset future period, To preset the photoelectric conversion efficiency, is a temperature influencing factor curve in the weather data within the preset future period, is a light angle influence factor curve in the weather data in the preset future period, is the current time node, The end time node of the preset future period; The step of determining a temperature influence factor curve according to the ambient temperature data in the weather data comprises: Using formula 1, the temperature influence factor curve is determined according to the ambient temperature data in the weather data. , the formula 1 is: in, The ambient temperature data at the time node Ambient temperature To preset the reference ambient temperature, is the preset temperature attenuation coefficient; The step of determining the illumination angle influence factor curve according to the illumination angle data in the weather data comprises: Using formula 2, and according to the illumination angle data in the weather data, determine the illumination angle influence factor curve , the formula 2 is: in, The illumination angle data at the time node The lighting angle is To calibrate the optimal lighting angle, Adjustment factor for preset angle.

2. The artificial intelligence-based low-carbon building solar-storage-charging system hierarchical scheduling method according to claim 1 is characterized in that: The equipment load layer determines the predicted power load data for the preset future period according to the historical load monitoring data, including: The equipment load layer obtains the load power consumption corresponding to each time node in the historical load monitoring data to generate a historical load power consumption sequence; The prediction feature weight value is determined according to the historical load power consumption sequence, so as to determine the predicted power load power consumption corresponding to the preset future time period according to the historical load power consumption sequence, the prediction feature weight value and the predicted power load power consumption of the previous prediction cycle, and the predicted power load data of the preset future time period includes the predicted power load power consumption.

3. The artificial intelligence-based low-carbon building solar-storage-charging system hierarchical scheduling method according to claim 1 or 2, characterized in that: The intelligent scheduling layer uses a preset power transmission scheduling model and determines the power scheduling strategy in the preset future period according to the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, including: If a first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than a first ratio threshold, and the remaining power data is less than a preset remaining power, the power dispatch strategy is used to instruct the photovoltaic management layer to transmit power to the equipment load layer and the energy storage management layer, wherein the first ratio threshold is a value greater than 1; If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is greater than a first ratio threshold, and the remaining power data is greater than the preset remaining power, the power dispatch strategy is used to instruct the photovoltaic management layer to transmit power to the equipment load layer and the power grid management layer; If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, and the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is greater than the first ratio threshold, then the electric energy dispatching strategy is used to instruct the photovoltaic management layer and the energy storage management layer to transmit electric energy to the equipment load layer; If the first ratio between the predicted photovoltaic power generation data and the predicted power load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted power load data is less than the first ratio threshold, and the remaining electric energy data is greater than the preset remaining power, then the electric energy dispatching strategy is used to instruct the photovoltaic management layer, the energy storage management layer and the power grid management layer to transmit electric energy to the equipment load layer; If the first ratio between the predicted photovoltaic power generation data and the predicted electricity load data is less than the first ratio threshold, the second ratio between the sum of the electric energy of the predicted photovoltaic power generation data and the remaining electric energy data and the predicted electricity load data is less than the first ratio threshold, and the remaining electric energy data is less than the preset remaining power, then the electric energy scheduling strategy is used to instruct the photovoltaic management layer and the power grid management layer to transmit electric energy to the equipment load layer and the energy storage management layer.

4. The hierarchical scheduling method for low-carbon building solar-storage-charging system based on artificial intelligence according to claim 3 is characterized in that: The electric energy dispatching strategy is used to instruct the photovoltaic management layer to transmit electric energy to the equipment load layer and the energy storage management layer, including: The intelligent scheduling layer generates first predicted power supply data to be transmitted to the equipment load layer according to the predicted power load data, so as to instruct the photovoltaic management layer to transmit the power of the first predicted power supply data to the equipment load layer within the preset future period; The intelligent scheduling layer generates second predicted power supply data to be transmitted to the energy storage management layer according to the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer to transmit the power of the second predicted power supply data to the energy storage management layer within the preset future time period; Correspondingly, the electric energy dispatching strategy is used to instruct the photovoltaic management layer to transmit electric energy to the equipment load layer and the power grid management layer, including: The intelligent scheduling layer generates first predicted power supply data to be transmitted to the equipment load layer according to the predicted power load data, so as to instruct the photovoltaic management layer to transmit the power of the first predicted power supply data to the equipment load layer within the preset future period; The intelligent scheduling layer generates third predicted power supply data for transmission to the power grid management layer based on the predicted photovoltaic power generation data and the first predicted power supply data, so as to instruct the photovoltaic management layer to transmit the power of the third predicted power supply data to the power grid management layer within the preset future time period.

