A smart park digital energy consumption management and control method and system based on edge computing

Abstract

This invention provides a smart park digital energy consumption management method and system integrating edge computing. Edge computing nodes are deployed at various energy-consuming terminals within the park to collect multi-dimensional terminal energy consumption data in real time, performing local cleaning, feature extraction, and initial anomaly screening. Key data is then uploaded to a cloud-based management platform via a hierarchical transmission network built through the Internet of Things (IoT). The cloud platform, based on a digital twin energy consumption model and machine learning algorithms, identifies high-energy-consuming processes and abnormal energy consumption patterns, generating personalized energy-saving management strategies adapted to equipment characteristics and park operating patterns. These strategies are then distributed to the corresponding edge computing nodes, which drive energy-saving execution modules to adjust the operating status of energy-consuming equipment in real time. This invention enables real-time edge processing of energy consumption data and global optimization collaboration in the cloud, significantly reducing data transmission latency and bandwidth pressure, improving energy consumption management response speed and energy-saving optimization effects, and contributing to the green and low-carbon development of smart parks.

Description

Technical Field

[0001] This invention relates to the fields of edge computing, Internet of Things and digital energy intersection technology, and in particular to a smart park digital energy consumption management method and system that integrates edge computing. Background Technology

[0002] With the rapid advancement of smart park construction, the types and numbers of energy-consuming devices within the parks are constantly increasing, significantly enhancing the complexity and difficulty of energy consumption management. Traditional energy consumption management systems mostly adopt a centralized cloud processing architecture, requiring all energy consumption data to be uploaded to the cloud for analysis and processing. This results in problems such as high data transmission latency, high bandwidth pressure, and untimely management response, making it difficult to meet the energy-saving control scenarios with high real-time requirements.

[0003] Meanwhile, existing energy-saving management strategies are mostly based on fixed thresholds or general experience, lacking personalized adaptation to the energy consumption characteristics of different areas and equipment within the park. They also cannot be dynamically adjusted according to changes in the park's operating status and environment, resulting in poor energy-saving effects and potentially disrupting normal production and office operations. Furthermore, existing systems rely heavily on manual inspections or post-event data analysis to detect abnormal energy consumption events, making early warning and rapid response difficult and prone to energy waste and equipment malfunctions. Therefore, how to achieve efficient processing of energy consumption data, improve management response speed, and enhance energy-saving optimization effects has become a pressing issue in the field of smart park energy consumption management. Summary of the Invention

[0004] Based on this, the present invention provides a smart park digital energy consumption management method and system that integrates edge computing. Through the architecture of edge computing and cloud collaboration, it realizes local real-time processing of energy consumption data and global optimization in the cloud, solving the problems of high transmission latency, slow response and poor energy saving effect of traditional systems.

[0005] In a first aspect, the present invention provides a smart park digital energy consumption management method integrating edge computing, comprising the following steps:

[0006] Edge computing nodes are deployed at each energy-consuming terminal in the park to collect multi-dimensional energy consumption data of each energy-consuming terminal in real time, and data preprocessing and local anomaly detection are completed at the edge.

[0007] By building a graded energy consumption transmission network in the park through the Internet of Things, key energy consumption data that has been preprocessed at the edge and local anomaly detection results are uploaded to the cloud management and control platform.

[0008] The cloud-based management and control platform trains and updates the energy consumption analysis model based on a pre-built digital twin energy consumption model of the park and historical energy consumption datasets, and identifies high-energy-consuming links and abnormal energy consumption patterns in the park.

[0009] Based on the identification results and combined with the park's operation plan and environmental parameters, personalized energy-saving management strategies are generated to suit different energy-consuming equipment and areas.

[0010] The energy-saving management and control strategy is distributed to the corresponding edge computing nodes, which then drive the energy-saving execution module to adjust the operating status of energy-consuming equipment in real time and report the execution effect to the cloud management and control platform.

[0011] This invention reduces invalid data transmission at the source, lowers cloud computing load and network bandwidth pressure, and enables rapid local response to instantaneous abnormal energy consumption events. Through the synergy of cloud-based global optimization and edge real-time execution, it solves the problems of high transmission latency and slow control response in traditional centralized systems. Based on personalized strategies generated by dynamic data analysis, it overcomes the limitations of fixed threshold control and significantly improves the overall energy consumption efficiency and intelligent control level of the park.

