Energy management three-dimensional visualization method and system based on digital twin and Internet of Things

Abstract

The invention discloses an energy management three-dimensional visualization method and system based on digital twin and Internet of Things, and relates to the technical field of energy management visualization, and the method comprises the steps: obtaining multi-source heterogeneous energy data of an energy management object; constructing a virtual mirror image model corresponding to the physical energy system based on the multi-source heterogeneous energy data and the digital twin model; generating a three-dimensional visual scene based on the virtual mirror image model so as to map the geographic position distribution of the physical energy system, and presenting the real-time energy consumption state, the energy flow transmission path and the environmental parameter change of the equipment; receiving a user interaction instruction, carrying out interaction operation on the target area or equipment, calling the associated multi-source heterogeneous energy data, and carrying out superposition display on the associated multi-source heterogeneous energy data; energy consumption abnormity early warning information or an equipment regulation and control strategy is generated in combination with the energy management optimization rule, and the equipment regulation and control strategy is input into the physical energy system to be executed. The invention provides an energy management method capable of realizing multi-source data fusion and accurate mapping of a physical system.

Description

Technical Field

[0001] The present application relates to the field of energy management visualization technology, and in particular to a three-dimensional visualization method and system for energy management based on digital twins and the Internet of Things. Background Art

[0002] Currently, energy management primarily relies on decentralized monitoring devices and two-dimensional tables or simple graphical interfaces to display data. Due to heterogeneous sources and inconsistent formats, various data types (such as real-time energy consumption, equipment status, environmental parameters, and historical statistics) are difficult to integrate and analyze. Furthermore, two-dimensional visualization interfaces can only display equipment status through static charts or simple topological diagrams, failing to intuitively reflect the state of the physical energy system or energy flow. This makes it difficult for operations and maintenance personnel to quickly locate energy consumption anomalies or the root cause of equipment failures, hindering the efficient operation of energy systems.

[0003] Therefore, there is an urgent need for an energy management method that can achieve multi-source data fusion and accurate mapping of physical systems to solve the above technical problems. Summary of the Invention

[0004] In order to address the shortcomings of the existing technology and provide an energy management method that can realize multi-source data fusion and accurate mapping of physical systems, this application provides a three-dimensional visualization method and system for energy management based on digital twins and the Internet of Things.

[0005] In the first aspect, the invention objectives of this application are achieved by adopting the following technical solutions: The 3D visualization method for energy management based on digital twins and the Internet of Things includes: Acquire multi-source heterogeneous energy data of energy management objects, including real-time energy consumption data, device status data, environmental parameter data, and historical energy consumption statistics collected by IoT devices; Building a virtual mirror model of the corresponding physical energy system based on the multi-source heterogeneous energy data and the digital twin model; Generate a three-dimensional visualization scene based on the virtual mirror model, mapping the geographical distribution of the physical energy system through a spatial coordinate system, and presenting the real-time energy consumption status of the equipment, energy flow transmission path, and environmental parameter changes through dynamic rendering; receiving user interaction instructions, performing interactive operations on a target area or device in the three-dimensional visualization scene, retrieving associated multi-source heterogeneous energy data, and displaying them in an overlay; In the three-dimensional visualization scene, energy consumption abnormality warning information or equipment control strategy is generated in combination with preset energy management optimization rules, and the equipment control strategy is input into the physical energy system for execution.

[0006] By adopting the above technical solutions, the digital twin model includes the topological relationship of equipment, the law of energy flow and the parameters related to the environment; the interactive operations of the three-dimensional visualization scene include focusing, rotating and zooming operations. The three-dimensional visualization of energy management based on digital twins and the Internet of Things in this application has significantly improved the intelligence and refinement of energy management through the collaborative design of multi-source heterogeneous data fusion, digital twin model construction and three-dimensional visualization interaction. Through the efficient integration and real-time mapping of multi-source data, the intuitive interactivity, intelligent early warning and dynamic regulation capabilities of three-dimensional visualization have improved the scientificity and reliability of energy management. Specifically, by integrating the real-time energy consumption, equipment status, environmental parameters and historical statistical data collected by Internet of Things devices, the analysis lag problem caused by data dispersion and format heterogeneity in traditional energy management is solved. The virtual mirror model constructed based on the digital twin model realizes the real-time synchronous mapping of the physical energy system and the virtual space. The three-dimensional visualization scene uses spatial coordinate systems and dynamic rendering technology to convert abstract energy consumption data, energy flow paths and environmental parameters into perceptible spatial information (such as heat maps and particle flow effects), and combines equipment labels and multi-view switching functions to greatly reduce the understanding cost of operation and maintenance personnel; through user interaction, multi-source data is superimposed and displayed, and energy consumption abnormality warning information is automatically generated based on preset optimization rules, solving the problem of delayed response of traditional manual inspections or simple threshold alarms; further, the digital twin model is used to simulate the implementation effect of the control strategy, realize the pre-verification and optimization of the strategy, and avoid the impact of blind adjustments on system stability.

