Integrated energy system operation optimization system and method

Abstract

The application relates to the technical field of energy optimization, in particular to a comprehensive energy system operation optimization method.The method comprises the following steps: performing operation detection on a comprehensive energy system to obtain real-time operation data; performing position data monitoring on energy equipment to obtain energy equipment position data; performing energy node mapping on the energy equipment position data to construct an energy node matrix; performing energy demand analysis on the energy node matrix according to the real-time operation data to generate energy demand data; performing energy performance calculation on the real-time operation data according to the energy demand data to generate node energy performance data; performing energy load trend prediction on the real-time operation data through the node energy performance data to generate node load trend data; and performing node load analysis on the energy node matrix through the node load trend data to generate a node load value.The application realizes efficient and accurate energy system optimization.

Description

Technical Field

[0001] This invention relates to the field of energy optimization technology, and in particular to a system and method for optimizing the operation of integrated energy systems. Background Technology

[0002] With the continuous evolution of energy supply and demand patterns and the increasing importance of environmental sustainability, modern industry and society require different types of energy, including electricity, natural gas, solar energy, and wind energy. This diversity brings complexity to the energy supply chain, necessitating the comprehensive optimization of the production, transmission, storage, and use of different energy sources. Optimizing the operation of integrated energy systems has become a key challenge for industry and society. Energy systems encompass various forms of energy, including electricity, heat, and chemical energy. Their efficient operation is crucial for reducing energy costs, minimizing environmental impact, and ensuring the reliability of energy supply. Traditional operation and management methods often suffer from low energy operating efficiency and inaccuracies; therefore, an intelligent integrated energy system operation optimization system and methodology are needed. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention proposes a comprehensive energy system operation optimization system and method to solve at least one of the aforementioned technical problems.

[0004] To achieve the above objectives, the present invention provides a method for optimizing the operation of a comprehensive energy system, comprising the following steps:

[0005] Step S1: Perform operational monitoring on the integrated energy system to obtain real-time operational data; monitor the location data of energy equipment to obtain energy equipment location data; map the energy equipment location data to energy nodes and construct an energy node matrix;

[0006] Step S2: Perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; perform energy performance calculation on the real-time operating data based on the energy demand data to generate node energy performance data;

[0007] Step S3: Predict energy load trends from real-time operating data using node energy performance data to generate node load trend data; perform node load analysis on the energy node matrix using node load trend data to generate node load values;

[0008] Step S4: Based on the node energy performance data, construct a distributed multi-level structure for the energy node matrix, and build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; perform energy scheduling priority analysis on the node load values ​​according to the energy demand data, and generate node scheduling priority data.

[0009] Step S5: Perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct an energy optimization strategy.

[0010] Step S6: Visualize the energy optimization strategy to generate an energy optimization visualization view; use a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to construct an energy scheduling optimization model.

[0011] This invention enables real-time acquisition of operational status and performance data of an integrated energy system through operational monitoring. This allows for understanding the current actual operating conditions of the energy system, and monitoring the location data of energy equipment helps construct an accurate spatial mapping within the energy node matrix. It allows for the correspondence between equipment in the energy system and its physical location, providing a foundation for subsequent analysis. Analysis of real-time operational data generates accurate energy demand data, revealing the system's current energy demand. Calculating node energy performance based on energy demand data provides crucial information about energy supply and consumption. Analyzing node energy performance data allows for the prediction of future energy load trends, enabling advance preparation for energy allocation and scheduling. Analyzing node load values ​​helps understand the actual load of each node. Constructing a distributed, multi-level energy hierarchy based on energy performance data aids in a better understanding of the energy system's hierarchical structure and distribution. By performing scheduling priority analysis on node load values, it's possible to determine which nodes have priority in energy scheduling, thus allocating energy more effectively. Dynamic energy scheduling decision analysis based on node scheduling priority data enables real-time energy allocation, ensuring the system's consistently efficient operation. By dynamically optimizing allocation analysis, more flexible and efficient energy optimization strategies can be established. Visualizing these strategies allows decision-makers to intuitively understand the optimization results, facilitating the development of more suitable energy dispatching schemes. Furthermore, utilizing recurrent convolutional networks to perform dilated convolutions on the visualized view allows for the extraction of higher-level features, thereby constructing a more refined and efficient energy dispatching optimization model.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Perform operational monitoring on the integrated energy system and obtain real-time operational data;

[0014] Step S12: Monitor the location data of the energy equipment and obtain the location data of the energy equipment;

[0015] Step S13: Perform spatial topology analysis on the energy equipment to generate spatial topology data;

[0016] Step S14: Use the location data of energy equipment to map energy nodes to the spatial topology data and construct an energy node matrix.

[0017] This invention, through operational monitoring and acquisition of real-time operational data, enables an understanding of the current actual operating status of an integrated energy system, including information on energy supply, energy consumption, and equipment operating status. This provides benchmark data for energy system optimization, helps identify potential problems and performance bottlenecks, and monitoring the location data of energy equipment helps establish the physical layout of the integrated energy system. This helps understand the spatial relationships between devices, including distance and connection methods, which is crucial for energy system optimization. Spatial topology analysis helps determine the topological relationships between energy devices, including connections and transmission paths. This provides detailed information about the system's internal structure, helping to understand energy flow and transmission paths, providing a foundation for energy allocation and scheduling. By combining the location data of energy devices with spatial topology data, an energy node mapping can be established, thereby creating an energy node matrix. This matrix integrates device, location, and topology information to form a structural representation of the system. This provides a key tool for energy system analysis and optimization, including understanding the energy transmission relationships between nodes, energy paths, and potential bottlenecks.

[0018] Preferably, step S2 includes the following steps:

[0019] Step S21: Calculate energy consumption based on real-time operating data and generate node energy consumption parameters;

[0020] Step S22: Perform energy efficiency analysis on real-time operating data based on node energy consumption parameters to generate node energy efficiency data;

[0021] Step S23: Perform energy demand analysis on the energy node matrix based on the node energy efficiency data to generate energy demand data;

[0022] Step S24: Perform demand response analysis on real-time operating data based on energy demand data to generate energy demand response data;

[0023] Step S25: Calculate the energy performance of the real-time operating data based on the energy demand response data and the node energy performance calculation formula to generate node energy performance data.

[0024] This invention quantifies the energy consumption of each node by calculating real-time operational data, helping to identify which nodes perform well in terms of energy consumption and which need improvement. Generating node energy consumption parameters provides information about the consumption levels of each node, laying the foundation for energy optimization. By combining energy consumption parameters with real-time operational data, the energy efficiency of each node can be evaluated. This helps determine which nodes perform well in terms of energy consumption per unit and which may be wasteful. Generating node energy efficiency data helps identify potential areas for improvement to enhance the overall system's energy efficiency. Based on node energy efficiency data, energy demand analysis can be performed to determine the contribution of different nodes to the system's energy demand. This helps to understand which nodes play a critical role in meeting energy demand, allowing for targeted energy allocation and scheduling to meet the needs of different nodes. Demand response analysis helps understand the demand of different nodes in the system and their impact on energy supply. This helps to better adapt to changes in the system, ensuring that the needs of critical nodes are met, thereby improving system reliability and resilience. Energy performance calculations utilize energy demand response data and performance formulas to provide performance assessments of different nodes in meeting demand. This helps identify well-performing nodes and potential performance improvement opportunities. Generating node energy performance data can provide important information for the long-term operation and improvement of the system.

[0025] Preferably, the formula for calculating the node energy performance in step S25 is as follows:

[0026]

[0027] Where E is the node energy performance value, M is the node energy capacity, P is the node energy loss value, Q is the node energy supply frequency, K is the node operating efficiency, d is the energy utilization efficiency, A is the node actual load value, P is the node energy output cycle, L is the node energy density, n is the number of load devices of the node, R is the node energy power, and T is the node running time.

[0028] This invention is achieved through The natural logarithm of the product of node energy capacity and energy loss was calculated to quantify the node's energy capacity and loss levels, transforming them into a logarithmic scale. The square root of the node's energy supply frequency was then calculated; the energy supply frequency represents the number of times a node can obtain energy per unit time. Introducing the square root helps to balance the influence of frequency, avoiding excessive influence of extreme frequency values ​​on the final result. The natural logarithm of the product of node operating efficiency, energy utilization efficiency, and actual node load is calculated, taking into account operating efficiency, energy utilization efficiency, and load value, and transforming them into a logarithmic scale. The ratio of node energy output cycle to node energy density was calculated to the power of 1 / n. The energy output cycle represents the number of times a node can output energy per unit time, while the energy density represents the amount of energy per unit volume or unit area. The relationship between the energy output cycle and the energy density was considered and adjusted by exponential calculation. This calculation uses a negative exponent to determine the ratio of node energy power to node runtime. Energy power represents the amount of energy consumed by a node per unit time, while node runtime represents the node's operating time. The calculation considers the relationship between energy power and runtime, adjusting it through a negative exponentiation. The formula comprehensively considers parameters such as node energy capacity, energy loss, energy supply frequency, operating efficiency, energy utilization efficiency, and actual node load. By performing mathematical operations and transformations on these factors, the final node energy performance value is obtained. This allows for the evaluation and comparison of the energy performance of different nodes, thereby optimizing energy utilization and management.