[0012] As a further improvement to the technical solution of this invention, data preprocessing and local anomaly detection are performed at the edge, specifically including:

[0013] The collected raw energy consumption data is processed by filling missing values, filtering noise, and normalizing data.

[0014] Extract the time-domain and frequency-domain features of energy consumption data, including energy consumption per unit time, energy consumption fluctuation rate, and equipment operating time percentage;

[0015] Based on a lightweight isolated forest algorithm deployed at the edge, local anomaly detection is performed on the preprocessed energy consumption data, instantaneous abnormal energy consumption events are marked and local alarms are generated.

[0016] Data cleaning and feature extraction can be performed at the edge, reducing the amount of invalid data uploaded by more than 70%. Local anomaly detection can generate alarms within 100 milliseconds and perform emergency shutdown actions within 200 milliseconds, effectively avoiding energy waste and equipment damage caused by sudden anomalies such as equipment short circuits and pipeline leaks, and improving the safety and reliability of system operation.

[0017] As a further improvement to the technical solution of this invention, the construction of a park energy consumption hierarchical transmission network through the Internet of Things specifically includes:

[0018] A hybrid networking approach combining LoRaWAN and NB-IoT is used to construct the underlying sensing network, enabling wide-coverage, low-power energy consumption data collection.

[0019] Based on the requirements of data importance and real-time performance, energy consumption data is divided into three levels: Level 1 data consists of real-time control commands and emergency alarms; Level 2 data consists of hourly energy consumption data of critical equipment; and Level 3 data consists of daily energy consumption statistics of non-critical equipment.

[0020] Differentiated transmission strategies are adopted for different levels of data: Level 1 data is transmitted first through the 5G private network, Level 2 data is transmitted periodically through the MQTT protocol, and Level 3 data is stored locally on the edge node and then uploaded in batches.

[0021] This invention enables wide-coverage, low-power energy consumption data acquisition, ensuring that the end-to-end latency of emergency alarms and control commands does not exceed 10 milliseconds, and the transmission reliability reaches 99.999%. At the same time, it significantly optimizes network resource utilization, reduces data transmission costs in the campus, and avoids the impact of network congestion on critical services.

[0022] As a further improvement to the technical solution of this invention, the cloud-based management and control platform pre-constructs a digital twin energy consumption model for the park, specifically including:

[0023] Based on the building information model and energy-consuming equipment ledger of the park, a three-dimensional virtual mapping model including building space, equipment topology and energy pipelines is constructed.

[0024] Real-time energy consumption data uploaded by edge nodes is synchronized with environmental parameters and equipment operating status data to the digital twin model to achieve real-time visualization mapping of the energy consumption status of the physical park.

[0025] By simulating energy consumption trends under different energy use scenarios using digital twin models, a simulation verification environment is provided for generating energy-saving strategies.

[0026] This invention enables a global visualization mapping of the energy consumption status of the park, allowing managers to intuitively grasp the energy consumption of each area and device. By simulating and verifying energy-saving strategies through a digital twin model, the energy-saving effect of the strategies and their impact on the normal operation of the park can be evaluated in advance, avoiding production and office disruptions caused by improper strategy implementation.

[0027] As a further improvement to the technical solution of this invention, the energy consumption analysis model is trained and updated to identify high-energy-consuming links and abnormal energy consumption patterns in the park, specifically including:

[0028] Historical energy consumption data, environmental data, and equipment operation data are extracted from a cloud-based time-series database to construct a training dataset.

[0029] A gradient boosting tree algorithm is used to train an energy consumption prediction model to predict baseline energy consumption values ​​for different time periods and regions.

[0030] By comparing real-time energy consumption data with benchmark energy consumption values, high-energy-consuming links with energy consumption deviations exceeding preset thresholds are identified.

[0031] By analyzing historical energy consumption data using clustering algorithms, abnormal energy consumption patterns can be identified, including equipment running under no-load conditions, excessive cooling / heating, and continuous energy consumption during non-working hours.

