Cloud new energy state prediction scheduling method and system based on deep network

Abstract

The invention relates to the technical field of energy prediction, in particular to a cloud new energy state prediction scheduling method and system based on a deep network. The method comprises the following steps: acquiring cloud new energy network data; performing network topology analysis on the cloud new energy network data to generate cloud new energy network topology data; performing cloud new energy monitoring data acquisition on the cloud new energy network data according to the cloud new energy network topology data to generate standard cloud new energy monitoring data; and performing energy scheduling management stage classification on the standard cloud new energy monitoring data to generate energy scheduling management stage data. Through standardized data integration, full-life-cycle management, real-time dynamic prediction and energy coordination optimization, the problems of insufficient dispersibility, real-time performance and efficiency of cloud new energy state prediction scheduling in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of energy prediction technology, and in particular to a cloud-based new energy state prediction and scheduling method and system based on a deep network. Background Art

[0002] In recent years, with the acceleration of global energy transformation, new energy technologies such as wind power and solar energy have gradually become an important part of power supply. However, the volatility and uncertainty of these new energy sources have brought great challenges to the stable operation of the power system. To address this problem, new energy state prediction and scheduling technology based on deep networks has developed rapidly. Early new energy prediction mainly relied on traditional statistical models and time series analysis methods, which can capture the fluctuation trend of new energy to a certain extent, but the accuracy and real-time performance are limited when faced with a large amount of complex data. With the popularization of big data technology and cloud computing platforms, artificial intelligence, especially deep learning methods, have begun to be widely used in the field of new energy prediction. Deep networks can process massive and complex new energy data by simulating the neuronal connections of the human brain, providing more accurate short-term, medium-term and long-term power forecasts. Through cloud deployment, deep learning models can quickly integrate energy data from different regions to achieve real-time updates and scheduling optimization. However, the existing scheduling methods usually handle production, storage, distribution and consumption links independently, lack comprehensiveness and global perspectives, and often find it difficult to balance the coordination of various energy links, resulting in low scheduling efficiency, which leads to low dispersion, real-time and efficiency of state prediction scheduling. Summary of the invention

[0003] Based on this, it is necessary to provide a cloud-based new energy status prediction and scheduling method and system based on a deep network to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a cloud-based new energy state prediction and scheduling method based on a deep network is provided, the method comprising the following steps:

[0005] Step S1: Acquire cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data collection on the cloud-based new energy network data according to the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data;

[0006] Step S2: classify the standard cloud-based new energy monitoring data in the energy dispatching management stage to generate energy dispatching management stage data, wherein the energy dispatching management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data; perform energy power generation impact analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate actual energy power generation data in the production stage; perform energy storage state analysis on the standard cloud-based new energy monitoring data based on the energy storage stage data to generate energy storage efficiency data in the storage stage;

[0007] Step S3: Based on the data of the energy distribution stage, the standard cloud-based new energy monitoring data is mapped to the power grid transmission capacity to generate the actual energy supply and demand data of the distribution stage; based on the data of the energy consumption stage, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status to generate the energy consumption change data of the consumption stage;

[0008] Step S4: Calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy health status prediction data; perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0009] By acquiring cloud-based new energy network data and performing network topology analysis, the system can deeply understand the network structure and energy flow, ensure the comprehensiveness and accuracy of data collection, and generate standard cloud-based new energy monitoring data that provides a high-quality input basis for subsequent analysis and decision-making, reduces data redundancy and inconsistency problems, and improves data processing efficiency. The standard monitoring data is classified into energy dispatch management in stages to ensure that the system can perform detailed analysis and regulation for different links and accurately distinguish energy management stages such as production, storage, distribution and consumption. Through the analysis of the impact of power generation in the production stage, the system can predict and regulate the volatility of new energy in advance; through storage status analysis, the utilization rate and response capability of energy storage are improved, providing greater flexibility for system scheduling. Based on the data of the energy distribution stage, the transmission capacity of the power grid is mapped, so that the system can adjust the supply and demand balance in time, optimize energy distribution, and avoid resource waste or insufficient power supply caused by power transmission bottlenecks. By analyzing the power consumption status in the consumption stage, it is possible to accurately predict changes in energy demand, prevent excessive consumption or energy waste, and enhance the economy and efficiency of scheduling. By calculating the energy coordination index for data from each stage of production, storage, distribution, and consumption, the system can effectively balance the energy status of different links and ensure coordinated operation of each stage. The evaluation and prediction of energy health status provides real-time feedback, detects and responds to potential problems in advance, and improves the reliability of the system. Through intelligent scheduling, the system can not only dynamically adjust energy distribution, but also improve the utilization rate of new energy and the overall operating efficiency of the system, and promote the intelligent management of new energy networks. Therefore, the present invention solves the problems of dispersion, real-time and insufficient efficiency of cloud-based new energy status prediction and scheduling in the prior art through standardized data integration, full life cycle management, real-time dynamic prediction and energy coordination optimization.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Obtain cloud-based new energy network data;

[0012] Step S12: performing network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; performing cloud-based monitoring node confirmation on the cloud-based new energy network data according to the cloud-based new energy network topology data to obtain cloud-based new energy network monitoring node data;

[0013] Step S13: collecting cloud-based new energy monitoring data from cloud-based new energy network monitoring node data based on a preset time interval to generate cloud-based new energy monitoring data;

[0014] Step S14: preprocess the cloud-based new energy monitoring data to generate standard cloud-based new energy monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling, and data outlier processing.

[0015] The present invention can effectively improve the quality of monitoring data by performing network topology analysis and data preprocessing on cloud-based new energy network data. Data cleaning, denoising, missing value filling and outlier processing can ensure the accuracy and reliability of the data. Network topology analysis helps to identify and confirm the most effective monitoring nodes, thereby optimizing the network monitoring coverage and the accuracy of data collection. Data collection based on preset time intervals can ensure real-time updating and accuracy of data, and help to promptly discover and resolve potential network problems or abnormal situations. The standardized data preprocessing process provides a reliable foundation for subsequent data analysis and decision-making, and helps to better manage and optimize new energy networks. Through systematic data processing steps, human intervention and errors can be reduced, and the overall data processing efficiency can be improved.

[0016] Preferably, step S2 comprises the following steps:

[0017] Step S21: classifying the standard cloud-based new energy monitoring data by energy dispatch management stage to generate energy dispatch management stage data, wherein the energy dispatch management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data;

[0018] Step S22: Performing energy type analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate energy type data; performing monitoring address IP tracking on the cloud-based new energy network monitoring node data through the energy type data to generate new energy monitoring address tracking data;

[0019] Step S23: using environmental sensors to monitor meteorological data on the new energy monitoring address tracking data to generate meteorological monitoring data; using the meteorological monitoring data to analyze the impact of energy type data on energy generation, and generate actual energy generation data in the production stage;

[0020] Step S24: extracting storage stage features of the standard cloud-based new energy monitoring data based on the energy storage stage data to obtain storage stage feature data; performing energy storage state analysis on the storage stage feature data to generate storage stage energy storage efficiency data.

[0021] The present invention can clarify the characteristics of each energy scheduling and management stage by classifying and analyzing the standard cloud-based new energy monitoring data, help optimize the energy production, storage, distribution and consumption process, and improve the overall energy management efficiency. Energy type analysis can accurately identify different types of energy sources and characteristics, thereby supporting targeted energy production and distribution strategies. Monitoring address IP tracking helps to locate and solve problems in the network. Using environmental sensors to monitor meteorological data can accurately assess the impact of environmental factors on new energy power generation, thereby formulating more scientific power generation plans and countermeasures to optimize power generation efficiency. The extraction and analysis of energy storage stage characteristics can evaluate the energy efficiency of the storage stage and find ways to optimize storage efficiency, which helps to reduce energy losses and improve energy utilization. By generating actual power generation data in the production stage and energy storage efficiency data in the storage stage, detailed reference data can be provided for energy management decisions, supporting more scientific energy scheduling and optimization strategies. Comprehensive analysis of data at each stage can provide a deep understanding of the new energy system, help identify potential problems, optimize system performance, and improve system reliability and stability.

[0022] Preferably, step S24 includes the following steps:

[0023] Step S241: screening the energy storage device operation data of the standard cloud-based new energy monitoring data based on the energy storage stage data to obtain the energy storage device operation data;

[0024] Step S242: Calculate the storage capacity of the energy storage device operation data to generate the energy storage device storage capacity data; extract energy storage characteristics from the energy storage device operation data to obtain energy storage characteristic data;

[0025] Step S243: converting the charge and discharge curves according to the energy storage characteristic data to generate an energy charge curve and an energy discharge curve; overlaying the energy charge curve and the energy discharge curve to generate an energy charge and discharge overlay curve; analyzing the overlay points of the energy charge and discharge overlay data to generate energy charge and discharge level buffer data;

[0026] Step S244: Calculate the energy storage device utilization efficiency based on the energy charging and discharging level buffer data and the energy storage device storage capacity data to generate storage phase energy storage efficiency data.