[0029] Preferably, step S3 includes the following steps:

[0030] Step S31: Perform load fluctuation analysis on real-time operating data to generate load fluctuation data;

[0031] Step S32: Perform load time series analysis on the real-time running data to generate load time series data;

[0032] Step S33: Fit the load fluctuation data to a fluctuation curve based on the load time series data to generate a load fluctuation curve;

[0033] Step S34: Predict the energy load trend of the load fluctuation curve using node energy performance data, and generate node load trend data;

[0034] Step S35: Perform load balancing analysis on the energy node matrix using node load trend data to generate load balancing data;

[0035] Step S36: Perform node load analysis on the energy node matrix based on load balancing data to generate node load values.

[0036] This invention utilizes load fluctuation analysis to understand the load fluctuations at different nodes in a system. Generating load fluctuation data helps identify patterns and trends in load fluctuations, which is crucial for planning and managing energy systems. It reveals which nodes frequently experience load fluctuations, allowing for measures to stabilize energy distribution. Load time-series data provides time-series information about the load, enabling in-depth understanding of load changes over time. This is extremely useful for identifying seasonal, periodic, or random load variations, helping to better understand the dynamic characteristics of system operation. By fitting fluctuation curves, trends and patterns of load fluctuations can be summarized. This helps create models to predict future load fluctuations, leading to better planning of energy supply and demand. Combining node energy performance data with load fluctuation curves allows for the prediction of future load trends. This is crucial for planning energy supply and avoiding energy shortages or surpluses. Energy distribution can be adjusted based on load trend data to meet future demand. Load balancing analysis helps optimize load distribution across different nodes in the system. Generating load balancing data allows identification of nodes that may experience load imbalances, enabling measures to balance the load and improve system reliability and efficiency. Node load analysis provides a detailed understanding of the load level of each node. This helps determine which nodes are likely under significant load and which still have available capacity. This information can be used for decision-making, such as reallocating load or increasing energy resources to meet demand.

[0037] Preferably, step S3 includes the following steps:

[0038] Step S41: Classify the energy node matrix by node performance level based on node energy performance data, and generate node performance levels, including high-performance nodes, medium-performance nodes and low-performance nodes.

[0039] Step S42: Divide the energy node matrix into energy levels according to the node performance level to obtain the node energy hierarchy; among them, medium performance nodes are the first level energy level, high performance nodes are the second level energy level, and low performance nodes are the third level energy level.

[0040] Step S43: Construct a distributed multi-level structure for the energy node matrix through the node energy hierarchy, and construct a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure and a third-level energy hierarchy structure.

[0041] Step S44: Calculate the energy supply capacity of the distributed multi-level energy hierarchy based on energy demand data, and generate an energy supply capacity value;

[0042] Step S45: Perform energy scheduling priority analysis on node load values ​​based on energy supply capacity values ​​to generate node scheduling priority data.

[0043] This invention classifies nodes by performance level, identifying which nodes excel in energy performance, which have average performance, and which have poor performance. This helps determine the strengths and weaknesses of the system, leading to better resource allocation and performance management. Medium-performance nodes are at the first energy level, high-performance nodes at the second, and low-performance nodes at the third. In energy scheduling, medium-performance nodes are used first because high-performance nodes have high energy utilization but high operating costs and energy consumption, while low-performance nodes have very low energy utilization. Therefore, medium-performance nodes, representing the first energy level, are used to power the load devices. When medium-performance nodes are low on energy, high-performance nodes are then used for energy supply (second energy level). Finally, when high-performance nodes are low on energy, low-performance nodes are used, maximizing energy utilization and environmental friendliness. Dividing nodes into different energy levels allows for a hierarchical energy system structure. This helps manage nodes with different performance levels more effectively, allocating resources to appropriate levels and improving the overall efficiency and reliability of the system. The construction of a distributed, multi-level energy hierarchy allows for the establishment of a hierarchical, decentralized energy system. This structure is more flexible and can better adapt to the performance and needs of different energy nodes. It also provides more control options to accommodate the operation and management of different levels. By calculating energy supply capacity, the capacity of each energy level can be quantified to meet the system's energy demands. This helps determine which level requires more energy resources to ensure that the needs of the nodes are met while avoiding resource waste. Energy scheduling priority analysis helps determine which nodes should be prioritized when supplying energy to ensure efficient energy supply. This helps reduce energy waste, ensures a match between energy supply and demand, and improves the system's operational efficiency.

[0044] Preferably, step S45 includes the following steps:

[0045] Step S451: Based on the energy supply capacity value, determine the supply and demand matching of the node load value. When the energy supply capacity value is greater than or equal to the node load value, mark it as a low priority node for scheduling.

[0046] Step S452: Based on the energy supply capacity value, determine the supply and demand matching of the node load value. When the energy supply capacity value is less than the node load value, mark it as a high-priority node for scheduling.

[0047] Step S453: Perform energy scheduling priority analysis on low-priority and high-priority nodes to generate node scheduling priority data.

[0048] This invention categorizes nodes into two classes: low-priority nodes and high-priority nodes, based on whether their energy supply capacity is sufficient to meet load demands. Nodes that can meet the demands are marked as low-priority because they do not require urgent energy dispatch. This helps avoid unnecessary dispatching and resource waste. Nodes are marked as high-priority because their energy supply capacity is insufficient to meet their load demands. These nodes require more urgent energy dispatch to ensure their operation is not interrupted. This helps focus resources and efforts on meeting the most important needs. By analyzing high- and low-priority nodes, it provides guidance for energy dispatching. It helps decision-makers identify which nodes require more urgent energy allocation to meet their needs, and which nodes can operate with lower priority. This helps improve system efficiency and ensures that resources are allocated effectively to meet the most important energy demands.

[0049] Preferably, step S5 includes the following steps:

[0050] Step S51: Map the scheduling priority of the distributed multi-level energy hierarchy according to the node scheduling priority data to generate a node scheduling priority graph;

[0051] Step S52: Perform dynamic energy scheduling on the node scheduling priority graph according to the distributed multi-level energy hierarchy to generate dynamic energy scheduling data;

[0052] Step S53: Perform dynamic optimization and allocation analysis on the distributed multi-level energy hierarchy using dynamic energy dispatch data to construct an energy optimization strategy.

[0053] This invention maps different energy nodes to a distributed multi-level energy hierarchy using node scheduling priority data. This helps establish a node scheduling priority graph, where energy nodes are arranged according to their priority. In this way, energy system managers can clearly understand which energy nodes should have higher priority in energy allocation and which nodes can have lower priority. Dynamic energy scheduling combines actual energy allocation with the node scheduling priority graph. This helps allocate energy in actual operation, ensuring that high-priority nodes are prioritized, thereby reducing the potential risk of energy shortages. The generated dynamic energy scheduling data records the actual energy allocation of each node, providing a data foundation for subsequent analysis. Using dynamic energy scheduling data, the distributed multi-level energy hierarchy can be analyzed and optimized in real time. This helps identify potential bottlenecks, inefficient areas, and areas that may need improvement in the system. Based on the analysis results, energy optimization strategies can be constructed to adjust energy allocation, improve system efficiency, reduce energy waste, and cope with fluctuations in energy demand.

[0054] Preferably, the dynamic energy dispatch in step S52 specifically involves;

[0055] When a high-performance node is marked as a high-priority scheduling node, the energy scheduling of the first-level energy hierarchy is performed using the second-level energy hierarchy.

[0056] When a high-performance node is marked as a high-priority scheduling node, energy scheduling is performed on the second-level energy hierarchy using the three-level source hierarchy.

[0057] This invention enables optimized energy scheduling in the primary energy hierarchy by marking medium-performance nodes as high-priority scheduling nodes. This means the energy system will tend to allocate more energy resources to medium-performance nodes to ensure their efficient operation. This helps improve the overall system performance, especially for tasks or nodes with high performance requirements, allowing for more timely and sufficient fulfillment of their energy needs. Marking high-performance nodes as high-priority scheduling nodes allows for more granular scheduling in the secondary energy hierarchy. High-performance nodes are typically more sensitive to energy demands, thus scheduling at this level can be more flexible and detailed. Through optimized energy scheduling of high-performance nodes, the system can better adapt to applications with stringent performance requirements, improving the overall system efficiency and responsiveness.