[0032] The present invention has an average absolute error of no more than 5% in energy consumption prediction and can accurately identify high energy consumption links with an energy consumption deviation of more than 20%. Through cluster analysis, it can automatically discover hidden abnormal energy consumption patterns such as equipment running under no-load and excessive cooling and heating. The dynamic update mechanism of the model ensures that it can continuously adapt to changes in the energy consumption characteristics of the park and reduce misjudgments and omissions.

[0033] As a further improvement to the technical solution of this invention, generating personalized energy-saving management strategies adapted to different energy-consuming devices and regions specifically includes:

[0034] Based on the identification results of high-energy-consuming links and abnormal energy consumption patterns, the priority and target equipment for energy-saving management are determined;

[0035] By combining the park's operation plan, personnel distribution data, and weather forecast data, energy-saving management strategies are generated based on time periods and regions.

[0036] Differentiated control parameters are developed for different types of energy-consuming equipment, including air conditioning temperature setpoints, lighting brightness levels, and power equipment operating power and start / stop times.

[0037] This invention enables precise adaptation of energy-saving strategies, balancing energy-saving effects with user comfort; it can adjust strategies in real time according to dynamic changes in the park's operating status, avoiding the inconvenience of one-size-fits-all management; and the control parameters designed for different equipment characteristics can maximize the energy-saving potential of various equipment and improve the overall energy-saving rate.

[0038] As a further improvement to the technical solution of this invention, the real-time adjustment of the operating status of energy-consuming equipment by the energy-saving execution module driven by the edge computing node specifically includes:

[0039] Edge computing nodes receive energy-saving management policies from the cloud and parse them into control commands for the corresponding devices;

[0040] Control commands are sent to energy-saving execution modules, including smart switches, frequency converters, and temperature controllers, via industrial communication protocols.

[0041] It monitors changes in the operating status of equipment in real time, verifies the execution effect of control commands, and generates local alarms and sends them to the cloud if execution fails.

[0042] The total time for strategy parsing and command issuance in this invention is no more than 150 milliseconds, which greatly improves the control response speed; the execution effect verification mechanism ensures that control commands can be executed accurately, avoiding situations where devices do not respond after commands are issued; timely feedback on execution failures facilitates rapid handling by maintenance personnel and ensures the stable operation of the system.

[0043] As a further improvement to the technical solution of the present invention, it also includes:

[0044] The cloud-based management platform continuously optimizes energy consumption analysis models and energy-saving management strategies based on execution performance data fed back from edge nodes.

[0045] Regularly generate park energy consumption analysis reports, displaying total energy consumption, energy-saving effects, ranking of high-energy-consuming equipment, and statistics on abnormal energy consumption events;

[0046] Users can manually adjust energy-saving control parameters through a visual interface, achieving a combination of manual intervention and intelligent control.

[0047] This invention forms a continuously iterative closed-loop optimization mechanism, which enables the system's energy-saving effect to continuously improve over time; the standardized energy consumption analysis report provides park managers with comprehensive and accurate decision-making basis; the manual intervention function enables the system to flexibly adapt to the energy needs of various special scenarios, thereby improving the system's applicability.

[0048] As a further improvement to the technical solution of this invention, the multi-dimensional energy consumption data includes power consumption, electricity consumption, water consumption, gas consumption, equipment operating current, voltage, temperature, and humidity. This invention achieves comprehensive monitoring of various energy consumptions in the park, avoiding the limitations of single-energy monitoring; the collection of equipment operation and environmental parameters can provide richer contextual information for energy consumption analysis, improving the accuracy of anomaly identification and energy-saving strategy generation.

[0049] Secondly, the present invention provides a smart park digital energy consumption management and control system integrating edge computing, comprising:

[0050] Edge computing nodes are deployed at various energy-consuming terminals in the park to collect multi-dimensional energy consumption data in real time, complete data preprocessing and local anomaly detection, and execute energy-saving management and control strategies issued by the cloud.

[0051] The Internet of Things (IoT) data acquisition terminal connects to various energy-consuming devices and edge computing nodes to collect device operating status data and transmit it to the edge computing nodes.