[0027] By screening and calculating the operating data of energy storage devices, the present invention can accurately evaluate the storage capacity and operating characteristics of the equipment and provide a detailed understanding of the performance of the energy storage equipment. By analyzing and overlapping the charge and discharge curves of the energy storage equipment, the performance of the equipment under different charge and discharge states can be identified, thereby optimizing the energy storage and use strategy and reducing energy loss. By analyzing the charge and discharge level buffer data, the use efficiency of the energy storage equipment can be calculated, which helps to discover and solve the problem of inefficiency and improve the overall performance of the energy storage system. The conversion and overlap point analysis of the energy charge and discharge curves provides a scientific basis for decision-making in the energy storage stage, so that adjustments and optimizations can be made based on the data in actual operation. Through the comprehensive analysis of the storage capacity and use efficiency of energy storage equipment, effective data support can be provided for the maintenance and management of the equipment, and the reliability and life of the equipment can be improved. The generated energy storage efficiency data provides an important reference for energy scheduling and planning, which helps to formulate more scientific energy strategies and improve the overall efficiency of the energy system.

[0028] Preferably, step S3 comprises the following steps:

[0029] Step S31: Based on the energy distribution stage data, the new energy monitoring address tracking data is used to generate energy regional distribution data; the energy regional distribution data is used to perform power demand analysis to generate energy regional distribution demand data;

[0030] Step S32: Analyze the regional time period electricity load demand of the new energy monitoring address tracking data according to the regional energy distribution demand data to generate regional time period electricity load demand data;

[0031] Step S33: Mapping the grid transmission capacity of the standard cloud-based new energy monitoring data based on the regional time period power load demand data to generate actual energy supply and demand data for the distribution stage;

[0032] Step S34: extract consumption stage features from the standard cloud-based new energy monitoring data based on the energy consumption stage data to obtain consumption stage feature data; analyze the energy consumption status of the consumption stage feature data to generate consumption stage energy consumption change data.

[0033] The present invention can realize the accurate allocation of energy demand in different regions and ensure the rational use of energy resources by generating energy regional allocation data and analyzing electricity demand for new energy monitoring address tracking data. The analysis of regional time period electricity load demand data can provide detailed power load demand forecasts, which is helpful to optimize power grid load management and reduce power supply fluctuations. The actual energy supply and demand data of the distribution stage generated based on the power grid transmission capacity mapping can optimize the energy supply and transmission strategy of the power grid and improve the transmission efficiency and stability of the power grid. The extraction and analysis of the characteristic data of the consumption stage can deeply understand the changes in energy consumption and support the accurate monitoring and adjustment of energy use. Through the generated energy regional allocation demand data and the energy consumption change data of the consumption stage, strong data support can be provided for energy scheduling and decision-making, helping to formulate a more reasonable energy management strategy. Refined energy demand analysis and load management can improve the system's responsiveness to changes in energy demand and reduce the risks brought by supply and demand imbalance. Comprehensive analysis of electricity demand and power grid transmission capacity can help optimize energy utilization efficiency, reduce resource waste, and improve the efficiency of the overall energy system.

[0034] Preferably, step S34 includes the following steps:

[0035] Step S341: extracting time series features from the standard cloud-based new energy monitoring data based on the energy consumption stage data to obtain consumption stage time series feature data; performing load change analysis on the consumption stage time series feature data to generate load change feature data;

[0036] Step S342: classify the consumption patterns according to the load change characteristic data and the consumption stage time series characteristic data to generate consumption pattern data; perform power consumption state detection on the consumption pattern data to generate preliminary power consumption state data;

[0037] Step S343: compare the power efficiency differences of the preliminary power usage status data to generate power consumption status comparison data; use the power consumption status comparison data to analyze the energy consumption changes of the preliminary power usage status data to generate energy consumption change data in the consumption stage.

[0038] The present invention can deeply understand the energy consumption pattern in the consumption stage by extracting time series features and analyzing load changes, and provide data support for further energy management. Consumption pattern classification and power consumption status detection can help identify different power consumption patterns, support more accurate power consumption status monitoring and management, and discover potential power consumption problems in advance. Power efficiency difference comparison and energy consumption change analysis can reveal efficiency differences and change trends in energy use, thereby helping to optimize energy utilization and reduce waste. Through the generated power consumption status comparison data, targeted power consumption strategies and optimization measures can be formulated to improve overall power efficiency and system performance. Detailed energy consumption change data in the consumption stage provides a scientific basis for intelligent decision-making, so that energy management can better adapt to actual needs and changes. Based on data analysis of power consumption status detection and energy consumption comparison, the system's responsiveness to power demand and state changes can be improved, and the system's adaptability and stability can be improved. Through accurate analysis of energy consumption changes, deficiencies in energy use can be effectively identified and improved, and the realization of energy conservation and emission reduction goals can be promoted.

[0039] Preferably, step S4 comprises the following steps:

[0040] Step S41: Calculate the energy coordination index based on the actual energy generation data in the production phase, the energy storage efficiency data in the storage phase, the actual energy supply and demand data in the distribution phase, and the energy consumption change data in the consumption phase to obtain the energy coordination index;

[0041] Step S42: evaluating the health status of new energy on the cloud using the energy coordination index for the standard new energy monitoring data on the cloud, and generating new energy health status prediction data on the cloud;

[0042] Step S43: performing multi-dimensional energy scheduling optimization on the standard cloud-based new energy monitoring data according to the cloud-based new energy health status prediction data to generate energy scheduling optimization data;

[0043] Step S44: Perform energy intelligent scheduling on the energy scheduling management stage data through energy scheduling optimization data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0044] By calculating the energy coordination index, the present invention can comprehensively evaluate the coordination of each stage of production, storage, distribution and consumption, and ensure that the energy flow and utilization in each stage are efficient and consistent. The health status assessment based on the energy coordination index can accurately predict the health status of the cloud-based new energy system, help to identify potential problems in a timely manner and take preventive measures. By performing multi-dimensional energy scheduling optimization on the cloud-based new energy health status prediction data, a more accurate energy scheduling strategy can be formulated to optimize the allocation and use of energy resources. Using energy scheduling optimization data for intelligent scheduling can improve the efficiency and accuracy of energy scheduling and achieve more scientific energy management. By implementing intelligent scheduling, it is possible to better cope with changes in energy demand and system load fluctuations, thereby improving the reliability and stability of the system. Comprehensively considering the data of each stage for scheduling optimization can help achieve comprehensive optimization of the energy system and improve the overall efficiency of energy management. Optimized energy scheduling can reduce energy waste and reduce operating costs, and support the realization of energy conservation and emission reduction goals.

[0045] Preferably, step S42 includes the following steps:

[0046] Step S421: Performing energy dynamic change analysis on standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy dynamic change data;

[0047] Step S422: divide the cloud-based new energy dynamic change data into data sets to generate a model training set and a model test set; use a support vector set algorithm to perform model training on the model training set to generate a cloud-based new energy health prediction pre-model; perform model optimization iteration on the cloud-based new energy health prediction pre-model through the model test set, thereby generating a cloud-based new energy health prediction model;

[0048] Step S423: Importing the standard cloud-based new energy monitoring data into the cloud-based new energy health prediction model to perform cloud-based new energy health status assessment and generate cloud-based new energy health status prediction data.

[0049] The present invention can deeply understand the performance and changes of cloud-based new energy systems in different time periods through the analysis of dynamic changes in energy, and provide a more accurate system status assessment. The division of data sets and the training and optimization of support vector machine (SVM) algorithms help to generate a high-accuracy and reliable health prediction model and improve the credibility of the prediction results. The cloud-based new energy health prediction model can perform health status assessment based on dynamically changing data, help predict future problems, and perform maintenance and adjustments in advance. Accurate health status prediction data can support the formulation of more effective maintenance strategies and plans, reduce the risk of sudden failures, and improve the stability and reliability of the system. The prediction data generated by the health prediction model provides strong support for decision makers, making decisions more scientific and data-driven, and improving the decision-making quality of energy management. Through continuous model optimization and iteration, the adaptability of the model can be continuously improved, and the prediction of the system status can be adjusted in time to adapt to the changing environment and conditions. Using the health prediction model for status assessment helps to achieve intelligent management and control of cloud-based new energy systems and optimize overall system performance.

[0050] Preferably, step S43 includes the following steps:

[0051] Step S431: Compare the cloud-based new energy health status prediction data with a preset standard health status threshold. When the cloud-based new energy health status prediction data is greater than or equal to the preset standard health status threshold, a long-term scheduling demand mode is set based on the cloud-based new energy health status prediction data to obtain a long-term scheduling demand mode.

[0052] Step S432: when the cloud-based new energy health status prediction data is less than a preset standard health status threshold, a short-term scheduling demand mode is set based on the cloud-based new energy health status prediction data to obtain a short-term scheduling demand mode;

[0053] Step S433: Minimize the cost of standard cloud-based new energy monitoring data through the long-term scheduling demand model to generate a long-term energy scheduling strategy; maximize the efficiency of standard cloud-based new energy monitoring data through the short-term scheduling demand model to generate a short-term energy scheduling strategy;

[0054] Step S434: Based on the long-term energy scheduling strategy and the short-term energy scheduling strategy, the standard cloud-based new energy monitoring data is optimized in multiple dimensions to generate energy scheduling optimization data.