[0058] Preferably, step S6 includes the following steps:

[0059] Step S61: Visualize the energy optimization strategy to generate an energy optimization visualization view;

[0060] Step S62: Use a recurrent convolutional network to perform convolutional preprocessing on the energy optimization visualization view to generate a convolutional sample set;

[0061] Step S63: Perform superpixel convolution data segmentation on the convolution sample set to generate convolution feature sequences;

[0062] Step S64: Perform dilated convolution on the convolutional feature sequence to generate a convolutional feature network;

[0063] Step S65: Use a multi-scale sampling algorithm to perform pooling multi-layer sampling on the convolutional feature network to generate a convolutional feature map;

[0064] Step S66: Perform data mining modeling on the convolutional feature map to construct an energy scheduling optimization model.

[0065] This invention visualizes energy optimization strategies, enabling the system to more clearly understand and analyze existing strategies. This helps decision-makers and engineers better understand the system's energy usage, identify potential problems and optimization opportunities, and provide input data for subsequent deep learning processing. Convolutional preprocessing helps extract features from image data, transforming the visualization into a computer-processable form. This improves data representation and provides better input data for subsequent steps. Generating convolutional sample sets is for use in deep learning models for further analysis and learning. Superpixel convolutional data segmentation divides images into smaller regions, helping the model better understand the features of different regions. This enhances the model's perceptual capabilities, enabling it to better capture local features in the energy system. Generating convolutional feature sequences prepares the data for subsequent processing. Dilated convolution is a convolutional neural network technique used to increase the receptive field of convolutional layers to better capture long-range dependencies in the data. This improves the model's understanding of energy system data and its feature extraction capabilities. Generating convolutional feature networks builds more complex feature representations for subsequent processing. Multi-scale pooling reduces data dimensionality and size without losing important information. This helps improve the computational efficiency of the model and better capture features at different scales. Generating convolutional feature maps is to obtain high-dimensional feature representations for subsequent modeling. Deep learning models use convolutional feature maps for data mining and modeling to build energy dispatch optimization models. This means the model can learn the complex patterns and characteristics of energy systems to provide more effective dispatch strategies. The final model can then make predictions and optimization decisions based on the data to achieve optimized operation of the energy system.

[0066] This specification provides a comprehensive energy system operation optimization system, comprising:

[0067] The node matrix module is used to monitor the operation of the integrated energy system and obtain real-time operation data; monitor the location data of energy equipment and obtain energy equipment location data; and map the energy equipment location data to energy nodes to construct an energy node matrix.

[0068] The energy performance module is used to perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; and to perform energy performance calculations on the real-time operating data based on the energy demand data to generate node energy performance data.

[0069] The load trend prediction module is used to predict the energy load trend of real-time operating data based on node energy performance data, and generate node load trend data; and to perform node load analysis on the energy node matrix based on the node load trend data, and generate node load values.

[0070] The scheduling priority module is used to construct a distributed multi-level structure of the energy node matrix based on node energy performance data, and to build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; and to perform energy scheduling priority analysis on node load values ​​based on energy demand data to generate node scheduling priority data.

[0071] The dynamic optimization module is used to perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; and to perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct energy optimization strategies.

[0072] The scheduling optimization model module is used to visualize energy optimization strategies and generate an energy optimization visualization view. It uses a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to construct an energy scheduling optimization model.

[0073] This invention generates real-time node energy performance data by performing energy demand analysis and energy performance calculations on an energy node matrix. This helps to deeply understand the system's energy needs and provides foundational data for subsequent optimization. Load trend prediction is performed using the node energy performance data to generate node load trend data. This helps the system predict future energy load conditions, prepare in advance, and optimize energy allocation and usage. The node load values ​​generated from node load analysis are important inputs for optimization. A distributed multi-level energy hierarchy is constructed using the node energy performance data, and energy scheduling priority analysis is performed based on energy demand data to generate node scheduling priority data. This helps to establish a hierarchical structure for the system, improving the flexibility and efficiency of energy scheduling. Dynamic energy scheduling decision analysis is performed based on the node scheduling priority data to generate dynamic energy scheduling data. Through dynamic optimization allocation analysis, an energy optimization strategy is constructed. This enables the system to dynamically adjust according to real-time demand, improving overall energy utilization efficiency. The energy optimization strategy is visualized, generating an energy optimization visualization view. A recurrent convolutional network is applied to dilated convolutions on the visualization view to construct an energy scheduling optimization model. This helps to more deeply understand and analyze the optimization strategy, improving the model's performance and accuracy. Attached Figure Description

[0074] Figure 1 This is a flowchart illustrating the steps of the integrated energy system operation optimization system and method of the present invention;

[0075] Figure 2 This is a detailed flowchart illustrating the implementation steps of step S1.

[0076] Figure 3 This is a detailed flowchart illustrating the implementation steps of step S2;

[0077] Figure 4 This is a flowchart illustrating the detailed implementation steps of step S3. Detailed Implementation

[0078] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0079] This application provides an integrated energy system operation optimization system and method. The implementing entities of the integrated energy system operation optimization system and method include, but are not limited to, mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc., which can be considered as general computing nodes in this application. The data processing platform includes, but is not limited to, at least one of an audio-visual management system, an information management system, and a cloud-based data management system.

[0080] Please see Figures 1 to 4 This invention provides a method for optimizing the operation of an integrated energy system, the method comprising the following steps:

[0081] Step S1: Perform operational monitoring on the integrated energy system to obtain real-time operational data; monitor the location data of energy equipment to obtain energy equipment location data; map the energy equipment location data to energy nodes and construct an energy node matrix;

[0082] Step S2: Perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; perform energy performance calculation on the real-time operating data based on the energy demand data to generate node energy performance data;

[0083] Step S3: Predict energy load trends from real-time operating data using node energy performance data to generate node load trend data; perform node load analysis on the energy node matrix using node load trend data to generate node load values;

[0084] Step S4: Based on the node energy performance data, construct a distributed multi-level structure for the energy node matrix, and build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; perform energy scheduling priority analysis on the node load values ​​according to the energy demand data, and generate node scheduling priority data.

[0085] Step S5: Perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct an energy optimization strategy.

[0086] Step S6: Visualize the energy optimization strategy to generate an energy optimization visualization view; use a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to construct an energy scheduling optimization model.

[0087] This invention enables real-time acquisition of operational status and performance data of an integrated energy system through operational monitoring. This allows for understanding the current actual operating conditions of the energy system, and monitoring the location data of energy equipment helps construct an accurate spatial mapping within the energy node matrix. It allows for the correspondence between equipment in the energy system and its physical location, providing a foundation for subsequent analysis. Analysis of real-time operational data generates accurate energy demand data, revealing the system's current energy demand. Calculating node energy performance based on energy demand data provides crucial information about energy supply and consumption. Analyzing node energy performance data allows for the prediction of future energy load trends, enabling advance preparation for energy allocation and scheduling. Analyzing node load values ​​helps understand the actual load of each node. Constructing a distributed, multi-level energy hierarchy based on energy performance data aids in a better understanding of the energy system's hierarchical structure and distribution. By performing scheduling priority analysis on node load values, it's possible to determine which nodes have priority in energy scheduling, thus allocating energy more effectively. Dynamic energy scheduling decision analysis based on node scheduling priority data enables real-time energy allocation, ensuring the system's consistently efficient operation. By dynamically optimizing allocation analysis, more flexible and efficient energy optimization strategies can be established. Visualizing these strategies allows decision-makers to intuitively understand the optimization results, facilitating the development of more suitable energy dispatching schemes. Furthermore, utilizing recurrent convolutional networks to perform dilated convolutions on the visualized view allows for the extraction of higher-level features, thereby constructing a more refined and efficient energy dispatching optimization model.

[0088] In this embodiment of the invention, reference Figure 1 The above is a flowchart illustrating the steps of a comprehensive energy system operation optimization system and method according to the present invention. In this example, the steps of the comprehensive energy system operation optimization method include:

[0089] Step S1: Perform operational monitoring on the integrated energy system to obtain real-time operational data; monitor the location data of energy equipment to obtain energy equipment location data; map the energy equipment location data to energy nodes and construct an energy node matrix;

[0090] In this embodiment, sensor devices are installed in the integrated energy system to monitor various key parameters, such as electricity usage, temperature, humidity, water flow, and gas usage. These sensors can be IoT devices or traditional monitoring equipment for real-time data acquisition. The acquired real-time data needs to be transmitted to a central data storage or cloud platform. Location sensors (such as GPS, RFID, or Wi-Fi positioning devices) are installed on energy equipment to obtain their location information. This can cover generators, solar panels, wind turbines, etc. Similar to operational data, location data needs to be collected and transmitted to a central database or cloud platform. The location data is then cleaned and preprocessed to ensure accurate location information. This may include removing outliers or correcting GPS signal errors. Various energy nodes in the integrated energy system are defined, such as generators, batteries, solar panels, wind turbines, energy storage devices, grid connection points, etc. They are categorized according to function and association, and real-time operational data and location data are integrated into a unified energy node mapping system. This can be achieved by establishing data association rules to map devices and their data points to nodes, creating a connection between energy devices and energy nodes. By integrating the data, an energy node matrix can be constructed, where each row represents a node and each column represents a data point or attribute. This matrix will facilitate a holistic view of the system and data analysis.