[0052] The cloud-based management and control platform is used to build a digital twin energy consumption model for the park, train and update the energy consumption analysis model, identify high-energy-consuming links and abnormal energy consumption patterns, and generate personalized energy-saving management and control strategies.

[0053] The energy-saving execution module connects to the edge computing node and is used to adjust the operating status of energy-consuming equipment according to the control commands issued by the edge computing node.

[0054] The modular architecture of this invention facilitates system deployment, expansion, and maintenance, and can be adapted to smart parks of different sizes and types. Each module has a clear function and works collaboratively, achieving an organic combination of real-time edge processing and global cloud optimization, and possessing complete functions such as real-time energy consumption monitoring, intelligent control, energy-saving optimization, and data visualization.

[0055] Compared with the prior art, the present invention has the following advantages:

[0056] This invention achieves local collection, preprocessing, and initial anomaly screening of energy consumption data by deploying edge computing nodes at various energy-consuming terminals within the park. This significantly reduces the amount of data that needs to be uploaded to the cloud, effectively reducing network bandwidth pressure and data transmission latency. Simultaneously, it enables rapid local response and emergency handling of instantaneous abnormal energy consumption events. By constructing a hierarchical IoT transmission network, differentiated transmission strategies are adopted for data with varying importance and real-time requirements. This ensures reliable real-time transmission of critical control commands and emergency alarms while further optimizing network resource utilization. Based on a pre-built digital twin energy consumption model and machine learning energy consumption analysis model for the park in the cloud, it achieves… The global visualization mapping of the park's energy consumption status and the accurate identification of high-energy-consuming links and abnormal energy consumption patterns overcome the limitations of traditional fixed threshold control strategies that cannot adapt to the energy consumption characteristics of different equipment and areas. By distributing personalized energy-saving control strategies generated in the cloud to edge computing nodes for execution, a collaborative control architecture is built, which combines global optimization decision-making in the cloud with real-time control execution on the edge. This forms a complete closed loop of energy consumption data collection, analysis, decision-making, execution, and feedback, significantly improving the response speed and execution efficiency of energy consumption control. Ultimately, this achieves refined and intelligent control of energy consumption in smart parks, effectively improving energy utilization efficiency and reducing the overall operational energy consumption of the park. Attached Figure Description

[0057] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0058] Figure 1 This is an exemplary flowchart of a smart park digital energy consumption management method integrating edge computing, as shown in some embodiments of the present invention.

[0059] Figure 2 This is a schematic diagram of a smart park digital energy consumption management and control system that integrates edge computing, as shown in some embodiments of the present invention.

[0060] Figure 3 This is a schematic diagram of the structure of a computer device for implementing a smart park digital energy consumption management method based on converged edge computing, as shown in some embodiments of the present invention. Detailed Implementation

[0061] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0062] The present invention will be further described in detail below with reference to the accompanying drawings.

[0063] refer to Figure 1 The figure is an exemplary flowchart of a smart park digital energy consumption management method integrating edge computing according to some embodiments of the present invention. The smart park digital energy consumption management method integrating edge computing mainly includes the following steps:

[0064] In step 101, edge computing nodes are deployed at each energy-consuming terminal in the park to collect multi-dimensional energy consumption data of each energy-consuming terminal in real time, and data preprocessing and local anomaly detection are completed at the edge.