[0055] By comparing the health status prediction data with the preset standard threshold, the present invention can formulate more appropriate long-term and short-term scheduling demand patterns to ensure the scientificity and pertinence of the scheduling strategy. According to the different health status prediction data, long-term and short-term scheduling patterns are formulated, and the scheduling strategy can be flexibly adjusted in different situations to adapt to different needs and changes in conditions. The setting of the long-term scheduling demand pattern supports cost minimization scheduling, which helps to reduce operating costs; the setting of the short-term scheduling demand pattern focuses on efficiency maximization scheduling to improve energy utilization efficiency. By comprehensively applying long-term and short-term energy scheduling strategies, multi-dimensional energy scheduling optimization can be achieved, and the scheduling efficiency and economy of the energy system can be comprehensively improved. Scientific scheduling strategies help stabilize energy supply, reduce system fluctuations caused by improper scheduling, and improve system stability and reliability. Through the generated energy scheduling optimization data, accurate data support is provided to decision makers to ensure the scientificity and effectiveness of scheduling decisions. The optimized energy scheduling strategy can effectively improve the overall performance of the energy system and promote the long-term sustainable development of the system.

[0056] In this specification, a cloud-based new energy state prediction and scheduling system based on a deep network is provided, which is used to execute the above-mentioned cloud-based new energy state prediction and scheduling method based on a deep network. The cloud-based new energy state prediction and scheduling system based on a deep network includes:

[0057] The data acquisition module is used to obtain cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data acquisition on the cloud-based new energy network data based on the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data;

[0058] The production storage analysis module is used to classify the standard cloud-based new energy monitoring data into energy dispatch management phases and generate energy dispatch management phase data, wherein the energy dispatch management phase data includes energy production phase data, energy storage phase data, energy distribution phase data and energy consumption phase data; based on the energy production phase data, the standard cloud-based new energy monitoring data is analyzed for energy generation impact and the actual energy generation data of the production phase is generated; based on the energy storage phase data, the standard cloud-based new energy monitoring data is analyzed for energy storage status and the energy storage efficiency data of the storage phase is generated;

[0059] The distribution and consumption analysis module is used to map the power grid transmission capacity of the standard cloud-based new energy monitoring data based on the energy distribution stage data, and generate the actual energy supply and demand data in the distribution stage; based on the energy consumption stage data, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status, and the energy consumption change data in the consumption stage is generated;

[0060] The energy scheduling module is used to calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; to evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index, and to generate cloud-based new energy health status prediction data; to perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0061] The beneficial effect of the present invention is that the new energy network data is obtained through the cloud, and the network topology analysis is performed to generate topology data. This process ensures a global understanding of the new energy network structure and lays the foundation for subsequent data collection and monitoring. Standardization of cloud-based new energy monitoring data ensures that the data is consistent between different stages and different devices, which provides high-quality and reliable data input for subsequent analysis. Through topological analysis, the structure of the new energy network is deeply understood, the data collection process is optimized, and it is helpful to identify key nodes and potential bottlenecks, thereby improving the monitoring efficiency and reliability of the new energy network. The new energy scheduling management is divided into four stages: production, storage, distribution and consumption, which refines the entire new energy management process. This classification method helps to analyze each link independently and make the scheduling more targeted. Through classification analysis, the operation status of each stage can be accurately evaluated, and stage data can be provided to provide a basis for subsequent decision-making. The power generation analysis in the production stage ensures the high efficiency of new energy production and can identify the factors affecting the change in power generation. Data analysis in the storage stage can improve the efficiency of energy storage and avoid energy waste. Mapping the transmission capacity of the power grid in the energy distribution stage and generating actual supply and demand data can help identify load balancing problems in the power grid, optimize supply and demand matching, and improve the transmission efficiency of the power grid. The analysis of power grid transmission capacity ensures the stability and efficiency of power transmission and reduces energy loss. The analysis of energy consumption status can provide dynamic monitoring of changes in energy use, thereby helping to discover fluctuations in energy consumption and make timely adjustments, which helps to optimize the energy consumption structure and reduce unnecessary energy waste. Based on the data of the production, storage, distribution and consumption stages, the energy coordination index is calculated to comprehensively evaluate the operational coordination of the entire energy system. The index can reflect the coordination level between each stage and help discover potential energy management problems. The coordination index provides quantitative indicators for energy status monitoring and system optimization, which helps to accurately dispatch. The health status of the cloud-based new energy system is evaluated through the energy coordination index to generate health status prediction data. This prediction helps to discover potential risks and problems in advance and ensure the long-term healthy operation of the new energy network. Intelligent scheduling is carried out based on the health status prediction data to optimize the use and management of energy at each stage, maximize energy utilization, and improve the operating efficiency and stability of the new energy system. Therefore, the present invention solves the problems of dispersion, real-time and inefficient cloud-based new energy status prediction and scheduling in the prior art through standardized data integration, full life cycle management, real-time dynamic prediction and energy coordination optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A schematic diagram of the steps of a cloud-based new energy state prediction and scheduling method based on a deep network;

[0063] Figure 2 for Figure 1Detailed implementation steps of step S2 in the flowchart;

[0064] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0065] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0066] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0067] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0068] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0069] To achieve this, please refer to Figures 1 to 3 , a cloud-based new energy state prediction and scheduling method based on deep network, the method comprises the following steps:

[0070] Step S1: Acquire cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data collection on the cloud-based new energy network data according to the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data;

[0071] Step S2: classify the standard cloud-based new energy monitoring data in the energy dispatching management stage to generate energy dispatching management stage data, wherein the energy dispatching management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data; perform energy power generation impact analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate actual energy power generation data in the production stage; perform energy storage state analysis on the standard cloud-based new energy monitoring data based on the energy storage stage data to generate energy storage efficiency data in the storage stage;

[0072] Step S3: Based on the data of the energy distribution stage, the standard cloud-based new energy monitoring data is mapped to the power grid transmission capacity to generate the actual energy supply and demand data of the distribution stage; based on the data of the energy consumption stage, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status to generate the energy consumption change data of the consumption stage;

[0073] Step S4: Calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy health status prediction data; perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0074] By acquiring cloud-based new energy network data and performing network topology analysis, the system can deeply understand the network structure and energy flow, ensure the comprehensiveness and accuracy of data collection, and generate standard cloud-based new energy monitoring data that provides a high-quality input basis for subsequent analysis and decision-making, reduces data redundancy and inconsistency problems, and improves data processing efficiency. The standard monitoring data is classified into energy dispatch management in stages to ensure that the system can perform detailed analysis and regulation for different links and accurately distinguish energy management stages such as production, storage, distribution and consumption. Through the analysis of the impact of power generation in the production stage, the system can predict and regulate the volatility of new energy in advance; through storage status analysis, the utilization rate and response capability of energy storage are improved, providing greater flexibility for system scheduling. Based on the data of the energy distribution stage, the transmission capacity of the power grid is mapped, so that the system can adjust the supply and demand balance in time, optimize energy distribution, and avoid resource waste or insufficient power supply caused by power transmission bottlenecks. By analyzing the power consumption status in the consumption stage, it is possible to accurately predict changes in energy demand, prevent excessive consumption or energy waste, and enhance the economy and efficiency of scheduling. By calculating the energy coordination index for data from each stage of production, storage, distribution, and consumption, the system can effectively balance the energy status of different links and ensure coordinated operation of each stage. The evaluation and prediction of energy health status provides real-time feedback, detects and responds to potential problems in advance, and improves the reliability of the system. Through intelligent scheduling, the system can not only dynamically adjust energy distribution, but also improve the utilization rate of new energy and the overall operating efficiency of the system, and promote the intelligent management of new energy networks. Therefore, the present invention solves the problems of dispersion, real-time and insufficient efficiency of cloud-based new energy status prediction and scheduling in the prior art through standardized data integration, full life cycle management, real-time dynamic prediction and energy coordination optimization.