[0091] Step S2: Perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; perform energy performance calculation on the real-time operating data based on the energy demand data to generate node energy performance data;

[0092] In this embodiment, an appropriate analysis method is selected to calculate energy demand based on real-time data. This may include models based on historical data, prediction algorithms, statistical methods, etc. Demand can encompass electricity demand, heat demand, fuel demand, etc., and the selected method is used to calculate the energy demand for each energy node. This can be a real-time, periodic, or event-triggered calculation, depending on the system requirements. The calculated demand data is combined with the energy node matrix to generate a new data matrix containing the energy demand information for each node. An appropriate method is then selected to calculate the performance of each energy node. This may include efficiency calculations, energy output calculations, cost-benefit analyses, etc., and the selected method is used to calculate the energy performance parameters for each node. This will include energy utilization rate, energy output rate, energy consumption rate, etc. The calculated performance data is combined with the energy node matrix to generate a new data matrix containing the energy performance information for each node.

[0093] Step S3: Predict energy load trends from real-time operating data using node energy performance data to generate node load trend data; perform node load analysis on the energy node matrix using node load trend data to generate node load values;

[0094] In this embodiment, the acquired node energy performance data needs to be cleaned and organized to ensure its accuracy and completeness. This may include removing outliers and filling in missing data. Before prediction and analysis, the performance data of different nodes are standardized to ensure they are compared under the same metric. Appropriate data analysis methods are selected to predict the energy load trend of each node. This may include time series analysis, regression analysis, machine learning models, etc. Historical node energy performance data is used to train a selected model to predict future energy load trends. The model selection will depend on the nature of the data and the characteristics of the system. Using the trained model, the future energy load trend of each node is predicted, typically based on time, to obtain a load estimate over a future period. The predicted energy load trend data is associated with node identifiers to generate node load trend data. This generated node load trend data is combined with an energy node matrix to establish a new dataset containing load trend information for each node. Appropriate analysis methods are selected to extract the node load values ​​from the trend data. This can include average, peak, valley, load distribution, etc. The selected method is used to calculate the load value of each node, which reflects the load demand in the energy system. The calculated load value is associated with the node identifier to generate a new data matrix containing the load value information of each node.

[0095] Step S4: Based on the node energy performance data, construct a distributed multi-level structure for the energy node matrix, and build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; perform energy scheduling priority analysis on the node load values ​​according to the energy demand data, and generate node scheduling priority data.

[0096] In this embodiment, a distributed multi-level structure is constructed for the energy node matrix based on node energy performance data, creating a distributed multi-level energy hierarchy. This hierarchy includes a first-level, second-level, and third-level energy hierarchy. The first-level energy hierarchy prioritizes power supply to the load devices. When the first-level energy hierarchy is insufficient, the second-level energy hierarchy is used to power the load devices; when the second-level energy hierarchy is insufficient, the third-level energy hierarchy is used. Real-time or historical energy demand data is acquired, including the energy demand of different nodes and time windows. This energy demand data is used to analyze node load values ​​to identify which energy demands on different nodes are critical, urgent, or have high priority. This may involve techniques such as load forecasting and demand change analysis. Based on the analysis of energy demand data, it is determined which nodes need to be prioritized to meet their energy demands and how to schedule energy to meet these demands. This may include developing scheduling plans and optimizing energy allocation. Node scheduling priority information is associated with the corresponding nodes to generate node scheduling priority data, which records the scheduling order or priority of each node.

[0097] Step S5: Perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct an energy optimization strategy.

[0098] In this embodiment, real-time or historical energy production and demand data are acquired, including node load, energy supply status, energy cost, and energy quality. This data is used to support decision analysis, applying node scheduling priority data to nodes at all levels of the energy hierarchy. This determines which nodes in the multi-level structure require priority scheduling, and dynamic scheduling decisions are made based on current energy demand and node scheduling priority information. This may involve decisions such as adjusting energy allocation, starting and stopping energy sources, and adjusting energy transmission routes. Mathematical models, optimization algorithms, or artificial intelligence techniques are used to establish an energy scheduling model to determine how to dynamically schedule energy to meet node needs. Based on the dynamic scheduling decisions, actual energy allocation and scheduling operations are executed to ensure that node needs are met. This may include adjusting generator output, changing grid configuration, starting and stopping storage systems, etc., and recording actual dynamic energy scheduling data, including which operations are performed, their timing, and their effects. These data will be used for further analysis and optimization. By utilizing the recorded dynamic energy dispatch data, the performance of the energy system will be analyzed, including cost, efficiency, and reliability. Based on the analysis results, an optimization model of the energy system will be established to determine how to better allocate and dispatch energy to meet node demand and minimize costs. Specific optimization strategies will be formulated, which may include more efficient resource utilization, more optimized dispatch plans, and better energy source selection. Based on the optimization strategies, actual energy system adjustments and operations will be implemented.

[0099] Step S6: Visualize the energy optimization strategy to generate an energy optimization visualization view; use a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to construct an energy scheduling optimization model.

[0100] In this embodiment, data visualization tools such as Matplotlib, Seaborn, and Tableau are used to transform optimization data into graphs or charts. This can include line charts, bar charts, heatmaps, etc., to better understand and analyze the data, creating visual views of energy optimization strategies. These views must clearly convey the system's performance and optimization status. The generated energy optimization visualizations are then converted into data formats suitable for deep learning, typically image data. This may involve standardizing and preprocessing the images, and using recurrent convolutional networks (such as LSTM, GRU, etc.) to process the visualization data. These networks are particularly well-suited for sequential data, capturing temporal relationships. Dilated convolutional layers are introduced on top of the recurrent convolutional network to expand the network's receptive field and better capture long-term dependencies in time-series data. Dilated convolutions are advantageous when processing different time steps in sequential data. Using labeled optimization data, a recurrent convolutional network is trained to learn an optimization model for energy scheduling. The training process includes forward propagation, backpropagation, loss calculation, etc., and the trained model is evaluated to ensure good performance. As needed, hyperparameter tuning and model optimization can be performed to integrate the trained recurrent convolutional network model with actual energy dispatch optimization strategies. This may include embedding the model into the actual dispatch system, using the constructed optimized model to monitor and optimize the real-time operation of the energy system. The model can dynamically adjust energy allocation and dispatch strategies based on actual data, establishing a feedback loop to continuously improve and optimize the energy dispatch model. This can be achieved through comparison with actual operating performance and continuous model updates.

[0101] In this embodiment, reference Figure 2 The above is a detailed implementation flowchart of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0102] Step S11: Perform operational monitoring on the integrated energy system and obtain real-time operational data;

[0103] Step S12: Monitor the location data of the energy equipment and obtain the location data of the energy equipment;

[0104] Step S13: Perform spatial topology analysis on the energy equipment to generate spatial topology data;

[0105] Step S14: Use the location data of energy equipment to map energy nodes to the spatial topology data and construct an energy node matrix.

[0106] This invention, through operational monitoring and acquisition of real-time operational data, enables an understanding of the current actual operating status of an integrated energy system, including information on energy supply, energy consumption, and equipment operating status. This provides benchmark data for energy system optimization, helps identify potential problems and performance bottlenecks, and monitoring the location data of energy equipment helps establish the physical layout of the integrated energy system. This helps understand the spatial relationships between devices, including distance and connection methods, which is crucial for energy system optimization. Spatial topology analysis helps determine the topological relationships between energy devices, including connections and transmission paths. This provides detailed information about the system's internal structure, helping to understand energy flow and transmission paths, providing a foundation for energy allocation and scheduling. By combining the location data of energy devices with spatial topology data, an energy node mapping can be established, thereby creating an energy node matrix. This matrix integrates device, location, and topology information to form a structural representation of the system. This provides a key tool for energy system analysis and optimization, including understanding the energy transmission relationships between nodes, energy paths, and potential bottlenecks.