[0065] In practical implementation, edge computing nodes can be industrial-grade edge gateways, deployed in power distribution boxes or equipment control cabinets in areas such as office buildings, production workshops, and public facilities within the park. Each edge computing node is responsible for managing several energy-consuming terminals within its coverage area. IoT data acquisition terminals include smart meters, smart water meters, smart gas meters, current transformers, voltage sensors, temperature and humidity sensors, etc., installed at the energy inlet and operating environment of each energy-consuming device. Edge computing nodes establish connections with IoT data acquisition terminals via industrial communication protocols such as RS485 and Modbus, and collect multi-dimensional energy consumption data from each energy-consuming terminal in real time according to a preset sampling frequency (e.g., 1 minute / time), including power consumption, electricity consumption, water consumption, gas consumption, equipment operating current, voltage, ambient temperature, and humidity. The collected raw data is first preprocessed at the edge, specifically including: filling missing values ​​using linear interpolation, removing noise from the data using moving average filtering, and mapping data of different dimensions to the [0,1] interval using min-max normalization. After preprocessing, edge computing nodes extract the time-domain and frequency-domain features of energy consumption data, such as energy consumption per unit time, energy consumption fluctuation rate, equipment runtime percentage, and peak energy consumption time. Subsequently, a lightweight isolated forest algorithm deployed on the edge side is used to perform local anomaly detection on the feature data. When an instantaneous abnormal energy consumption event is detected (such as a sudden increase in current caused by a short circuit in the equipment or a sudden increase in water consumption caused by a pipeline leak), a local alarm is immediately generated, and the energy-saving execution module is driven to take emergency shutdown measures. At the same time, the abnormal information is marked as first-level data and uploaded to the cloud with priority.

[0066] In step 102, an energy consumption classification transmission network is constructed in the park through the Internet of Things, and the key energy consumption data after edge preprocessing and the local anomaly detection results are uploaded to the cloud management and control platform.

[0067] In practical implementation, a hybrid LoRaWAN and NB-IoT network is used to construct the underlying sensing network. LoRaWAN communication is used for IoT data acquisition terminals with long distances and low power consumption requirements (such as smart streetlights and water meters in public areas), while NB-IoT communication is used for terminals with large data transmission volumes and high real-time requirements (such as power equipment sensors in production workshops). Edge computing nodes connect to the cloud management platform via a 5G private network or fiber optic cable. Based on the importance and real-time requirements of the data, energy consumption data is divided into three levels: Level 1 data consists of real-time control commands and emergency alarms; Level 2 data consists of hourly energy consumption and operating status data for critical equipment (such as central air conditioning, elevators, and large production equipment); and Level 3 data consists of daily energy consumption statistics for non-critical equipment (such as office lighting and water dispensers). Differentiated transmission strategies are adopted for different levels of data: Level 1 data is transmitted preferentially via the 5G private network using the TCP protocol to ensure millisecond-level response; Level 2 data is uploaded hourly via the MQTT protocol; and Level 3 data is stored locally on the edge computing nodes for 7 days and uploaded to the cloud in batches weekly. By employing a tiered transmission strategy, the real-time nature of critical data is ensured while significantly reducing network traffic and lowering bandwidth costs.

[0068] In step 103, the cloud-based management and control platform trains and updates the energy consumption analysis model based on the pre-built digital twin energy consumption model of the park and the historical energy consumption dataset, and identifies high-energy-consuming links and abnormal energy consumption patterns in the park.

[0069] In practical implementation, the cloud-based management platform first constructs a 3D digital twin energy consumption model based on the park's Building Information Model (BIM) and energy-consuming equipment ledger. This model includes the building's spatial structure, equipment topology, and energy pipeline routing. Real-time energy consumption data, environmental parameters, and equipment operating status data uploaded from edge nodes are synchronized to the digital twin model through a data access layer. This drives the virtual model to operate synchronously with the physical park, achieving real-time visualization of the park's energy consumption status. Users can intuitively view the real-time energy consumption of each area and device through a 3D interface. Simultaneously, the cloud extracts historical energy consumption data, meteorological data, and park operation plan data from a time-series database for more than one year to construct a training dataset. The Gradient Boosting Tree (XGBoost) algorithm is used to train an energy consumption prediction model, using time, temperature, humidity, and weekday / holiday conditions as input features to predict baseline energy consumption values ​​for different time periods and areas. The real-time collected energy consumption data is compared with the predicted baseline energy consumption values. When the actual energy consumption of a certain area or device exceeds a preset threshold (e.g., 20%) of the baseline energy consumption value, it is identified as a high-energy-consuming area. In addition, K-means clustering algorithm is used to analyze historical energy consumption data to identify typical abnormal energy consumption patterns such as equipment idling, excessive cooling / heating, and continuous energy consumption during non-working hours. The cloud-based management platform incrementally updates the energy consumption analysis model weekly using newly accumulated energy consumption data to ensure the model's accuracy and adaptability.