5. The artificial intelligence-based low-carbon building solar-storage-charging system hierarchical scheduling method according to claim 4 is characterized in that: The electric energy dispatching strategy is used to instruct the photovoltaic management layer and the energy storage management layer to transmit electric energy to the equipment load layer, including: The intelligent scheduling layer generates fourth predicted power supply data to be transmitted to the equipment load layer according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within the preset future time period; The intelligent scheduling layer generates fifth predicted power supply data for transmission to the energy storage management layer based on the predicted power load data and the predicted photovoltaic power generation data, so as to instruct the energy storage management layer to transmit the electric energy of the fifth predicted power supply data to the equipment load layer within the preset future time period.

6. The artificial intelligence-based low-carbon building solar-storage-charging system hierarchical scheduling method according to claim 5 is characterized in that: The electric energy dispatching strategy is used to instruct the photovoltaic management layer, the energy storage management layer, and the power grid management layer to transmit electric energy to the equipment load layer, including: The intelligent scheduling layer generates fourth predicted power supply data to be transmitted to the equipment load layer according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within the preset future time period; The intelligent scheduling layer generates sixth predicted power supply data to be transmitted to the device load layer according to the remaining power data and the preset remaining power threshold, so as to instruct the energy storage management layer to transmit the power of the sixth predicted power supply data to the device load layer within the preset future time period; The intelligent scheduling layer determines the seventh predicted power supply data according to the predicted power load data, the predicted photovoltaic power generation data and the sixth predicted power supply data, so as to instruct the power grid management layer to transmit the power of the seventh predicted power supply data to the equipment load layer within the preset future time period; Correspondingly, the electric energy dispatching strategy is used to instruct the photovoltaic management layer and the power grid management layer to transmit electric energy to the equipment load layer and the energy storage management layer, including: The intelligent scheduling layer generates fourth predicted power supply data to be transmitted to the equipment load layer according to the predicted photovoltaic power generation data, so as to instruct the photovoltaic management layer to transmit the power of the fourth predicted power supply data to the equipment load layer within the preset future time period; The intelligent scheduling layer determines the eighth predicted power supply data based on the predicted power load data and the predicted photovoltaic power generation data to instruct the power grid management layer to transmit the electric energy of the eighth predicted power supply data to the equipment load layer within the preset future time period.

7. A building solar storage and charging management system, characterized in that: include: An intelligent dispatching layer, a photovoltaic management layer, an energy storage management layer, a power grid management layer and an equipment load layer, wherein the intelligent dispatching layer is connected to the photovoltaic management layer, the energy storage management layer and the equipment load layer respectively; The photovoltaic management layer obtains weather data within a preset future period, determines predicted photovoltaic power generation data for the preset future period based on the weather data, and sends the predicted photovoltaic power generation data to the intelligent scheduling layer; The equipment load layer determines the predicted power load data for the preset future period according to the historical load monitoring data, and sends the predicted power load data to the intelligent scheduling layer; The energy storage management layer obtains the current remaining power data of the energy storage device and sends the remaining power data to the intelligent scheduling layer; The intelligent scheduling layer determines the power scheduling strategy within the preset future period according to the predicted photovoltaic power generation data, the predicted power load data and the remaining power data, and the power scheduling strategy is used to indicate the power transmission direction between the photovoltaic management layer, the equipment load layer, the power grid management layer and the energy storage management layer; The photovoltaic management layer obtains weather data in a preset future period, and determines predicted photovoltaic power generation data for the preset future period according to the weather data, including: Determine a temperature influence factor curve according to the ambient temperature data in the weather data; Determine an illumination angle influencing factor curve according to the illumination angle data in the weather data; Formula 3 is used to determine the predicted photovoltaic power generation data according to the light intensity data in the weather data, the temperature influence factor curve, and the light angle influence factor curve, wherein the predicted photovoltaic power generation data includes the predicted photovoltaic power generation, and Formula 3 is: in, is the predicted photovoltaic power generation in the predicted photovoltaic power generation data, is a light intensity curve in the weather data within the preset future period, To preset the photoelectric conversion efficiency, is a temperature influencing factor curve in the weather data within the preset future period, is a light angle influence factor curve in the weather data in the preset future period, is the current time node, The end time node of the preset future period; The step of determining a temperature influence factor curve according to the ambient temperature data in the weather data comprises: Using formula 1, the temperature influence factor curve is determined according to the ambient temperature data in the weather data. , the formula 1 is: in, The ambient temperature data at the time node Ambient temperature To preset the reference ambient temperature, is the preset temperature attenuation coefficient; The step of determining the illumination angle influence factor curve according to the illumination angle data in the weather data comprises: Using formula 2, and according to the illumination angle data in the weather data, determine the illumination angle influence factor curve , the formula 2 is: in, The illumination angle data at the time node The lighting angle is To calibrate the optimal lighting angle, Adjustment factor for preset angle.

8. An electronic device, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

Images