[0107] In this embodiment, sensors are deployed in the energy system to monitor various energy parameters such as electricity, heat, and cooling. These sensors may include electricity meters, temperature sensors, humidity sensors, etc. Data acquisition devices are configured to acquire sensor data in real time. This data may include parameters such as energy consumption, temperature, humidity, current, and voltage. The collected real-time data is stored in a database or cloud storage for further analysis and processing. Location sensors are deployed or GPS devices are used to monitor the location of energy equipment. This may include energy equipment such as solar panels, generators, and wind turbines. Location sensors are configured to acquire the location data of these energy equipment in real time. This data typically includes location information such as longitude, latitude, and altitude. The location data and the correlation information between the energy equipment are compiled into a dataset. This may include building layout, equipment connection relationships, etc., and the spatial topology between energy equipment is analyzed. This helps determine the relative positions and connections between energy equipment. Based on the analysis results, spatial topology data describing the relationships between energy equipment is generated. This can be represented using a graph structure from graph theory, integrating location data and spatial topology data to create a comprehensive dataset that includes location information and equipment connection information, determining which devices or locations are defined as energy nodes. These nodes can be energy-generating devices (such as solar panels and wind turbines), energy-consuming devices (such as buildings and equipment), or energy storage devices (such as batteries). Linking the location data of these energy nodes with spatial topology data creates an energy node map. This helps determine the physical connections and topological relationships between energy nodes. Based on the node map, an energy node matrix is ​​constructed, including the relationships between nodes, connection states, and other relevant information. This matrix can then be used for further energy system optimization algorithms.

[0108] In this embodiment, reference Figure 3 The above is a detailed implementation flowchart of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0109] Step S21: Calculate energy consumption based on real-time operating data and generate node energy consumption parameters;

[0110] Step S22: Perform energy efficiency analysis on real-time operating data based on node energy consumption parameters to generate node energy efficiency data;

[0111] Step S23: Perform energy demand analysis on the energy node matrix based on the node energy efficiency data to generate energy demand data;

[0112] Step S24: Perform demand response analysis on real-time operating data based on energy demand data to generate energy demand response data;

[0113] Step S25: Calculate the energy performance of the real-time operating data based on the energy demand response data and the node energy performance calculation formula to generate node energy performance data.

[0114] This invention quantifies the energy consumption of each node by calculating real-time operational data, helping to identify which nodes perform well in terms of energy consumption and which need improvement. Generating node energy consumption parameters provides information about the consumption levels of each node, laying the foundation for energy optimization. By combining energy consumption parameters with real-time operational data, the energy efficiency of each node can be evaluated. This helps determine which nodes perform well in terms of energy consumption per unit and which may be wasteful. Generating node energy efficiency data helps identify potential areas for improvement to enhance the overall system's energy efficiency. Based on node energy efficiency data, energy demand analysis can be performed to determine the contribution of different nodes to the system's energy demand. This helps to understand which nodes play a critical role in meeting energy demand, allowing for targeted energy allocation and scheduling to meet the needs of different nodes. Demand response analysis helps understand the demand of different nodes in the system and their impact on energy supply. This helps to better adapt to changes in the system, ensuring that the needs of critical nodes are met, thereby improving system reliability and resilience. Energy performance calculations utilize energy demand response data and performance formulas to provide performance assessments of different nodes in meeting demand. This helps identify well-performing nodes and potential performance improvement opportunities. Generating node energy performance data can provide important information for the long-term operation and improvement of the system.

[0115] In this embodiment, appropriate algorithms and models are used to process real-time data to calculate the energy consumption of each energy node. This can cover various energy types such as electrical energy, thermal energy, and cooling energy. The calculated energy consumption data is associated with the corresponding nodes to generate node energy consumption parameters. The node energy consumption parameters are integrated with real-time operating data to ensure that the energy consumption parameters of each node are related to its operating status. Appropriate models and algorithms are used to calculate the energy efficiency of each node. Energy efficiency can be expressed as the ratio of energy output to input, or other appropriate indicators, depending on the system performance metrics. The calculated node energy efficiency data is associated with the corresponding nodes to generate node energy efficiency data. The node energy efficiency data is combined with the energy node matrix to ensure that the energy efficiency data of each node is related to its location and connection relationships. Using the energy node matrix and node energy efficiency data, the energy demand between different nodes is calculated. This can include the demand for energy transmission, storage, and distribution. The energy demand data is combined with real-time operating data to ensure that the demand data of each node is related to its actual operating status. The energy demand data is used to analyze the actual operating data to determine whether the demand is met. If demand is not met, determine the necessary response strategy, such as energy scheduling or optimizing operating parameters. Associate the calculated response data with the corresponding nodes to generate energy demand response data. Integrate this energy demand response data with real-time operating data to ensure that each node's demand response data is correlated with its operating status. Use appropriate formulas and indicators to calculate the energy performance of each node. This may include energy usage efficiency, energy transmission losses, etc. Associate the calculated node energy performance data with the corresponding nodes to generate node energy performance data.

[0116] In this embodiment, the node energy performance calculation formula in step S25 is as follows:

[0117]

[0118] Where E is the node energy performance value, M is the node energy capacity, P is the node energy loss value, Q is the node energy supply frequency, K is the node operating efficiency, d is the energy utilization efficiency, A is the node actual load value, P is the node energy output cycle, L is the node energy density, n is the number of load devices of the node, R is the node energy power, and T is the node running time.

[0119] This invention is achieved through The natural logarithm of the product of node energy capacity and energy loss was calculated to quantify the node's energy capacity and loss levels, transforming them into a logarithmic scale. The square root of the node's energy supply frequency was then calculated; the energy supply frequency represents the number of times a node can obtain energy per unit time. Introducing the square root helps to balance the influence of frequency, avoiding excessive influence of extreme frequency values ​​on the final result. The natural logarithm of the product of node operating efficiency, energy utilization efficiency, and actual node load is calculated, taking into account operating efficiency, energy utilization efficiency, and load value, and transforming them into a logarithmic scale. The ratio of node energy output cycle to node energy density was calculated to the power of 1 / n. The energy output cycle represents the number of times a node can output energy per unit time, while the energy density represents the amount of energy per unit volume or unit area. The relationship between the energy output cycle and the energy density was considered and adjusted by exponential calculation. This calculation uses a negative exponent to determine the ratio of node energy power to node runtime. Energy power represents the amount of energy consumed by a node per unit time, while node runtime represents the node's operating time. The calculation considers the relationship between energy power and runtime, adjusting it through a negative exponentiation. The formula comprehensively considers parameters such as node energy capacity, energy loss, energy supply frequency, operating efficiency, energy utilization efficiency, and actual node load. By performing mathematical operations and transformations on these factors, the final node energy performance value is obtained. This allows for the evaluation and comparison of the energy performance of different nodes, thereby optimizing energy utilization and management.

[0120] In this embodiment, reference Figure 4 The above is a detailed implementation flowchart of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0121] Step S31: Perform load fluctuation analysis on real-time operating data to generate load fluctuation data;

[0122] Step S32: Perform load time series analysis on the real-time running data to generate load time series data;

[0123] Step S33: Fit the load fluctuation data to a fluctuation curve based on the load time series data to generate a load fluctuation curve;

[0124] Step S34: Predict the energy load trend of the load fluctuation curve using node energy performance data, and generate node load trend data;

[0125] Step S35: Perform load balancing analysis on the energy node matrix using node load trend data to generate load balancing data;

[0126] Step S36: Perform node load analysis on the energy node matrix based on load balancing data to generate node load values.

[0127] This invention utilizes load fluctuation analysis to understand the load fluctuations at different nodes in a system. Generating load fluctuation data helps identify patterns and trends in load fluctuations, which is crucial for planning and managing energy systems. It reveals which nodes frequently experience load fluctuations, allowing for measures to stabilize energy distribution. Load time-series data provides time-series information about the load, enabling in-depth understanding of load changes over time. This is extremely useful for identifying seasonal, periodic, or random load variations, helping to better understand the dynamic characteristics of system operation. By fitting fluctuation curves, trends and patterns of load fluctuations can be summarized. This helps create models to predict future load fluctuations, leading to better planning of energy supply and demand. Combining node energy performance data with load fluctuation curves allows for the prediction of future load trends. This is crucial for planning energy supply and avoiding energy shortages or surpluses. Energy distribution can be adjusted based on load trend data to meet future demand. Load balancing analysis helps optimize load distribution across different nodes in the system. Generating load balancing data allows identification of nodes that may experience load imbalances, enabling measures to balance the load and improve system reliability and efficiency. Node load analysis provides a detailed understanding of the load level of each node. This helps determine which nodes are likely under significant load and which still have available capacity. This information can be used for decision-making, such as reallocating load or increasing energy resources to meet demand.