[0007] In a preferred example of the present application, the acquisition of multi-source heterogeneous data of energy management objects includes: Collect real-time energy consumption data, equipment status data, and environmental parameter data of each node device in the physical energy system through the Internet of Things sensor network; Retrieving historical energy consumption statistics from the energy management system database, the historical energy consumption statistics including the total energy consumption over a specified period, the year-on-year change rate of equipment energy consumption, and energy consumption baseline values ​​under typical operating conditions; Data preprocessing is performed on the real-time energy consumption data, equipment status data, environmental parameter data and historical energy consumption statistics to generate a standardized multi-source heterogeneous data set.

[0008] By adopting the above technical solutions, real-time multi-source heterogeneous data can be obtained based on the Internet of Things, and data quality can be improved through data preprocessing such as data standardization to support high-precision digital twin models.

[0009] In a preferred example of the present application, the virtual mirror model of the corresponding physical energy system is constructed based on the multi-source heterogeneous energy data and the digital twin model, including: Constructing an initial three-dimensional geometric model of the physical energy system based on a building information model or a geographic information system, wherein the initial three-dimensional geometric model includes equipment spatial location, pipeline direction, and building structure parameters; Inputting standardized multi-source heterogeneous data sets into the digital twin platform and driving the optimization and update of the initial 3D geometric model, synchronously mapping the morphological changes caused by the real-time load of the equipment, the energy flow transmission rate and the influence of environmental parameters; An information association rule base for the physical energy system is established, wherein the information association rule base includes correlation coefficients between equipment energy consumption and environmental parameters, and functional relationships between energy transmission loss and environmental conditions, and is used to correct the dynamic simulation accuracy of the virtual mirror model.

[0010] By adopting the above technical solutions, a high-precision virtual mirror model is constructed, and the device status and environmental changes are updated in real time through digital twin technology to improve the model simulation accuracy.

[0011] In a preferred example of the present application, in the three-dimensional visualization scene, generating energy consumption abnormality warning information or equipment control strategy in combination with preset energy management optimization rules includes: Anomaly detection is performed on the real-time energy consumption data in the three-dimensional visualization scene using a machine learning algorithm. When the energy consumption data of a certain area or device exceeds a preset threshold, an early warning instruction is triggered and the location is marked in the three-dimensional visualization scene; Analyze the causes of abnormal energy consumption by combining equipment topology and environmental parameter data, and generate a diagnostic report that includes fault component location, impact range assessment, and priority ranking; Based on the preset energy management optimization rules, candidate solutions are obtained from the energy management strategy library. The implementation effect information of each candidate solution is simulated through the digital twin model, and the optimal equipment control strategy is selected and output to the physical energy system for execution.

[0012] By adopting the above technical solutions, energy consumption anomalies can be automatically identified to implement anomaly detection. By combining device topology and environmental data, the source of the fault can be located and a diagnostic report including the impact range and priority can be generated.

[0013] In a preferred example of the present application, the preset energy management optimization rules include: Obtaining a physical energy system and an energy management strategy, and determining a first energy demand forecast value and a second energy demand forecast value for different time periods based on the energy system information and the energy management strategy; generating an energy scheduling comparison table for adjusting energy allocation based on the energy management strategy, the first energy demand forecast value, and the second energy demand forecast value; Obtaining an energy usage change reference range representing an energy usage change threshold, and generating an energy management control model based on the energy usage change reference range and the energy scheduling comparison table; First actual energy consumption data is obtained, and the first actual energy consumption data is input into the energy management control model to optimize energy distribution.