[0075] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a cloud-based new energy state prediction and scheduling method based on a deep network of the present invention. In this example, the cloud-based new energy state prediction and scheduling method based on a deep network includes the following steps:

[0076] Step S1: Acquire cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data collection on the cloud-based new energy network data according to the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data;

[0077] In an embodiment of the present invention, by selecting a specific cloud-based new energy network data source, including wind power generation, photovoltaic power generation, energy storage system, and power transmission equipment, etc. Data can come from various monitoring devices, sensors, and power management platforms. Real-time operation data of new energy equipment is obtained through an API interface, a data interface, or an Internet of Things platform. Common data include power generation, equipment operating status, fault information, voltage, current, etc. The acquired new energy network data is stored in a cloud database to ensure the continuity and integrity of the data. The database can adopt distributed storage technology to ensure efficient access to large-scale data. The acquired new energy network data is topologically identified. The connection relationship between each node (such as power generation equipment, energy storage equipment, substation, etc.) is analyzed to identify the power transmission path. A graph theory method or other algorithm is used to generate a topological structure diagram of the network, and each node in the network and its connection relationship are defined. Based on the topological analysis results, cloud-based new energy network topological data is generated to describe the node configuration, network structure, connection between devices, and energy flow path of the network. Changes in the topological structure are continuously monitored in the cloud, and the network topological diagram is updated in real time when equipment is added, fails, or removed to ensure the accuracy and timeliness of the data. According to the network topology data, the key nodes to be monitored are determined. These nodes are specifically power generation equipment, energy storage equipment, substations, etc., and their operating status is monitored in detail. Based on the network topology structure, data is collected for each monitoring node, including real-time power data, equipment status, environmental conditions (such as temperature, wind speed, light intensity, etc.), and historical operation data of the equipment. The monitoring node data is collected regularly using scheduled tasks or on-demand triggering to ensure the continuity and real-time nature of the data. The collected data is transmitted to the cloud storage system through the network, and the data is initially stored and managed. Invalid or redundant data is deleted and duplicate records are removed. Filtering algorithms or machine learning techniques are used to eliminate noise data and improve data quality. For missing items in the data, interpolation, mean filling or machine learning algorithms are used to fill them. Outliers in the monitoring data are processed, such as using statistical analysis or anomaly detection algorithms to identify and process deviation data. All monitoring data are standardized, including unit unification and format unification, to ensure that the data is comparable and consistent in subsequent analysis and calculation, and to generate standard cloud-based new energy monitoring data as the basic data for subsequent energy scheduling, analysis and optimization.

[0078] Step S2: classify the standard cloud-based new energy monitoring data in the energy dispatching management stage to generate energy dispatching management stage data, wherein the energy dispatching management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data; perform energy power generation impact analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate actual energy power generation data in the production stage; perform energy storage state analysis on the standard cloud-based new energy monitoring data based on the energy storage stage data to generate energy storage efficiency data in the storage stage;

[0079] In an embodiment of the present invention, the standard cloud-based new energy monitoring data is classified according to different energy scheduling and management stages based on the operating structure of the cloud-based new energy network. The classified stages generally include: energy production stage, energy storage stage, energy distribution stage, and energy consumption stage. From the standard cloud-based new energy monitoring data, data related to power generation equipment (such as wind turbines, photovoltaic panels, etc.) are extracted, including power generation, equipment operating status, weather conditions, etc., to generate energy production stage data. Data related to the energy storage system, such as battery charging and discharging status, capacity, charging efficiency, etc., are extracted to generate energy storage stage data. Data related to energy transmission and distribution, such as power transmission power of the power grid, load conditions, power transmission data between nodes, etc., are extracted to generate energy distribution stage data. Energy consumption data, such as household, industrial, etc. power consumption, and the operating status of each load are extracted from the power terminal equipment to generate energy consumption stage data. Based on the energy production stage data generated in step S21, data related to power generation is extracted, mainly including actual power generation, equipment operating time, weather conditions (such as light intensity, wind speed, etc.), etc. Analyze the environmental factors that affect the generation of new energy, and use meteorological monitoring data (such as temperature, wind speed, light, etc.) combined with energy production stage data to evaluate the impact of these factors on the power generation. By establishing a mathematical model or machine learning algorithm, the power generation under different conditions is predicted and analyzed to generate energy generation impact data corresponding to the actual environmental conditions. Combined with the impact of environmental factors on the power generation equipment, the actual power generation is calculated to generate the actual power generation data of the production stage, which are used to evaluate the operating efficiency of the power generation equipment and the actual impact of environmental conditions on power generation. From the energy storage stage data generated in step S21, extract the operating data of the energy storage device, including the charging and discharging records, current storage capacity, maximum storage capacity, etc. of the battery or other energy storage system. Monitor the health status of the energy storage device and evaluate its operating efficiency, charging and discharging rate, and whether there is loss or abnormality. The health status of the device can be judged by analyzing factors such as the temperature of the energy storage device and the number of charging cycles. Based on the operating data of the energy storage device, the charging and discharging efficiency is calculated, and the performance of the energy storage device in different time periods or load conditions is analyzed. The storage capacity, charging and discharging efficiency, and current operating status of the energy storage device are combined to generate storage stage energy storage efficiency data. This data can help optimize the use strategy of energy storage equipment and improve overall energy storage efficiency.

[0080] Step S3: Based on the data of the energy distribution stage, the standard cloud-based new energy monitoring data is mapped to the power grid transmission capacity to generate the actual energy supply and demand data of the distribution stage; based on the data of the energy consumption stage, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status to generate the energy consumption change data of the consumption stage;

[0081] In an embodiment of the present invention, by extracting key data related to power grid transmission, such as voltage, current, transmission power, load distribution, etc., based on the energy distribution phase data generated in step S21. Focus on the transmission capacity and load of the power grid in different time periods to ensure that the data can accurately reflect the current operation status of the power grid. The transmission capacity of the power grid is evaluated by the transmission capacity analysis algorithm of the power system (such as power flow analysis, short-circuit current calculation, etc.). Analyze the power transmission path between each power grid node and identify the bottleneck area of ​​the power grid. Establish a power grid transmission model, and analyze the power supply capacity and transmission efficiency of power grids in different regions according to the network topology and actual monitoring data. Based on the results of the power grid transmission capacity analysis, generate power grid transmission capacity mapping data. This data will reflect the actual transmission capacity of the power grid in each region, and can point out areas with excessive load or insufficient power supply. The mapping data can be displayed in a graphical manner to intuitively display the power transmission status of the power grid in each region. Combined with the energy production phase data and the power grid transmission capacity mapping data, the actual energy supply and demand data of each region are calculated. If an imbalance between supply and demand is found, further measures (such as dispatching power generation equipment, adjusting the energy storage system, etc.) can be taken to optimize power distribution. Finally, the actual energy supply and demand data of the distribution stage is generated to reflect the energy supply and demand balance in different regions in real time. From the energy consumption stage data generated in step S21, detailed information related to electricity consumption is extracted, including the electricity consumption of each user or region, the operation of the power equipment, the peak and valley load periods, etc. Monitor the real-time data of the power terminals, such as the power load of households, industries and commerce, and record their power consumption habits and trends. Based on the power consumption data, use data mining algorithms (such as cluster analysis, trend analysis, etc.) to identify the power consumption patterns of different user groups or regions. Analyze typical power consumption behaviors and distinguish between peak and valley power demand. By comparing historical data with real-time monitoring data, predict future power consumption trends and provide suggestions to improve power efficiency or reduce load pressure during peak power consumption. Evaluate the status of power equipment and identify abnormal conditions, such as equipment failure, overload, reduced energy efficiency, etc. Abnormal power equipment can be found and warned by comparing energy consumption data with the rated power of the equipment. Using intelligent algorithms or rules to judge, power consumption status analysis can identify abnormal power consumption in real time, such as overload operation or unreasonable high energy consumption behavior. Analyze the dynamic changes in energy consumption and calculate the changing trend of energy consumption in different time periods. By comparing the changes in power consumption in different time periods (such as daytime and nighttime, weekdays and weekends, etc.), you can have a clearer understanding of the fluctuations in energy consumption, generate energy consumption change data in the consumption stage, which is used to reflect the power consumption trend of each region or equipment, and provide data support for subsequent energy scheduling and optimization. Integrate the actual supply and demand data of the power grid with the energy consumption change data to analyze whether the actual supply of energy can meet the needs of each region or equipment.If there is an imbalance between supply and demand, dynamic dispatch measures can be taken to adjust the output power of power generation equipment or enable energy storage equipment to fill the shortage. Based on the analysis results of supply and demand balance and power consumption status, power transmission and power consumption optimization suggestions are generated. Including dispatch suggestions, load adjustment plans, or technical solutions to optimize the transmission capacity of the power grid. For equipment or areas with abnormal power consumption status, specific adjustment or maintenance suggestions are put forward to improve the stability and power efficiency of the overall power system.