[0128] In this embodiment, appropriate analytical tools and algorithms are used to analyze real-time load data to identify the fluctuation characteristics of the load, such as peaks and troughs, periodicity, etc. This can encompass methods such as statistical analysis and time series analysis, associating the characteristic data of load fluctuations with timestamps to generate load fluctuation data. Time series analysis methods are used to analyze the time series characteristics of the load data, including periodicity, trends, seasonality, etc. The time series analysis results are associated with timestamps to generate load time series data. Mathematical models or fitting algorithms are used to fit the load fluctuation data into an appropriate fluctuation curve. This can be a sine curve, a polynomial curve, or other applicable curve types. The fitted fluctuation curve is associated with timestamps to generate a load fluctuation curve. The load fluctuation curve is correlated with node energy performance data to ensure that energy performance data is correlated with load fluctuations. The node energy performance data is used to analyze the future trend of the load fluctuation curve. This can include predicting peak and trough loads, energy demand fluctuations, etc., associating node load trend data with an energy node matrix to perform load balancing analysis, and using node load trend data to analyze the load balance between various energy nodes. Identify which nodes are likely to be overloaded and which may have surplus capacity. Associate the load balancing analysis results with the corresponding nodes to generate load balancing data. Map this load balancing data to the energy node matrix to ensure the load balancing status of each node is reflected in the analysis. Use the load balancing data to calculate the load value for each node. This may involve measures such as load redistribution and energy supply adjustments. Associate the calculated node load values ​​with the corresponding nodes to generate node load data.

[0129] In this embodiment, step S4 includes the following steps:

[0130] Step S41: Classify the energy node matrix by node performance level based on node energy performance data, and generate node performance levels, including high-performance nodes, medium-performance nodes and low-performance nodes.

[0131] Step S42: Divide the energy node matrix into energy levels according to the node performance level to obtain the node energy hierarchy; among them, medium performance nodes are the first level energy level, high performance nodes are the second level energy level, and low performance nodes are the third level energy level.

[0132] Step S43: Construct a distributed multi-level structure for the energy node matrix through the node energy hierarchy, and construct a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure and a third-level energy hierarchy structure.

[0133] Step S44: Calculate the energy supply capacity of the distributed multi-level energy hierarchy based on energy demand data, and generate an energy supply capacity value;

[0134] Step S45: Perform energy scheduling priority analysis on node load values ​​based on energy supply capacity values ​​to generate node scheduling priority data.

[0135] This invention classifies nodes by performance level, identifying which nodes excel in energy performance, which have average performance, and which have poor performance. This helps determine the strengths and weaknesses of the system, leading to better resource allocation and performance management. Medium-performance nodes are at the first energy level, high-performance nodes at the second, and low-performance nodes at the third. In energy scheduling, medium-performance nodes are used first because high-performance nodes have high energy utilization but high operating costs and energy consumption, while low-performance nodes have very low energy utilization. Therefore, medium-performance nodes, representing the first energy level, are used to power the load devices. When medium-performance nodes are low on energy, high-performance nodes are then used for energy supply (second energy level). Finally, when high-performance nodes are low on energy, low-performance nodes are used, maximizing energy utilization and environmental friendliness. Dividing nodes into different energy levels allows for a hierarchical energy system structure. This helps manage nodes with different performance levels more effectively, allocating resources to appropriate levels and improving the overall efficiency and reliability of the system. The construction of a distributed, multi-level energy hierarchy allows for the establishment of a hierarchical, decentralized energy system. This structure is more flexible and can better adapt to the performance and needs of different energy nodes. It also provides more control options to accommodate the operation and management of different levels. By calculating energy supply capacity, the capacity of each energy level can be quantified to meet the system's energy demands. This helps determine which level requires more energy resources to ensure that the needs of the nodes are met while avoiding resource waste. Energy scheduling priority analysis helps determine which nodes should be prioritized when supplying energy to ensure efficient energy supply. This helps reduce energy waste, ensures a match between energy supply and demand, and improves the system's operational efficiency.

[0136] In this embodiment, appropriate algorithms or rules are used to classify nodes into different performance levels, such as high performance, medium performance, and low performance. This can be based on performance index thresholds, historical data, or other relevant information to associate each node's performance level with its node ID, generating node performance level data, and mapping each performance level to its corresponding energy level. For example, a medium-performance node can be defined as a first-level energy level, a high-performance node as a second-level energy level, and a low-performance node as a third-level energy level. The defined node energy level information is associated with the node performance level data to generate node energy level data. This node energy level data is then associated with an energy node matrix to ensure that each node is associated with its corresponding energy level. Based on the node's energy level information, a distributed multi-level energy hierarchy structure is constructed. This may involve grouping nodes into different levels, defining the relationships between levels, etc., and associating the constructed multi-level energy hierarchy structure with the corresponding nodes to generate distributed multi-level energy hierarchy structure data. Using energy demand data and node performance information, the energy supply capacity of each energy level is calculated. This can include energy generation capacity, storage capacity, etc. The calculated energy supply capacity value is correlated with the corresponding energy level to generate energy supply capacity data. This energy supply capacity data is then correlated with node load values ​​to ensure that node load demand is related to the energy supply capacity data. Using the energy supply capacity data, it is determined which nodes need priority access to energy supply to meet their load demands. This can be based on analysis of factors such as energy level and load size, and the scheduling priority analysis results are correlated with the corresponding nodes to generate node scheduling priority data to guide energy allocation and scheduling.

[0137] In this embodiment, step S45 includes the following steps:

[0138] Step S451: Based on the energy supply capacity value, determine the supply and demand matching of the node load value. When the energy supply capacity value is greater than or equal to the node load value, mark it as a low priority node for scheduling.

[0139] Step S452: Based on the energy supply capacity value, determine the supply and demand matching of the node load value. When the energy supply capacity value is less than the node load value, mark it as a high-priority node for scheduling.

[0140] Step S453: Perform energy scheduling priority analysis on low-priority and high-priority nodes to generate node scheduling priority data.

[0141] This invention categorizes nodes into two classes: low-priority nodes and high-priority nodes, based on whether their energy supply capacity is sufficient to meet load demands. Nodes that can meet the demands are marked as low-priority because they do not require urgent energy dispatch. This helps avoid unnecessary dispatching and resource waste. Nodes are marked as high-priority because their energy supply capacity is insufficient to meet their load demands. These nodes require more urgent energy dispatch to ensure their operation is not interrupted. This helps focus resources and efforts on meeting the most important needs. By analyzing high- and low-priority nodes, it provides guidance for energy dispatching. It helps decision-makers identify which nodes require more urgent energy allocation to meet their needs, and which nodes can operate with lower priority. This helps improve system efficiency and ensures that resources are allocated effectively to meet the most important energy demands.

[0142] In this embodiment, for each node, its energy supply capacity and load value are compared. If the energy supply capacity value is greater than or equal to the node's load value, the node is marked as a low-priority node. This indicates that the node's energy demand can be met, but is not urgent. For each node, its energy supply capacity and load value are compared. If the energy supply capacity value is less than the node's load value, the node is marked as a high-priority node. This indicates that the node's energy demand cannot be fully met and needs to be prioritized. The nodes already marked as low-priority and high-priority are associated with the energy supply capacity data and node load data to determine how to allocate limited energy resources to meet their load demands. This may include increasing energy supply, optimizing energy allocation strategies, etc., to determine how to allocate remaining energy resources to maximize the satisfaction of their load demands while ensuring that the demands of high-priority nodes are met. The results of the priority analysis are associated with the corresponding nodes to generate node scheduling priority data. This data can be used to guide actual energy scheduling operations, ensuring that the energy demands of high-priority nodes are met while making full use of available energy resources.

[0143] In this embodiment, step S5 includes the following steps:

[0144] Step S51: Map the scheduling priority of the distributed multi-level energy hierarchy according to the node scheduling priority data to generate a node scheduling priority graph;

[0145] Step S52: Perform dynamic energy scheduling on the node scheduling priority graph according to the distributed multi-level energy hierarchy to generate dynamic energy scheduling data;

[0146] Step S53: Perform dynamic optimization and allocation analysis on the distributed multi-level energy hierarchy using dynamic energy dispatch data to construct an energy optimization strategy.

[0147] This invention maps different energy nodes to a distributed multi-level energy hierarchy using node scheduling priority data. This helps establish a node scheduling priority graph, where energy nodes are arranged according to their priority. In this way, energy system managers can clearly understand which energy nodes should have higher priority in energy allocation and which nodes can have lower priority. Dynamic energy scheduling combines actual energy allocation with the node scheduling priority graph. This helps allocate energy in actual operation, ensuring that high-priority nodes are prioritized, thereby reducing the potential risk of energy shortages. The generated dynamic energy scheduling data records the actual energy allocation of each node, providing a data foundation for subsequent analysis. Using dynamic energy scheduling data, the distributed multi-level energy hierarchy can be analyzed and optimized in real time. This helps identify potential bottlenecks, inefficient areas, and areas that may need improvement in the system. Based on the analysis results, energy optimization strategies can be constructed to adjust energy allocation, improve system efficiency, reduce energy waste, and cope with fluctuations in energy demand.