[0014] By adopting the above technical solutions, refined energy allocation can be achieved based on time-based demand forecasts to adapt to the needs of different scenarios. By combining energy buffer zones and risk levels to generate scheduling priorities, the flexibility and risk tolerance of energy allocation can be improved.

[0015] In a preferred example of the present application, the obtaining of the physical energy system and the energy management strategy, and determining the first energy demand forecast value and the second energy demand forecast value for different time periods based on the energy system information and the energy management strategy, include: Obtaining system information and energy management strategies for the physical energy system, including energy device type, energy device power, device operating status, energy storage capacity, and user usage habits. The energy management strategies include power restriction priority rules during peak hours, energy storage charging strategies during off-peak hours, and backup energy switching rules during emergency periods. Determining energy usage patterns at different time periods during the day based on the user's usage habits, the power of the energy device, and the operating status of the device; Predicting a first energy demand forecast value within a future short-term period based on the energy usage pattern, the equipment effective power, and the short-term rules in the energy management strategy; The second energy demand forecast value in the future medium to long term is predicted by combining the energy storage capacity, the energy equipment type, the energy usage pattern and the external environmental data.

[0016] By adopting the above technical solutions, the real-time energy consumption fluctuations during the day (such as equipment start-up and shutdown, changes in user behavior) are captured based on short-term forecasts (first energy demand forecast value), and minute-level energy allocation response is achieved; the medium- and long-term forecasts (second energy demand forecast value) are combined with external environmental data (such as weather, production plans) and equipment life cycles to plan energy reserves and scheduling for the next few days in advance, avoid resource waste, and help improve the dynamic adaptability of energy management optimization rules.

[0017] In a preferred example of the present application, generating an energy scheduling comparison table for adjusting energy allocation based on the energy management strategy, the first energy demand forecast value, and the second energy demand forecast value further includes: Obtaining an energy buffer zone according to the energy storage capacity, the energy device power, and the energy usage change reference range; Obtaining an energy shortage risk level according to the energy buffer period and the adjusted energy demand value; generating an emergency energy dispatch priority according to the energy shortage risk level and the backup energy switching rule during the emergency period; The energy dispatch comparison table is updated based on the energy priority allocation level and the emergency energy dispatch priority.

[0018] By adopting the above technical solution, the energy buffer zone is determined based on the energy storage capacity, equipment power and the reference range of energy usage changes, so as to identify potential energy supply risks in advance, so that preventive measures can be taken and the efficiency of emergency response in emergency situations can be improved.

[0019] In the second aspect, the invention objective of this application is achieved by adopting the following technical solutions: Energy management 3D visualization system based on digital twin and IoT, including: Data acquisition module, used to obtain multi-source heterogeneous energy data of energy management objects; A virtual modeling module, configured to construct a virtual mirror model of the corresponding physical energy system based on the multi-source heterogeneous energy data and the digital twin model; A three-dimensional visualization platform for generating a three-dimensional visualization scene based on the virtual mirror model. The three-dimensional visualization scene maps the geographical distribution of the physical energy system through a spatial coordinate system and presents the real-time energy consumption status of the equipment, the energy flow transmission path, and the changes in environmental parameters through dynamic rendering; The three-dimensional visualization platform is further configured to receive user interaction instructions, perform interactive operations on target areas or devices in the three-dimensional visualization scene, and retrieve associated multi-source heterogeneous energy data for overlay display on the visualization interface; The strategy analysis and feedback module is used to generate energy consumption abnormality warning information or equipment control strategy in the three-dimensional visualization scene in combination with preset energy management optimization rules, and output the equipment control strategy to the physical energy system for execution.

[0020] In a third aspect, the invention objective of this application is achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned three-dimensional visualization method for energy management based on digital twins and the Internet of Things.

[0021] Fourthly, the invention objectives of this application are achieved by adopting the following technical solutions: A computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned three-dimensional visualization method for energy management based on digital twins and the Internet of Things.