[0082] Step S4: Calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy health status prediction data; perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0083] In an embodiment of the present invention, the actual energy generation data of the production stage, the energy storage efficiency data of the storage stage, the actual energy supply and demand data of the distribution stage, and the energy consumption change data of the consumption stage are extracted from the previous steps. Ensure the timeliness and accuracy of the data for subsequent analysis and calculation. Integrate these data to form a multi-dimensional energy monitoring data set, reflecting the actual operation of each link of energy from production, storage, distribution to consumption. Construct coordination evaluation indicators for each energy link (production, storage, distribution, consumption), such as power generation utilization rate, energy storage equipment efficiency, supply and demand matching, power consumption stability, etc. According to these indicators, a weighted algorithm or a multi-dimensional analysis method (such as principal component analysis, fuzzy comprehensive evaluation, etc.) is used to calculate the local coordination index of each link. Based on the local coordination index of each link, the comprehensive energy coordination index of the entire system is calculated by a weighted formula. Weighted formula example: C=w1·P+w2·S+w3·D+w4·C E ; Where C is the comprehensive energy coordination index, P is the power generation coordination index in the production stage, S is the storage efficiency coordination index in the storage stage, D is the supply and demand matching degree in the distribution stage, C Eis the stability of electricity consumption in the consumption stage, and w1, w2, w3, and w4 are the weight coefficients of each stage. The calculation results will reflect the coordination degree of the energy system in each link and comprehensively evaluate the health status of the energy system. Based on the energy coordination index, a health status assessment model for the energy system is constructed. The model can be combined with machine learning or big data analysis methods to use historical data and real-time monitoring data for prediction and analysis. Define the health status level (such as "normal", "warning", and "dangerous"), and judge the current health status of the energy system according to different coordination index ranges. Use time series prediction models (such as ARIMA models, LSTM neural networks, etc.) to predict the health status of the energy system in the future based on the energy coordination index and the data trends of each link, and generate cloud-based new energy health status prediction data, including future system health change trends, abnormal conditions, and early warning information. This data provides a decision-making basis for subsequent scheduling. Based on the cloud-based new energy health status prediction data, an intelligent scheduling strategy is constructed. The scheduling strategy should fully consider the actual operating status and predicted health status of each energy link to ensure the smooth and efficient operation of the energy system. Intelligent dispatching strategies include the start-stop management of power generation equipment, the charging and discharging strategies of energy storage equipment, the adjustment of power grid transmission load, and the dynamic dispatching of power consumption equipment. Combine the dispatching strategy with the standard cloud-based new energy monitoring data to generate intelligent dispatching data for the energy stage. This data will be used to implement the real-time dispatching of the energy system to ensure the energy efficiency optimization and coordination of each link. For example, when the energy supply is insufficient, energy storage equipment will be enabled first; during the peak period of power consumption, the load distribution of the power grid will be dynamically adjusted to reduce the pressure of peak power consumption on the system. Monitor the execution of intelligent dispatching in real time and analyze the effectiveness of the dispatching strategy. According to the deviation between the actual execution data and the predicted results, adjust the intelligent dispatching strategy in time to ensure the dynamic optimization of the system. Analyze and feedback the dispatching results, continuously optimize the dispatching strategy of the energy system, and realize intelligent and adaptive energy dispatching management.

[0084] Preferably, step S1 comprises the following steps:

[0085] Step S11: Obtain cloud-based new energy network data;

[0086] Step S12: performing network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; performing cloud-based monitoring node confirmation on the cloud-based new energy network data according to the cloud-based new energy network topology data to obtain cloud-based new energy network monitoring node data;

[0087] Step S13: collecting cloud-based new energy monitoring data from cloud-based new energy network monitoring node data based on a preset time interval to generate cloud-based new energy monitoring data;

[0088] Step S14: preprocess the cloud-based new energy monitoring data to generate standard cloud-based new energy monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling, and data outlier processing.

[0089] In an embodiment of the present invention, by selecting a specific cloud-based new energy network data source, such as wind power generation, solar power generation and other related data sources. Real-time and historical new energy network data are obtained from the cloud-based energy management platform through an API or a data interface. These data include power generation, equipment status, meteorological data, etc. The acquired data is stored in a cloud database for subsequent processing. The acquired cloud-based new energy network data is subjected to network topology analysis to identify network nodes and their connection relationships. For example, power generation facilities, substations, transmission lines, etc. are identified. Based on the network analysis results, cloud-based new energy network topology data is generated, which includes node connection relationships, network structure diagrams, etc. According to the network topology data, the monitoring nodes in the cloud-based new energy network are confirmed. These nodes include key equipment, sensor nodes, etc., and cloud-based new energy network monitoring node data is generated for subsequent data collection and analysis. According to a preset time interval (for example, every hour, every day), a data collection plan is formulated. Monitoring data is collected from the confirmed cloud-based new energy network monitoring nodes. These data include power generation, equipment operating status, environmental conditions, etc. The collected data is stored in a data warehouse to ensure the integrity and accuracy of the data. Duplicate data and irrelevant data are removed to ensure the accuracy and consistency of the data. A filter or algorithm is used to remove noise in the data to improve data quality. Use interpolation, mean filling and other methods to fill missing values ​​in the data. Identify and process outliers in the data, specifically using statistical analysis or machine learning methods for anomaly detection and correction. Standardize the processed data for subsequent analysis and comparison, generate standard cloud-based new energy monitoring data, and prepare for further data analysis and modeling.

[0090] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0091] Step S21: classifying the standard cloud-based new energy monitoring data by energy dispatch management stage to generate energy dispatch management stage data, wherein the energy dispatch management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data;

[0092] Step S22: Performing energy type analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate energy type data; performing monitoring address IP tracking on the cloud-based new energy network monitoring node data through the energy type data to generate new energy monitoring address tracking data;

[0093] Step S23: using environmental sensors to monitor meteorological data on the new energy monitoring address tracking data to generate meteorological monitoring data; using the meteorological monitoring data to analyze the impact of energy type data on energy generation, and generate actual energy generation data in the production stage;

[0094] Step S24: extracting storage stage features of the standard cloud-based new energy monitoring data based on the energy storage stage data to obtain storage stage feature data; performing energy storage state analysis on the storage stage feature data to generate storage stage energy storage efficiency data.

[0095] In an embodiment of the present invention, data related to energy production is identified and classified, such as the output of power generation equipment, power generation, equipment operating status, etc. Data related to energy storage is identified and classified, such as the charge and discharge status of the battery energy storage system, energy storage capacity, etc. Data related to energy distribution is identified and classified, such as power grid load distribution, energy transmission status, etc. Data related to energy consumption is identified and classified, such as energy usage and consumption patterns at the user end. The classified data is integrated to generate energy scheduling management stage data for subsequent analysis and optimization. Based on the energy production stage data, the output characteristics and proportions of different types of new energy (such as solar energy, wind energy, energy storage, etc.) are analyzed to generate energy type data to describe the production and distribution of various types of energy. The energy type data is used to track the address IP of the monitoring node, including determining the actual location, network address, etc. of each monitoring node, and generating new energy monitoring address tracking data for further geographic and network analysis. Environmental sensors (such as temperature, humidity, and wind speed sensors) are used to monitor meteorological data on the new energy monitoring address tracking data to generate meteorological monitoring data to describe the meteorological conditions of different monitoring nodes. Meteorological monitoring data is used to analyze the impact of meteorological conditions on energy production, such as the impact of temperature on solar power generation and wind speed on wind power generation, to generate actual energy generation data in the production phase, reflecting the relationship between actual power generation and meteorological conditions. Based on the energy storage phase data, the characteristics of the storage phase are extracted, such as charging efficiency, discharging efficiency, storage capacity utilization, etc., to obtain storage phase characteristic data to describe the performance and status of the storage device. The storage phase characteristic data is analyzed to evaluate the efficiency of energy storage, including energy loss, storage utilization, etc., to generate storage phase energy storage efficiency data for optimizing energy storage strategies and improving the performance of storage systems.

[0096] Preferably, step S24 includes the following steps:

[0097] Step S241: screening the energy storage device operation data of the standard cloud-based new energy monitoring data based on the energy storage stage data to obtain the energy storage device operation data;

[0098] Step S242: Calculate the storage capacity of the energy storage device operation data to generate the energy storage device storage capacity data; extract energy storage characteristics from the energy storage device operation data to obtain energy storage characteristic data;

[0099] Step S243: converting the charge and discharge curves according to the energy storage characteristic data to generate an energy charge curve and an energy discharge curve; overlaying the energy charge curve and the energy discharge curve to generate an energy charge and discharge overlay curve; analyzing the overlay points of the energy charge and discharge overlay data to generate energy charge and discharge level buffer data;

[0100] Step S244: Calculate the energy storage device utilization efficiency based on the energy charging and discharging level buffer data and the energy storage device storage capacity data to generate storage phase energy storage efficiency data.

[0101] In an embodiment of the present invention, data related to the operation of the energy storage device is screened out based on the energy storage stage data, including the working status of the device, charging and discharging records, device fault information, etc. Predefined screening conditions, such as time range, device type, data integrity, etc., are applied to ensure that the screened data is highly representative and of high quality, and the operation data of the energy storage device is obtained for further analysis. The storage capacity of the device is calculated using the operation data of the energy storage device. The calculation can generate the storage capacity data of the energy storage device based on the specification parameters of the device, the actual charging and discharging data, etc., to describe the storage capacity of the device. The operation data of the energy storage device is analyzed to extract the characteristics related to the storage performance, such as charging efficiency, discharging efficiency, charging and discharging time, etc., to obtain energy storage characteristic data for further analysis. According to the energy storage characteristic data, the raw data is converted into charging curves and discharging curves, which describe the charging and discharging states at different time points, generate energy charging curves and energy discharging curves, and display the data changes during the charging and discharging process. The energy charging curve and the energy discharging curve are overlapped to compare the corresponding relationship between the charging and discharging processes, and an energy charging and discharging overlap curve is generated for further analysis. Analyze the coincidence points in the energy charge and discharge coincidence curve, identify the consistency and difference in the charging and discharging process, generate energy charge and discharge level slow data, and describe the smoothness and consistency of the charging and discharging process. Based on the energy charge and discharge level slow data, analyze the storage capacity data of energy storage equipment and calculate the utilization efficiency of energy storage equipment. The efficiency calculation includes the ratio of the actual storage capacity of the equipment to the theoretical storage capacity, and generates energy storage efficiency data in the storage stage to evaluate the performance and efficiency of energy storage equipment.