[0148] In this embodiment, a node scheduling priority graph is constructed based on the relationships and priority data between nodes. This graph displays the dependencies and priorities between nodes, obtains data on the distributed multi-level energy hierarchy, including energy supply and load demand data for each level of energy node, and selects an appropriate scheduling algorithm, such as load balancing, priority scheduling, or shortest path algorithms. Energy resources are dynamically allocated based on system requirements and the relationships between nodes, as well as node priorities and energy supply and demand. High-priority nodes may receive more resources, while low-priority nodes may be restricted. Energy supply is continuously monitored and adjusted according to demand. This may require a real-time data and feedback control system to record the actual scheduling status of each node, including the amount of energy allocated and the time. This data will be used for subsequent analysis and optimization. The system performance under dynamic energy scheduling is evaluated, including energy utilization, response time, and system reliability, ensuring that the needs of high-priority nodes are met and low-priority nodes receive adequate resources. Based on the performance evaluation results and demand satisfaction, the scheduling strategy is adjusted to meet system objectives. For situations of insufficient or unbalanced performance, resource allocation is optimized, which may require reallocating energy resources or optimizing node positions. The constructed energy optimization strategy is implemented to ensure the system operates according to the strategy.

[0149] In this embodiment, the dynamic energy scheduling in step S52 specifically involves:

[0150] When a high-performance node is marked as a high-priority scheduling node, the energy scheduling of the first-level energy hierarchy is performed using the second-level energy hierarchy.

[0151] When a high-performance node is marked as a high-priority scheduling node, energy scheduling is performed on the second-level energy hierarchy using the three-level source hierarchy.

[0152] This invention enables optimized energy scheduling in the primary energy hierarchy by marking medium-performance nodes as high-priority scheduling nodes. This means the energy system will tend to allocate more energy resources to medium-performance nodes to ensure their efficient operation. This helps improve the overall system performance, especially for tasks or nodes with high performance requirements, allowing for more timely and sufficient fulfillment of their energy needs. Marking high-performance nodes as high-priority scheduling nodes allows for more granular scheduling in the secondary energy hierarchy. High-performance nodes are typically more sensitive to energy demands, thus scheduling at this level can be more flexible and detailed. Through optimized energy scheduling of high-performance nodes, the system can better adapt to applications with stringent performance requirements, improving the overall system efficiency and responsiveness.

[0153] In this embodiment, it determines which nodes are marked as medium-performance nodes in the primary energy hierarchy and require high-priority scheduling. It acquires data from the primary and secondary energy hierarchies, including node energy supply, load demand, and priority information. Based on the priority of the medium-performance nodes, it designs an energy scheduling strategy. This may include reallocating energy, reordering tasks, and adjusting node operating states. According to the generated strategy, it executes energy scheduling operations. This may include allocating more energy to medium-performance nodes to ensure their performance and demands are met, continuously monitoring the performance and energy supply of medium-performance nodes, and making necessary adjustments based on actual conditions. This can be a real-time feedback control system. It also determines which nodes are marked as high-performance nodes in the secondary energy hierarchy and require high-priority scheduling. It acquires data from the secondary and tertiary energy hierarchies, including node energy supply, load demand, and priority information. Based on the priority of the high-performance nodes, it designs an energy scheduling strategy. This may include reallocating energy, reordering tasks, and adjusting node operating states. According to the generated strategy, it executes energy scheduling operations. This may include allocating more energy to high-performance nodes to ensure their performance and demands are met, continuously monitoring the performance and energy supply of high-performance nodes, and making necessary adjustments based on actual conditions. This could be a real-time feedback control system.

[0154] In this embodiment, step S6 includes the following steps:

[0155] Step S61: Visualize the energy optimization strategy to generate an energy optimization visualization view;

[0156] Step S62: Use a recurrent convolutional network to perform convolutional preprocessing on the energy optimization visualization view to generate a convolutional sample set;

[0157] Step S63: Perform superpixel convolution data segmentation on the convolution sample set to generate convolution feature sequences;

[0158] Step S64: Perform dilated convolution on the convolutional feature sequence to generate a convolutional feature network;

[0159] Step S65: Use a multi-scale sampling algorithm to perform pooling multi-layer sampling on the convolutional feature network to generate a convolutional feature map;

[0160] Step S66: Perform data mining modeling on the convolutional feature map to construct an energy scheduling optimization model.

[0161] This invention visualizes energy optimization strategies, enabling the system to more clearly understand and analyze existing strategies. This helps decision-makers and engineers better understand the system's energy usage, identify potential problems and optimization opportunities, and provide input data for subsequent deep learning processing. Convolutional preprocessing helps extract features from image data, transforming the visualization into a computer-processable form. This improves data representation and provides better input data for subsequent steps. Generating convolutional sample sets is for use in deep learning models for further analysis and learning. Superpixel convolutional data segmentation divides images into smaller regions, helping the model better understand the features of different regions. This enhances the model's perceptual capabilities, enabling it to better capture local features in the energy system. Generating convolutional feature sequences prepares the data for subsequent processing. Dilated convolution is a convolutional neural network technique used to increase the receptive field of convolutional layers to better capture long-range dependencies in the data. This improves the model's understanding of energy system data and its feature extraction capabilities. Generating convolutional feature networks builds more complex feature representations for subsequent processing. Multi-scale pooling reduces data dimensionality and size without losing important information. This helps improve the computational efficiency of the model and better capture features at different scales. Generating convolutional feature maps is to obtain high-dimensional feature representations for subsequent modeling. Deep learning models use convolutional feature maps for data mining and modeling to build energy dispatch optimization models. This means the model can learn the complex patterns and characteristics of energy systems to provide more effective dispatch strategies. The final model can then make predictions and optimization decisions based on the data to achieve optimized operation of the energy system.

[0162] In this embodiment, relevant data on energy optimization strategies are collected, including energy supply, load demand, node information, optimization parameters, etc. Data visualization tools or libraries are used to visualize the strategy data into graphs or charts for better understanding and analysis of the strategy. Based on visualization requirements, a visualization view of energy optimization is created. This can include time series plots, heatmaps, scatter plots, etc., to better present the data. Data for preparing the visualization view can be converted into a format suitable for deep learning, such as images, using a Convolutional Neural Network (CNN) for data preprocessing. CNNs can be used for image feature extraction and transformation. This step aims to extract useful features for subsequent processing. After CNN preprocessing, a convolutional sample set is generated, containing features extracted from the visualization view. These samples can be used to train a deep learning model. The convolutional sample set is then divided into superpixel segments, dividing the image into small blocks, each called a superpixel. This helps reduce the dimensionality and complexity of the data. Convolutional operations are applied to each superpixel to further extract features. This can be a traditional convolution operation or the use of more complex deep learning models to combine the results of convolution operations into a convolutional feature sequence, which is a series of feature vectors or feature maps for subsequent processing. Dilated convolution is used to process this convolutional feature sequence. Dilated convolution increases the receptive field, helping to capture a wider range of information. The feature sequences processed by dilated convolution are combined into a convolutional feature network. This network contains richer information and can be used for more advanced data processing. Multi-scale sampling algorithms are used to process the convolutional feature network to capture information at different scales. This can include pooling operations or using different convolutional kernel sizes. After multi-scale sampling, convolutional feature maps are generated, containing feature information at different scales. Data mining and machine learning techniques are used to model these convolutional feature maps. This can include tasks such as classification, regression, and clustering, chosen based on the nature of the problem. Based on data mining techniques, an energy scheduling optimization model is built. This model predicts the optimal energy scheduling strategy based on the information in the convolutional feature maps. The model is trained, and its performance is evaluated using evaluation metrics. Adjustments and improvements are made based on the model's performance.

[0163] In this embodiment, a comprehensive energy system operation optimization system is provided, comprising:

[0164] The node matrix module is used to monitor the operation of the integrated energy system and obtain real-time operation data; monitor the location data of energy equipment and obtain energy equipment location data; and map the energy equipment location data to energy nodes to construct an energy node matrix.

[0165] The energy performance module is used to perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; and to perform energy performance calculations on the real-time operating data based on the energy demand data to generate node energy performance data.

[0166] The load trend prediction module is used to predict the energy load trend of real-time operating data based on node energy performance data, and generate node load trend data; and to perform node load analysis on the energy node matrix based on the node load trend data, and generate node load values.

[0167] The scheduling priority module is used to construct a distributed multi-level structure of the energy node matrix based on node energy performance data, and to build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; and to perform energy scheduling priority analysis on node load values ​​based on energy demand data to generate node scheduling priority data.

[0168] The dynamic optimization module is used to perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; and to perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct energy optimization strategies.

[0169] The scheduling optimization model module is used to visualize energy optimization strategies and generate an energy optimization visualization view. It uses a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to construct an energy scheduling optimization model.