[0022] In summary, this application includes at least one of the following beneficial technical effects: 1. This paper provides a three-dimensional visualization method for energy management that can perform multi-dimensional visualization, real-time interaction, and intelligent early warning and regulation. By synchronizing the real-time data of the digital twin model with the physical system, a closed-loop feedback mechanism is formed to improve the execution accuracy of the energy management strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a three-dimensional visualization method for energy management based on digital twins and the Internet of Things in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below with reference to the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, this application discloses a three-dimensional visualization method for energy management based on digital twins and the Internet of Things, which specifically includes the following steps: S1: Acquire multi-source heterogeneous energy data of energy management objects. Multi-source heterogeneous energy data includes real-time energy consumption data, device status data, environmental parameter data, and historical energy consumption statistics collected by IoT devices.

[0026] In this embodiment, real-time energy consumption data collected by IoT devices refers to instantaneous energy consumption parameters such as power, current, and voltage collected in real time by sensors deployed on energy equipment (such as motors, air conditioners, and lighting systems). Device status data is a binary or hierarchical identifier (such as normal / faulty / standby) reflecting the device's operating status. For example, a PLC controller receives the device's start / stop signals. If the motor current suddenly drops to zero and persists for more than 5 seconds, it is considered a "faulty" state. Environmental parameter data refers to external environmental indicators that affect energy consumption (such as temperature, humidity, and light intensity). Temperature and humidity sensors are deployed throughout the factory to monitor these environmental parameters in real time. Weather stations are installed outdoors to obtain real-time temperature and wind speed data. Historical energy consumption statistics are aggregated energy consumption data for a device or system over a period of time, such as average daily and monthly electricity consumption, and peak load.

[0027] Specifically, step S1 includes: S11: Collect real-time energy consumption data, equipment status data and environmental parameter data of each node device in the physical energy system through the Internet of Things sensor network.

[0028] In this embodiment, the IoT sensor network is a network composed of sensing nodes deployed in energy devices and environments, supporting data collection, transmission and communication.

[0029] Specifically, real-time energy consumption data is collected at a high frequency (e.g., every 1 minute), device status data is collected in an event-driven manner, that is, collection is triggered every time the device status changes, and environmental parameter data is collected in a fixed short time, such as every ten minutes.

[0030] S12: Retrieve historical energy consumption statistics from the database of the energy management system. The historical energy consumption statistics include the total energy consumption during a specified period of time, the year-on-year change rate of equipment energy consumption, and the energy consumption baseline value under typical operating conditions.

[0031] In this embodiment, historical energy consumption statistics are past energy consumption records extracted from an energy management system (EMS) or enterprise resource planning (ERP) system, which are used to analyze energy consumption patterns; the total energy consumption in a specified time period, such as the total factory electricity consumption in 2023 is 12 million kWh; the year-on-year change rate of equipment energy consumption, such as the percentage increase in air conditioning energy consumption in August 2023 compared to August 2022; the energy consumption benchmark value under typical working conditions, such as the theoretical energy consumption value of the equipment when operating at full load, can be determined through the equipment manual or experiments.

[0032] S13: Perform data preprocessing on real-time energy consumption data, equipment status data, environmental parameter data and historical energy consumption statistics to generate a standardized multi-source heterogeneous data set.

[0033] In this embodiment, data preprocessing includes missing value processing, data cleaning operations for outlier filtering, data alignment operations, and normalization standard processing. Data alignment is to unify the timestamp format (such as UTC time) and align multi-source data at a 1-minute granularity (such as synchronizing current, voltage, and power data to the same time axis).

[0034] S2: Build a virtual mirror model of the corresponding physical energy system based on multi-source heterogeneous energy data and digital twin models.

[0035] In this example, the digital twin model uses Unity3D's NavMeshAgent component to simulate the movement of equipment, such as automated guided vehicle (AGV) logistics vehicles. The Collider component detects collisions, such as a pipeline leak triggering a red alert. The digital twin model also includes model optimization rules based on equipment load thresholds. For example, when real-time power exceeds 80% of rated power, model nodes are highlighted.

[0036] Specifically, step S2 includes: S21: Construct an initial three-dimensional geometric model of the physical energy system based on a building information model or geographic information system. The initial three-dimensional geometric model includes the spatial location of equipment, pipeline direction, and building structure parameters.