[0102] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0103] Step S31: Based on the energy distribution stage data, the new energy monitoring address tracking data is used to generate energy regional distribution data; the energy regional distribution data is used to perform power demand analysis to generate energy regional distribution demand data;

[0104] Step S32: Analyze the regional time period electricity load demand of the new energy monitoring address tracking data according to the regional energy distribution demand data to generate regional time period electricity load demand data;

[0105] Step S33: Mapping the grid transmission capacity of the standard cloud-based new energy monitoring data based on the regional time period power load demand data to generate actual energy supply and demand data for the distribution stage;

[0106] Step S34: extract consumption stage features from the standard cloud-based new energy monitoring data based on the energy consumption stage data to obtain consumption stage feature data; analyze the energy consumption status of the consumption stage feature data to generate consumption stage energy consumption change data.

[0107] In an embodiment of the present invention, by extracting relevant energy distribution phase data from the new energy monitoring address tracking data, this includes the distribution of energy, distribution mode and other relevant information. Use energy distribution algorithms (such as linear programming, optimization algorithms) to perform regional energy distribution on new energy monitoring addresses. The algorithm can generate energy regional distribution data based on energy supply capacity, demand conditions and distribution rules. The distribution results are integrated into energy regional distribution data, which describe the energy distribution conditions in each region. Construct an electricity demand analysis model, which can use historical electricity data, demographic data and economic activity data to predict the electricity demand in each region. Perform electricity demand analysis on energy regional distribution data, calculate the electricity demand in each region, and generate energy regional distribution demand data, which will show the energy demand in each region. Obtain relevant time period electricity demand information from energy regional distribution demand data. Use time series analysis techniques (such as ARIMA model, seasonal decomposition) to analyze the electricity load demand in different regions in different time periods. Model the electricity load demand in different regions in different time periods to generate regional time period electricity load demand data, which include daily, weekly and monthly load demand conditions. Obtain standard cloud-based new energy monitoring data, which includes the transmission capacity of the power grid, energy supply, etc. Establish a power grid transmission capacity mapping model to match the regional time period electricity load demand data with the standard cloud-based new energy monitoring data. The model can use power grid flow analysis, load flow analysis and other technologies to generate actual energy supply and demand data in the distribution stage, showing the actual energy supply and demand of the power grid in various time periods and regions. Based on the energy consumption stage data, extract relevant features from the standard cloud-based new energy monitoring data, which include power consumption, energy type, consumption mode, etc. Use data mining technology (such as principal component analysis, feature selection algorithm) to extract key features of the consumption stage and generate consumption stage feature data, which reflects the main features and patterns of energy consumption. Construct an energy power consumption state analysis model to analyze the consumption stage feature data. The model includes energy consumption trend analysis, anomaly detection, etc., to generate energy consumption change data in the consumption stage, and show the change trend, periodicity and anomalies of energy consumption. Store the generated energy regional distribution data, energy regional distribution demand data, regional time period electricity load demand data, distribution stage energy actual supply and demand data and consumption stage energy consumption change data in the database. Generate detailed reports based on the analysis results, including energy distribution, electricity demand analysis, grid transmission capacity mapping, consumption stage characteristics and energy consumption changes, providing a basis for energy management and decision-making.

[0108] Preferably, step S34 includes the following steps:

[0109] Step S341: extracting time series features from the standard cloud-based new energy monitoring data based on the energy consumption stage data to obtain consumption stage time series feature data; performing load change analysis on the consumption stage time series feature data to generate load change feature data;

[0110] Step S342: classify the consumption patterns according to the load change characteristic data and the consumption stage time series characteristic data to generate consumption pattern data; perform power consumption state detection on the consumption pattern data to generate preliminary power consumption state data;

[0111] Step S343: compare the power efficiency differences of the preliminary power usage status data to generate power consumption status comparison data; use the power consumption status comparison data to analyze the energy consumption changes of the preliminary power usage status data to generate energy consumption change data in the consumption stage.

[0112] In an embodiment of the present invention, data of the energy consumption phase is extracted from the standard cloud-based new energy monitoring data, and these data include energy consumption in different time periods. Time series analysis techniques (such as Fourier transform, wavelet transform, sliding window analysis) are used to extract time series features, which include trends, seasonality, periodicity and random fluctuations, and generate consumption phase time series feature data, which describes in detail the main features and change trends in the time series. The load change analysis model (such as time series clustering analysis, change point detection) is applied to analyze the consumption phase time series feature data. The load change pattern and abnormal points are identified to generate load change feature data. This data shows information such as the change trend, peak and valley of the energy load. Based on the load change feature data and the consumption phase time series feature data, a classification algorithm (such as K-means clustering, support vector machine, decision tree) is applied to classify the consumption pattern. Different consumption patterns, such as peak load pattern, stable period pattern and abnormal pattern, are identified to generate consumption pattern data. The consumption pattern data is analyzed using a power consumption state detection model (such as anomaly detection algorithm, state estimation method). The health of the power consumption state is evaluated to generate preliminary power consumption state data. This data reflects the operating status and energy efficiency of electrical equipment. Perform a comparative analysis of the differences in electricity efficiency on the preliminary electricity status data. Compare the electricity efficiency of different regions, time periods or equipment to generate comparative data on electricity energy consumption status, and generate comparative data to show the energy consumption differences and efficiency changes under different electricity status. Apply energy consumption change analysis models (such as regression analysis and trend analysis) to further analyze the comparative data on electricity energy consumption status. Generate energy consumption change data in the consumption stage based on the analysis results. This data provides detailed trends, abnormalities and optimization suggestions for energy consumption. Store the time series characteristic data of the consumption stage, load change characteristic data, consumption pattern data, preliminary electricity status data, electricity energy consumption status comparison data and energy consumption change data in the consumption stage in the database.

[0113] Preferably, step S4 comprises the following steps:

[0114] Step S41: Calculate the energy coordination index based on the actual energy generation data in the production phase, the energy storage efficiency data in the storage phase, the actual energy supply and demand data in the distribution phase, and the energy consumption change data in the consumption phase to obtain the energy coordination index;

[0115] Step S42: evaluating the health status of new energy on the cloud using the energy coordination index for the standard new energy monitoring data on the cloud, and generating new energy health status prediction data on the cloud;

[0116] Step S43: performing multi-dimensional energy scheduling optimization on the standard cloud-based new energy monitoring data according to the cloud-based new energy health status prediction data to generate energy scheduling optimization data;

[0117] Step S44: Perform energy intelligent scheduling on the energy scheduling management stage data through energy scheduling optimization data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0118] In an embodiment of the present invention, an energy coordination analysis model is established by integrating the actual energy generation data of the production stage, the energy storage efficiency data of the storage stage, the actual energy supply and demand data of the distribution stage, and the energy consumption change data of the consumption stage. The model includes a weighted average method, a multiple regression analysis or a comprehensive evaluation model. According to the model, the energy coordination index is calculated to evaluate the coordination between each stage, including the matching degree of energy supply and demand, the efficiency of storage and consumption, the balance degree of production and use, etc. in each stage, and the energy coordination index is generated, which reflects the overall coordination and efficiency of the energy system in each stage. The calculated energy coordination index is applied to the cloud-based new energy health status assessment model. The model evaluates the health status of new energy by analyzing the coordination index and other relevant data (such as historical health data and environmental impact data). A prediction model (such as time series prediction, machine learning model) can be used to generate health status prediction data, and cloud-based new energy health status prediction data is generated, which shows the health status of the new energy system and future change trends. The cloud-based new energy health status prediction data is combined with the standard cloud-based new energy monitoring data to establish a multi-dimensional energy scheduling optimization model. Energy scheduling is optimized by applying optimization algorithms (such as linear programming, integer programming, and heuristic algorithms). The model considers factors in multiple dimensions, such as energy supply capacity, demand forecast, cost-effectiveness, etc., and generates energy scheduling optimization data, including optimized scheduling plans, resource allocation and adjustment strategies. Based on the energy scheduling optimization data, the data of the energy scheduling management stage are intelligently scheduled. The intelligent scheduling system includes automatic control systems, scheduling algorithms, real-time monitoring feedback, etc., to generate energy stage intelligent scheduling data, which reflects the optimized energy scheduling arrangements and resource allocation. According to the energy stage intelligent scheduling data, energy status monitoring and scheduling operations are performed. Including real-time monitoring of energy status, evaluation of scheduling effects, adjustment of scheduling strategies, etc. Collect monitoring data and feedback information, and further optimize energy scheduling strategies according to actual conditions to ensure the efficient operation of the energy system. The calculated energy coordination index, cloud-based new energy health status prediction data, energy scheduling optimization data and energy stage intelligent scheduling data are stored in the database for subsequent analysis and application.

[0119] Preferably, step S42 includes the following steps:

[0120] Step S421: Performing energy dynamic change analysis on standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy dynamic change data;

[0121] Step S422: divide the cloud-based new energy dynamic change data into data sets to generate a model training set and a model test set; use a support vector set algorithm to perform model training on the model training set to generate a cloud-based new energy health prediction pre-model; perform model optimization iteration on the cloud-based new energy health prediction pre-model through the model test set, thereby generating a cloud-based new energy health prediction model;

[0122] Step S423: Importing the standard cloud-based new energy monitoring data into the cloud-based new energy health prediction model to perform cloud-based new energy health status assessment and generate cloud-based new energy health status prediction data.