[0170] This invention generates real-time node energy performance data by performing energy demand analysis and energy performance calculations on an energy node matrix. This helps to deeply understand the system's energy needs and provides foundational data for subsequent optimization. Load trend prediction is performed using the node energy performance data to generate node load trend data. This helps the system predict future energy load conditions, prepare in advance, and optimize energy allocation and usage. The node load values ​​generated from node load analysis are important inputs for optimization. A distributed multi-level energy hierarchy is constructed using the node energy performance data, and energy scheduling priority analysis is performed based on energy demand data to generate node scheduling priority data. This helps to establish a hierarchical structure for the system, improving the flexibility and efficiency of energy scheduling. Dynamic energy scheduling decision analysis is performed based on the node scheduling priority data to generate dynamic energy scheduling data. Through dynamic optimization allocation analysis, an energy optimization strategy is constructed. This enables the system to dynamically adjust according to real-time demand, improving overall energy utilization efficiency. The energy optimization strategy is visualized, generating an energy optimization visualization view. A recurrent convolutional network is applied to dilated convolutions on the visualization view to construct an energy scheduling optimization model. This helps to more deeply understand and analyze the optimization strategy, improving the model's performance and accuracy.

[0171] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0172] 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 merely 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. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0173] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily 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 invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for optimizing the operation of a comprehensive energy system, characterized in that, Includes the following steps: Step S1: Perform operational monitoring on the integrated energy system and obtain real-time operational data; monitor the location data of the energy equipment and obtain the location data of the energy equipment; Energy node mapping is performed on the location data of energy equipment to construct an energy node matrix; Step S2: Perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; Energy performance is calculated based on real-time operating data according to energy demand data to generate node energy performance data; Step S3: Predict the energy load trend of real-time operating data using node energy performance data to generate node load trend data; Node load analysis is performed on the energy node matrix using node load trend data to generate node load values; The specific steps of step S3 are as follows: Step S31: Perform load fluctuation analysis on real-time operating data to generate load fluctuation data; Step S32: Perform load time series analysis on the real-time running data to generate load time series data; Step S33: Fit the load fluctuation data to a fluctuation curve based on the load time series data to generate a load fluctuation curve; Step S34: Predict the energy load trend of the load fluctuation curve using node energy performance data, and generate node load trend data; Step S35: Perform load balancing analysis on the energy node matrix using node load trend data to generate load balancing data; Step S36: Perform node load analysis on the energy node matrix based on load balancing data to generate node load values; Step S4: Based on the node energy performance data, construct a distributed multi-level structure for the energy node matrix, and build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; perform energy scheduling priority analysis on the node load values ​​according to the energy demand data, and generate node scheduling priority data. The specific steps of step S4 are as follows: Step S41: Classify the energy node matrix by node performance level based on node energy performance data, and generate node performance levels, including high-performance nodes, medium-performance nodes and low-performance nodes. Step S42: Divide the energy node matrix into energy levels according to the node performance level to obtain the node energy hierarchy; among them, medium performance nodes are the first level energy level, high performance nodes are the second level energy level, and low performance nodes are the third level energy level. Step S43: Construct a distributed multi-level structure for the energy node matrix through the node energy hierarchy, and construct a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure and a third-level energy hierarchy structure. Step S44: Calculate the energy supply capacity of the distributed multi-level energy hierarchy based on energy demand data, and generate an energy supply capacity value; Step S45: Perform energy scheduling priority analysis on node load values ​​based on energy supply capacity values ​​to generate node scheduling priority data; Step S5: Perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct an energy optimization strategy. The specific steps of step S5 are as follows: Step S51: Map the scheduling priority of the distributed multi-level energy hierarchy according to the node scheduling priority data to generate a node scheduling priority graph; Step S52: Perform dynamic energy scheduling on the node scheduling priority graph according to the distributed multi-level energy hierarchy to generate dynamic energy scheduling data; Step S53: Perform dynamic optimization and allocation analysis on the distributed multi-level energy hierarchy using dynamic energy dispatch data to construct an energy optimization strategy; Step S6: Visualize the energy optimization strategy to generate an energy optimization visualization view; use a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to build an energy dispatch optimization model; The specific steps of step S6 are as follows: Step S61: Visualize the energy optimization strategy to generate an energy optimization visualization view; Step S62: Use a recurrent convolutional network to perform convolutional preprocessing on the energy optimization visualization view to generate a convolutional sample set; Step S63: Perform superpixel convolution data segmentation on the convolution sample set to generate convolution feature sequences; Step S64: Perform dilated convolution on the convolutional feature sequence to generate a convolutional feature network; Step S65: Use a multi-scale sampling algorithm to perform pooling multi-layer sampling on the convolutional feature network to generate a convolutional feature map; Step S66: Perform data mining modeling on the convolutional feature map to construct an energy scheduling optimization model.

2. The method according to claim 1, characterized in that, The specific steps of step S1 are as follows: Step S11: Perform operational monitoring on the integrated energy system and obtain real-time operational data; Step S12: Monitor the location data of the energy equipment and obtain the location data of the energy equipment; Step S13: Perform spatial topology analysis on the energy equipment to generate spatial topology data; Step S14: Use the location data of energy equipment to map energy nodes to the spatial topology data and construct an energy node matrix.

3. The method according to claim 1, characterized in that, The specific steps of step S2 are as follows: Step S21: Calculate energy consumption based on real-time operating data and generate node energy consumption parameters; Step S22: Perform energy efficiency analysis on real-time operating data based on node energy consumption parameters to generate node energy efficiency data; Step S23: Perform energy demand analysis on the energy node matrix based on the node energy efficiency data to generate energy demand data; Step S24: Perform demand response analysis on real-time operating data based on energy demand data to generate energy demand response data; Step S25: Calculate the energy performance of the real-time operating data based on the energy demand response data using the node energy performance calculation formula to generate node energy performance data; The specific formula for calculating node energy performance in step S25 is as follows: ； in, The node energy performance value, For node energy capacity, This represents the node's energy loss value. For node energy supply frequency, For node operating efficiency, For energy efficiency, This represents the actual load value of the node. For the node energy output cycle, For node energy density, This represents the number of load devices at this node. For node energy power, This refers to the node's runtime.

4. The method according to claim 1, characterized in that, The specific steps of step S45 are as follows: Step S451: Based on the energy supply capacity value, determine the supply and demand matching of the node load value. When the energy supply capacity value is greater than or equal to the node load value, mark it as a low priority node for scheduling. Step S452: Based on the energy supply capacity value, determine the supply and demand matching of the node load value. When the energy supply capacity value is less than the node load value, mark it as a high-priority node for scheduling. Step S453: Perform energy scheduling priority analysis on low-priority and high-priority nodes to generate node scheduling priority data.

5. The method according to claim 1, characterized in that, The dynamic energy dispatching in step S52 specifically involves: When a high-performance node is marked as a high-priority scheduling node, the energy scheduling of the first-level energy hierarchy is performed using the second-level energy hierarchy. When a high-performance node is marked as a high-priority scheduling node, energy scheduling is performed on the second-level energy hierarchy using the three-level source hierarchy.

6. A comprehensive energy system operation optimization system, characterized in that, The method for optimizing the operation of an integrated energy system as described in claim 1 includes: The node matrix module is used to monitor the operation of the integrated energy system and obtain real-time operation data; monitor the location data of energy equipment and obtain energy equipment location data; and map the energy equipment location data to energy nodes to construct an energy node matrix. The energy performance module is used to perform energy demand analysis on the energy node matrix based on real-time operating data to generate energy demand data; and to perform energy performance calculations on the real-time operating data based on the energy demand data to generate node energy performance data. The load trend prediction module is used to predict the energy load trend of real-time operating data based on node energy performance data, and generate node load trend data; and to perform node load analysis on the energy node matrix based on the node load trend data, and generate node load values. The scheduling priority module is used to construct a distributed multi-level structure of the energy node matrix based on node energy performance data, and to build a distributed multi-level energy hierarchy structure, which includes a first-level energy hierarchy structure, a second-level energy hierarchy structure, and a third-level energy hierarchy structure; and to perform energy scheduling priority analysis on node load values ​​based on energy demand data to generate node scheduling priority data. The dynamic optimization module is used to perform dynamic energy scheduling decision analysis on the distributed multi-level energy hierarchy based on node scheduling priority data to generate dynamic energy scheduling data; and to perform dynamic optimization allocation analysis on the distributed multi-level energy hierarchy using dynamic energy scheduling data to construct energy optimization strategies. The scheduling optimization model module is used to visualize energy optimization strategies and generate an energy optimization visualization view. It uses a recurrent convolutional network to perform dilated convolution on the energy optimization visualization view to construct an energy scheduling optimization model.

Images