[0070] In step 104, based on the identification results and combined with the park's operation plan and environmental parameters, a personalized energy-saving management strategy adapted to different energy-consuming equipment and areas is generated.

[0071] In practice, the cloud-based management platform prioritizes energy-saving control based on the identification results of high-energy-consuming links and abnormal energy consumption patterns, according to the magnitude and scope of energy consumption deviations. It prioritizes high-energy-consuming links with large deviations and wide impacts. Combining park operation plans (such as get off work hours, meeting schedules, and production plans), personnel distribution data (obtained through access control systems and WiFi positioning), and weather forecast data, it generates time-based and area-based energy-saving control strategies. For example, during non-working hours, unnecessary lighting and air conditioning equipment are automatically turned off; in densely populated meeting rooms, air conditioning cooling capacity is appropriately increased; and during seasons with suitable temperatures, central air conditioning is turned off, and natural ventilation systems are activated. Differentiated control parameters are developed for different types of energy-consuming equipment: for central air conditioning, the set temperature and fan speed are dynamically adjusted based on indoor temperature and the number of people; for lighting systems, brightness is automatically adjusted based on natural light intensity; and for power equipment, operation scheduling is optimized to avoid idle operation. The generated energy-saving control strategies are first simulated and verified in a digital twin model to assess the energy-saving effect and impact on the normal operation of the park. Only after successful verification are the strategies distributed to edge computing nodes.

[0072] In step 105, the energy-saving management and control strategy is sent to the corresponding edge computing node, which drives the energy-saving execution module to adjust the operating status of the energy-consuming equipment in real time and feeds back the execution effect to the cloud management and control platform.

[0073] In practice, the cloud-based management platform distributes verified energy-saving management strategies to edge computing nodes in the corresponding areas via a 5G private network. Upon receiving the strategies, the edge computing nodes parse them into control commands for specific devices and send them to the energy-saving execution modules via industrial communication protocols such as Modbus and BACnet. These energy-saving execution modules include smart switches, frequency converters, thermostats, and electric valves, which adjust the operating status of energy-consuming equipment in real time according to the control commands, such as adjusting air conditioning temperature, controlling lighting brightness, and adjusting water pump speed. The edge computing nodes monitor changes in the equipment's operating status in real time, verifying the effectiveness of the control commands. If the equipment fails to execute the commands or exhibits an abnormal state, a local alarm is immediately generated and fed back to the cloud. Simultaneously, the edge computing nodes periodically upload the adjusted energy consumption data and operating status data to the cloud. Based on the feedback of the execution effect data, the cloud-based management platform evaluates the actual effectiveness of the energy-saving strategies and continuously optimizes the energy consumption analysis model and energy-saving management strategies, forming a closed-loop optimization mechanism.

[0074] In addition, the cloud-based management platform also features data visualization and report generation capabilities. It can display real-time information such as the overall energy consumption overview of the park, energy consumption rankings of various areas, and energy-saving effect statistics. It also regularly generates daily, weekly, monthly, and annual energy consumption analysis reports to provide decision support for park managers. Furthermore, it allows users to manually adjust energy-saving management parameters and set energy consumption modes for specific time periods through a web-based or mobile visual interface, achieving an organic combination of manual intervention and intelligent management.

[0075] refer to Figure 2 The figure is a schematic diagram of the structure of a smart park digital energy consumption management system integrating edge computing according to some embodiments of the present invention. This system includes: edge computing nodes, IoT data acquisition terminals, a cloud management platform, and an energy-saving execution module, which are described below:

[0076] Edge computing nodes are deployed at various energy-consuming terminals in the park to collect multi-dimensional energy consumption data in real time, complete data preprocessing and local anomaly detection, and execute energy-saving management and control strategies issued by the cloud.

[0077] The Internet of Things (IoT) data acquisition terminal connects to various energy-consuming devices and edge computing nodes to collect device operating status data and transmit it to the edge computing nodes.

[0078] The cloud-based management and control platform is used to build a digital twin energy consumption model for the park, train and update the energy consumption analysis model, identify high-energy-consuming links and abnormal energy consumption patterns, and generate personalized energy-saving management and control strategies.