[0123] In an embodiment of the present invention, standard cloud-based new energy monitoring data is obtained, including energy production, storage, distribution and consumption data in different time periods. Time series analysis, dynamic system modeling or coefficient of variation calculation and other technologies are applied to analyze the dynamic changes of energy on the monitoring data. Trend changes, periodic fluctuations and sudden anomalies are identified to generate cloud-based new energy dynamic change data, which shows the dynamic changes of the new energy system over time, including energy supply and demand fluctuations, efficiency changes, etc. The cloud-based new energy dynamic change data is divided to generate a model training set and a model test set. Random partitioning or time series cross-validation methods can usually be used. Ensure that the training set and the test set are representative and the data distribution is consistent. The support vector machine (SVM) algorithm is used for model training. SVM is suitable for processing high-dimensional data and classification problems, and can effectively predict the health status of new energy. The SVM model is trained using the model training set, including selecting a kernel function (such as a linear kernel, a radial basis kernel), adjusting hyperparameters (such as C, γ values), optimizing the model training process, and generating a cloud-based new energy health prediction pre-model, which is preliminarily trained based on the training set data. The cloud-based new energy health prediction model is tested and evaluated through the model test set to check the accuracy and generalization ability of the model. The model parameters are adjusted according to the test results, and optimization iterations are performed to improve the prediction performance of the model. Cross-validation, grid search and other technologies can be applied for further optimization to generate a cloud-based new energy health prediction model, which has high prediction accuracy and stability after optimization. Import standard cloud-based new energy monitoring data into the cloud-based new energy health prediction model. Including the latest monitoring data and historical data. Use the cloud-based new energy health prediction model to evaluate the input data and generate prediction results. The model predicts the health status of the new energy system based on the characteristics and patterns of the input data, and generates cloud-based new energy health status prediction data, which provides prediction results for the health status of the new energy system, including early warnings of potential problems and predictions of health trends.

[0124] Preferably, step S43 includes the following steps:

[0125] Step S431: Compare the cloud-based new energy health status prediction data with a preset standard health status threshold. When the cloud-based new energy health status prediction data is greater than or equal to the preset standard health status threshold, a long-term scheduling demand mode is set based on the cloud-based new energy health status prediction data to obtain a long-term scheduling demand mode.

[0126] Step S432: when the cloud-based new energy health status prediction data is less than a preset standard health status threshold, a short-term scheduling demand mode is set based on the cloud-based new energy health status prediction data to obtain a short-term scheduling demand mode;

[0127] Step S433: Minimize the cost of standard cloud-based new energy monitoring data through the long-term scheduling demand model to generate a long-term energy scheduling strategy; maximize the efficiency of standard cloud-based new energy monitoring data through the short-term scheduling demand model to generate a short-term energy scheduling strategy;

[0128] Step S434: Based on the long-term energy scheduling strategy and the short-term energy scheduling strategy, the standard cloud-based new energy monitoring data is optimized in multiple dimensions to generate energy scheduling optimization data.

[0129] In an embodiment of the present invention, cloud-based new energy health status prediction data and a preset standard health status threshold are obtained. The standard health status threshold is usually set based on historical data and business needs, and is used to judge the health status of the new energy system. The cloud-based new energy health status prediction data is compared and analyzed with the standard health status threshold. If the cloud-based new energy health status prediction data is greater than or equal to the preset standard health status threshold, it means that the system health status is good, and the long-term planning and scheduling requirements are reasonable. Based on this health status prediction data, a long-term scheduling demand mode is set. Including long-term energy demand prediction, resource planning, reserve management and other aspects, a long-term scheduling demand mode is generated. If the cloud-based new energy health status prediction data is less than the preset standard health status threshold, it means that the system health status is at risk and short-term adjustments are required. Based on this health status prediction data, a short-term scheduling demand mode is set. Including short-term demand prediction, immediate resource allocation, emergency response and other aspects, a short-term scheduling demand mode is generated. The long-term scheduling demand mode is used to schedule and optimize the standard cloud-based new energy monitoring data, with the goal of minimizing long-term operation and maintenance costs. Cost minimization algorithms (such as linear programming and integer programming) can be used to optimize resource allocation and scheduling plans, and generate long-term energy scheduling strategies, including long-term operation plans, resource allocation strategies, cost control measures, etc. Use the short-term scheduling demand model to schedule and optimize the standard cloud-based new energy monitoring data, with the goal of maximizing system efficiency and operating results in the short term. Efficiency maximization algorithms (such as dynamic programming and heuristic optimization) can be used to optimize short-term resource scheduling and energy utilization, and generate short-term energy scheduling strategies, including short-term operation plans, immediate adjustment measures, efficiency improvement strategies, etc. Integrate and optimize strategy information based on long-term energy scheduling strategies and short-term energy scheduling strategies. Consider the balance between long-term and short-term goals to ensure the comprehensiveness and flexibility of energy scheduling. Apply multi-dimensional optimization algorithms to perform comprehensive scheduling optimization on standard cloud-based new energy monitoring data. Including comprehensive scheduling models, global optimization algorithms, etc., to ensure coordination in various dimensions (such as cost, efficiency, risk), and generate final energy scheduling optimization data, including comprehensive scheduling plans, resource optimization configuration, strategy adjustment suggestions, etc.

[0130] In this specification, a cloud-based new energy state prediction and scheduling system based on a deep network is provided, which is used to execute the above-mentioned cloud-based new energy state prediction and scheduling method based on a deep network. The cloud-based new energy state prediction and scheduling system based on a deep network includes:

[0131] The data acquisition module is used to obtain cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data acquisition on the cloud-based new energy network data based on the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data;

[0132] The production storage analysis module is used to classify the standard cloud-based new energy monitoring data into energy dispatch management phases and generate energy dispatch management phase data, wherein the energy dispatch management phase data includes energy production phase data, energy storage phase data, energy distribution phase data and energy consumption phase data; based on the energy production phase data, the standard cloud-based new energy monitoring data is analyzed for energy generation impact and the actual energy generation data of the production phase is generated; based on the energy storage phase data, the standard cloud-based new energy monitoring data is analyzed for energy storage status and the energy storage efficiency data of the storage phase is generated;

[0133] The distribution and consumption analysis module is used to map the power grid transmission capacity of the standard cloud-based new energy monitoring data based on the energy distribution stage data, and generate the actual energy supply and demand data in the distribution stage; based on the energy consumption stage data, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status, and the energy consumption change data in the consumption stage is generated;

[0134] The energy scheduling module is used to calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; to evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index, and to generate cloud-based new energy health status prediction data; to perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

[0135] The beneficial effect of the present invention is that the new energy network data is obtained through the cloud, and the network topology analysis is performed to generate topology data. This process ensures a global understanding of the new energy network structure and lays the foundation for subsequent data collection and monitoring. Standardization of cloud-based new energy monitoring data ensures that the data is consistent between different stages and different devices, which provides high-quality and reliable data input for subsequent analysis. Through topological analysis, the structure of the new energy network is deeply understood, the data collection process is optimized, and it is helpful to identify key nodes and potential bottlenecks, thereby improving the monitoring efficiency and reliability of the new energy network. The new energy scheduling management is divided into four stages: production, storage, distribution and consumption, which refines the entire new energy management process. This classification method helps to analyze each link independently and make the scheduling more targeted. Through classification analysis, the operation status of each stage can be accurately evaluated, and stage data can be provided to provide a basis for subsequent decision-making. The power generation analysis in the production stage ensures the high efficiency of new energy production and can identify the factors affecting the change in power generation. Data analysis in the storage stage can improve the efficiency of energy storage and avoid energy waste. Mapping the transmission capacity of the power grid in the energy distribution stage and generating actual supply and demand data can help identify load balancing problems in the power grid, optimize supply and demand matching, and improve the transmission efficiency of the power grid. The analysis of power grid transmission capacity ensures the stability and efficiency of power transmission and reduces energy loss. The analysis of energy consumption status can provide dynamic monitoring of changes in energy use, thereby helping to discover fluctuations in energy consumption and make timely adjustments, which helps to optimize the energy consumption structure and reduce unnecessary energy waste. Based on the data of the production, storage, distribution and consumption stages, the energy coordination index is calculated to comprehensively evaluate the operational coordination of the entire energy system. The index can reflect the coordination level between each stage and help discover potential energy management problems. The coordination index provides quantitative indicators for energy status monitoring and system optimization, which helps to accurately dispatch. The health status of the cloud-based new energy system is evaluated through the energy coordination index to generate health status prediction data. This prediction helps to discover potential risks and problems in advance and ensure the long-term healthy operation of the new energy network. Intelligent scheduling is carried out based on the health status prediction data to optimize the use and management of energy at each stage, maximize energy utilization, and improve the operating efficiency and stability of the new energy system. Therefore, the present invention solves the problems of dispersion, real-time and inefficient cloud-based new energy status prediction and scheduling in the prior art through standardized data integration, full life cycle management, real-time dynamic prediction and energy coordination optimization.

[0136] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0137] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A cloud-based new energy state prediction and scheduling method based on deep network, characterized in that: The following steps are involved: Step S1: Acquire cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data collection on the cloud-based new energy network data according to the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data; Step S2: classify the standard cloud-based new energy monitoring data in the energy dispatch management stage to generate energy dispatch management stage data, wherein the energy dispatch management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data; perform energy power generation impact analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate actual energy power generation data in the production stage; Based on the energy storage stage data, the energy storage status of the standard cloud-based new energy monitoring data is analyzed to generate energy storage efficiency data for the storage stage; Step S3: Based on the data of the energy distribution stage, the standard cloud-based new energy monitoring data is mapped to the power grid transmission capacity to generate the actual energy supply and demand data of the distribution stage; based on the data of the energy consumption stage, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status to generate the energy consumption change data of the consumption stage; Step S4: Calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy health status prediction data; perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

2. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtain cloud-based new energy network data; Step S12: performing network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; performing cloud-based monitoring node confirmation on the cloud-based new energy network data according to the cloud-based new energy network topology data to obtain cloud-based new energy network monitoring node data; Step S13: collecting cloud-based new energy monitoring data from cloud-based new energy network monitoring node data based on a preset time interval to generate cloud-based new energy monitoring data; Step S14: preprocessing the cloud-based new energy monitoring data to generate standard cloud-based new energy monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling, and data outlier processing.

3. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: classifying the standard cloud-based new energy monitoring data by energy dispatch management stage to generate energy dispatch management stage data, wherein the energy dispatch management stage data includes energy production stage data, energy storage stage data, energy distribution stage data, and energy consumption stage data; Step S22: Performing energy type analysis on the standard cloud-based new energy monitoring data based on the energy production stage data to generate energy type data; performing monitoring address IP tracking on the cloud-based new energy network monitoring node data through the energy type data to generate new energy monitoring address tracking data; Step S23: using environmental sensors to monitor meteorological data on the new energy monitoring address tracking data to generate meteorological monitoring data; using the meteorological monitoring data to analyze the impact of energy type data on energy generation, and generate actual energy generation data in the production stage; Step S24: extracting storage stage features of the standard cloud-based new energy monitoring data based on the energy storage stage data to obtain storage stage feature data; performing energy storage state analysis on the storage stage feature data to generate storage stage energy storage efficiency data.

4. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: screening the energy storage device operation data of the standard cloud-based new energy monitoring data based on the energy storage stage data to obtain the energy storage device operation data; Step S242: Calculate the storage capacity of the energy storage device operation data to generate the energy storage device storage capacity data; extract energy storage characteristics from the energy storage device operation data to obtain energy storage characteristic data; Step S243: converting the charge and discharge curves according to the energy storage characteristic data to generate an energy charge curve and an energy discharge curve; overlaying the energy charge curve and the energy discharge curve to generate an energy charge and discharge overlay curve; analyzing the overlay points of the energy charge and discharge overlay data to generate energy charge and discharge level buffer data; Step S244: Calculate the energy storage device utilization efficiency based on the energy charging and discharging level buffer data and the energy storage device storage capacity data to generate storage phase energy storage efficiency data.

5. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Based on the energy distribution stage data, the new energy monitoring address tracking data is used to generate energy regional distribution data; the energy regional distribution data is used to perform power demand analysis to generate energy regional distribution demand data; Step S32: Analyze the regional time period electricity load demand of the new energy monitoring address tracking data according to the regional energy distribution demand data to generate regional time period electricity load demand data; Step S33: Mapping the grid transmission capacity of the standard cloud-based new energy monitoring data based on the regional time period power load demand data to generate actual energy supply and demand data for the distribution stage; Step S34: extract consumption stage features from the standard cloud-based new energy monitoring data based on the energy consumption stage data to obtain consumption stage feature data; analyze the energy consumption status of the consumption stage feature data to generate consumption stage energy consumption change data.

6. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 5 is characterized in that: Step S34 includes the following steps: Step S341: extracting time series features from the standard cloud-based new energy monitoring data based on the energy consumption stage data to obtain consumption stage time series feature data; performing load change analysis on the consumption stage time series feature data to generate load change feature data; Step S342: classify the consumption patterns according to the load change characteristic data and the consumption stage time series characteristic data to generate consumption pattern data; perform power consumption state detection on the consumption pattern data to generate preliminary power consumption state data; Step S343: compare the power efficiency differences of the preliminary power usage status data to generate power consumption status comparison data; use the power consumption status comparison data to analyze the energy consumption changes of the preliminary power usage status data to generate energy consumption change data in the consumption stage.

7. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Calculate the energy coordination index based on the actual energy generation data in the production phase, the energy storage efficiency data in the storage phase, the actual energy supply and demand data in the distribution phase, and the energy consumption change data in the consumption phase to obtain the energy coordination index; Step S42: evaluating the health status of new energy on the cloud using the energy coordination index for the standard new energy monitoring data on the cloud, and generating new energy health status prediction data on the cloud; Step S43: performing multi-dimensional energy scheduling optimization on the standard cloud-based new energy monitoring data according to the cloud-based new energy health status prediction data to generate energy scheduling optimization data; Step S44: Perform energy intelligent scheduling on the energy scheduling management stage data through energy scheduling optimization data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

8. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 7 is characterized in that: Step S42 includes the following steps: Step S421: Performing energy dynamic change analysis on standard cloud-based new energy monitoring data through the energy coordination index to generate cloud-based new energy dynamic change data; Step S422: divide the cloud-based new energy dynamic change data into data sets to generate a model training set and a model test set; use a support vector set algorithm to perform model training on the model training set to generate a cloud-based new energy health prediction pre-model; perform model optimization iteration on the cloud-based new energy health prediction pre-model through the model test set, thereby generating a cloud-based new energy health prediction model; Step S423: Importing the standard cloud-based new energy monitoring data into the cloud-based new energy health prediction model to perform cloud-based new energy health status assessment and generate cloud-based new energy health status prediction data.

9. The cloud-based new energy state prediction and scheduling method based on deep network according to claim 7 is characterized in that: Step S43 includes the following steps: Step S431: Compare the cloud-based new energy health status prediction data with a preset standard health status threshold. When the cloud-based new energy health status prediction data is greater than or equal to the preset standard health status threshold, a long-term scheduling demand mode is set based on the cloud-based new energy health status prediction data to obtain a long-term scheduling demand mode. Step S432: when the cloud-based new energy health status prediction data is less than a preset standard health status threshold, a short-term scheduling demand mode is set based on the cloud-based new energy health status prediction data to obtain a short-term scheduling demand mode; Step S433: Minimize the cost of standard cloud-based new energy monitoring data through the long-term scheduling demand model to generate a long-term energy scheduling strategy; maximize the efficiency of standard cloud-based new energy monitoring data through the short-term scheduling demand model to generate a short-term energy scheduling strategy; Step S434: Based on the long-term energy scheduling strategy and the short-term energy scheduling strategy, the standard cloud-based new energy monitoring data is optimized in multiple dimensions to generate energy scheduling optimization data.

10. A cloud-based new energy state prediction and scheduling system based on deep network, characterized in that: Used to execute the cloud-based new energy state prediction and scheduling method based on deep network as claimed in claim 1, the cloud-based new energy state prediction and scheduling system based on deep network includes: The data acquisition module is used to obtain cloud-based new energy network data; perform network topology analysis on the cloud-based new energy network data to generate cloud-based new energy network topology data; perform cloud-based new energy monitoring data acquisition on the cloud-based new energy network data based on the cloud-based new energy network topology data to generate standard cloud-based new energy monitoring data; The production storage analysis module is used to classify the standard cloud-based new energy monitoring data into energy dispatch management phases and generate energy dispatch management phase data, wherein the energy dispatch management phase data includes energy production phase data, energy storage phase data, energy distribution phase data and energy consumption phase data; based on the energy production phase data, the standard cloud-based new energy monitoring data is analyzed for energy generation impact and the actual energy generation data of the production phase is generated; based on the energy storage phase data, the standard cloud-based new energy monitoring data is analyzed for energy storage status and the energy storage efficiency data of the storage phase is generated; The distribution and consumption analysis module is used to map the power grid transmission capacity of the standard cloud-based new energy monitoring data based on the energy distribution stage data, and generate the actual energy supply and demand data in the distribution stage; based on the energy consumption stage data, the standard cloud-based new energy monitoring data is analyzed for energy power consumption status, and the energy consumption change data in the consumption stage is generated; The energy scheduling module is used to calculate the energy coordination index for the actual energy generation data in the production stage, the energy storage efficiency data in the storage stage, the actual energy supply and demand data in the distribution stage, and the energy consumption change data in the consumption stage to obtain the energy coordination index; to evaluate the health status of cloud-based new energy for standard cloud-based new energy monitoring data through the energy coordination index, and to generate cloud-based new energy health status prediction data; to perform energy intelligent scheduling on the standard cloud-based new energy monitoring data based on the cloud-based new energy health status prediction data, thereby generating energy stage intelligent scheduling data to execute energy status monitoring and scheduling operations.

Images