[0079] The energy-saving execution module connects to the edge computing node and is used to adjust the operating status of energy-consuming equipment according to the control commands issued by the edge computing node.

[0080] The modules in the aforementioned smart park digital energy consumption management system integrating edge computing can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0081] In another embodiment, the present invention provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores historical data, digital twin model data, and energy-saving strategy data for smart park energy consumption management. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a smart park digital energy consumption management method that integrates edge computing.

[0082] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0083] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above embodiment of the smart park digital energy consumption management method with converged edge computing.

[0084] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps described in the embodiment of the smart park digital energy consumption management method with converged edge computing.

[0085] In one embodiment, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps described in the embodiment of the smart park digital energy consumption management method integrating edge computing.

[0086] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0087] The technical solutions provided by the embodiments disclosed in this invention have the following beneficial effects:

[0088] The present invention provides a smart park digital energy consumption management method and system integrating edge computing. First, edge computing nodes are deployed at each energy-consuming terminal in the park to achieve local collection, preprocessing, and initial screening of energy consumption data, significantly reducing the amount of data that needs to be uploaded to the cloud, lowering bandwidth pressure and transmission latency, while enabling rapid local response to instantaneous abnormal energy consumption events. Second, a hierarchical transmission network is constructed through the Internet of Things (IoT), employing differentiated transmission strategies for data of varying importance to ensure the real-time performance and reliability of critical data. Third, the cloud management platform, based on a digital twin energy consumption model and machine learning algorithms, achieves global analysis and optimization of park energy consumption, accurately identifying high-energy-consuming links and abnormal energy consumption patterns, generating personalized and dynamic energy-saving management strategies, overcoming the limitations of traditional fixed threshold strategies. Finally, the energy-saving management strategies are distributed to edge computing nodes for execution, achieving synergy between cloud-based global optimization and edge real-time control, improving management response speed and execution efficiency. In summary, the solution of the present invention effectively solves the problems of high transmission latency, slow response, and poor energy-saving effect in traditional energy consumption management systems, achieving precise management of digital energy consumption in smart parks, improving energy utilization efficiency, and reducing overall park energy consumption.

[0089] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A smart park digital energy consumption management method integrating edge computing, characterized in that, Includes the following steps: Edge computing nodes are deployed at each energy-consuming terminal in the park to collect multi-dimensional energy consumption data of each energy-consuming terminal in real time, and data preprocessing and local anomaly detection are completed at the edge. By building a graded energy consumption transmission network in the park through the Internet of Things, key energy consumption data that has been preprocessed at the edge and local anomaly detection results are uploaded to the cloud management and control platform. The cloud-based management and control platform trains and updates the energy consumption analysis model based on a pre-built digital twin energy consumption model of the park and historical energy consumption datasets, and identifies high-energy-consuming links and abnormal energy consumption patterns in the park. Based on the identification results and combined with the park's operation plan and environmental parameters, energy-saving management strategies adapted to different energy-consuming equipment and areas are generated. The energy-saving management and control strategy is distributed to the corresponding edge computing nodes, which then drive the energy-saving execution module to adjust the operating status of energy-consuming equipment in real time and report the execution effect to the cloud management and control platform.

2. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, Performing data preprocessing and local anomaly detection at the edge specifically includes: The collected raw energy consumption data is processed by filling missing values, filtering noise, and normalizing data. Extract the time-domain and frequency-domain features of energy consumption data, including energy consumption per unit time, energy consumption fluctuation rate, and equipment operating time percentage; Based on a lightweight isolated forest algorithm deployed at the edge, local anomaly detection is performed on the preprocessed energy consumption data, instantaneous abnormal energy consumption events are marked and local alarms are generated.

3. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, Building a graded energy consumption transmission network for the park through the Internet of Things specifically includes: A hybrid networking approach combining LoRaWAN and NB-IoT is used to construct the underlying sensing network, enabling wide-coverage, low-power energy consumption data collection. Based on the requirements of data importance and real-time performance, energy consumption data is divided into three levels: Level 1 data consists of real-time control commands and emergency alarms; Level 2 data consists of hourly energy consumption data of critical equipment; and Level 3 data consists of daily energy consumption statistics of non-critical equipment. Differentiated transmission strategies are adopted for different levels of data: Level 1 data is transmitted first through the 5G private network, Level 2 data is transmitted periodically through the MQTT protocol, and Level 3 data is stored locally on the edge node and then uploaded in batches.

4. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, The cloud-based management platform pre-builds a digital twin energy consumption model for the park, specifically including: Based on the building information model and energy-consuming equipment ledger of the park, a three-dimensional virtual mapping model including building space, equipment topology and energy pipelines is constructed. Real-time energy consumption data uploaded by edge nodes is synchronized with environmental parameters and equipment operating status data to the digital twin model to achieve real-time visualization mapping of the energy consumption status of the physical park. By simulating energy consumption trends under different energy use scenarios using digital twin models, a simulation verification environment is provided for generating energy-saving strategies.

5. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, Training and updating the energy consumption analysis model to identify high-energy-consuming links and abnormal energy use patterns in the park specifically includes: Historical energy consumption data, environmental data, and equipment operation data are extracted from a cloud-based time-series database to construct a training dataset. A gradient boosting tree algorithm is used to train an energy consumption prediction model to predict baseline energy consumption values ​​for different time periods and regions. By comparing real-time energy consumption data with benchmark energy consumption values, high-energy-consuming links with energy consumption deviations exceeding preset thresholds are identified. By analyzing historical energy consumption data using clustering algorithms, abnormal energy consumption patterns can be identified, including equipment running under no-load conditions, excessive cooling / heating, and continuous energy consumption during non-working hours.

6. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, The specific steps for generating energy-saving management strategies adapted to different energy-consuming devices and regions include: Based on the identification results of high-energy-consuming links and abnormal energy consumption patterns, the priority and target equipment for energy-saving management are determined; By combining the park's operation plan, personnel distribution data, and weather forecast data, energy-saving management strategies are generated based on time periods and regions. Differentiated control parameters are developed for different types of energy-consuming equipment, including air conditioning temperature setpoints, lighting brightness levels, and power equipment operating power and start / stop times.

7. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, The real-time adjustment of the operating status of energy-consuming equipment by the energy-saving execution module driven by the edge computing node specifically includes: Edge computing nodes receive energy-saving management policies from the cloud and parse them into control commands for the corresponding devices; Control commands are sent to energy-saving execution modules, including smart switches, frequency converters, and temperature controllers, via industrial communication protocols. It monitors changes in the operating status of equipment in real time, verifies the execution effect of control commands, and generates local alarms and sends them to the cloud if execution fails.

8. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, Also includes: The cloud-based management platform continuously optimizes energy consumption analysis models and energy-saving management strategies based on execution performance data fed back from edge nodes. Regularly generate park energy consumption analysis reports, displaying total energy consumption, energy-saving effects, ranking of high-energy-consuming equipment, and statistics on abnormal energy consumption events; Users can manually adjust energy-saving control parameters through a visual interface, achieving a combination of manual intervention and intelligent control.

9. The smart park digital energy consumption management method integrating edge computing as described in claim 1, characterized in that, The multi-dimensional energy consumption data includes power consumption, electricity consumption, water consumption, gas consumption, equipment operating current, voltage, temperature, and humidity.

10. A smart park digital energy consumption management and control system integrating edge computing, characterized in that, include: Edge computing nodes are deployed at various energy-consuming terminals in the park to collect multi-dimensional energy consumption data in real time, complete data preprocessing and local anomaly detection, and execute energy-saving management and control strategies issued by the cloud. The Internet of Things (IoT) data acquisition terminal connects to various energy-consuming devices and edge computing nodes to collect device operating status data and transmit it to the edge computing nodes. The cloud-based management and control platform is used to build a digital twin energy consumption model for the park, train and update the energy consumption analysis model, identify high-energy-consuming links and abnormal energy use patterns, and generate energy-saving management and control strategies. The energy-saving execution module connects to the edge computing node and is used to adjust the operating status of energy-consuming equipment according to the control commands issued by the edge computing node.

Images