[0037] In this embodiment, the Building Information Model (BIM) is a digital model based on the entire building lifecycle, encompassing both geometric and non-geometric information such as the building structure, equipment layout, and pipeline routing. Revit software is used to import CAD drawings of factory buildings and construct a 3D model that includes equipment coordinates, 3D pipeline routing, and wall material parameters. The installation locations and spatial dimensions of key equipment (such as transformers and pumps) are marked in the 3D model. A Geographic Information System (GIS) is a modeling tool based on geospatial data, suitable for layout modeling of outdoor energy systems (such as wind farms and transmission lines). The GPS coordinates of physical energy system equipment and topographic data of transmission line corridors are overlaid on the GIS platform to construct an energy system model that incorporates geographic environmental characteristics.

[0038] S22: Input standardized multi-source heterogeneous data sets into the digital twin platform and drive the optimization and update of the initial 3D geometric model, synchronously mapping the morphological changes caused by the real-time load of the equipment, the energy flow transmission rate and the influence of environmental parameters.

[0039] In this embodiment, the digital twin platform is used as a middleware to connect the physical energy system and the virtual model, supporting real-time data access, dynamic model rendering and simulation analysis.

[0040] Specifically, Unity3D is used as the digital twin platform, and standardized data sets are received through the API interface. For example, when the sensor detects that the temperature of a motor has risen, the platform automatically calls the corresponding node of the device in the model and changes its surface color (such as a red warning).

[0041] Specifically, for different types of multi-source heterogeneous datasets, corresponding data change thresholds are associated. The detected multi-source heterogeneous data is then compared in real time with the corresponding data change thresholds. When a particular multi-source heterogeneous data set exceeds the data change threshold, the initial 3D geometric model is driven to optimize and update the latest energy heterogeneous data. Dynamic mapping includes real-time load mapping, energy flow transmission mapping, and environmental parameter mapping. Real-time load mapping uses a physics engine to simulate morphological changes such as device speed and vibration based on real-time energy consumption data (such as motor power fluctuations). Each type of real-time energy consumption data is associated with a corresponding morphological change threshold based on the device identifier to facilitate morphological change monitoring. For example, when the motor load increases, the tachometer pointer in the model dynamically deflects, and the transmission belt tension is visually enhanced.

[0042] Energy flow transmission mapping is based on the law of conservation of energy and simulates the transmission of energy such as electricity and heat; path and loss; for example, in the pipeline model, the red fluid represents the high-temperature medium, and the flow rate is positively correlated with the real-time flow data.

[0043] Environmental parameter mapping is to bind environmental data such as temperature, humidity, and light to the sensor nodes in the model. Each sensor node is associated with an environmental parameter change threshold. When the change of a certain environmental parameter exceeds the corresponding environmental parameter change threshold, the mapping of the environmental parameter in the initial three-dimensional geometric model is adjusted in real time to achieve dynamic adjustment of visual effects such as light intensity and shadow distribution.

[0044] S23: Establish an information association rule base for the physical energy system. The information association rule base includes the correlation coefficient between equipment energy consumption and environmental parameters, and the functional relationship between energy transmission loss and environmental conditions, which is used to correct the dynamic simulation accuracy of the virtual mirror model.

[0045] Specifically, the information association rule base refers to defining the quantitative relationship between equipment energy consumption, environmental parameters and energy transmission efficiency through mathematical models or empirical formulas, which is used to correct model simulation errors.

[0046] For example, the air conditioning energy consumption formula is: real-time energy consumption of the air conditioning system = temperature sensitivity coefficient × outdoor temperature + 200. The temperature sensitivity coefficient is usually 0.5, and 200 is the baseline energy consumption, which is the baseline energy consumption when the outdoor temperature is 0°C, including the no-load power consumption of the air conditioning compressor or the basic power consumption of the control system.

[0047] The formula for power transmission loss is: Energy loss during power transmission = 0.01 × physical length of the power line × (1 + temperature correction factor × (ambient temperature - 25)). The temperature correction factor is usually 0.002, which means that the loss increases by 0.2% for every 1°C increase in temperature.

[0048] S3: Generate a three-dimensional visualization scene based on the virtual mirror model. The three-dimensional visualization scene maps the geographical distribution of the physical energy system through a spatial coordinate system, and presents the real-time energy consumption status of the equipment, energy flow transmission path and environmental parameter changes through dynamic rendering.

[0049] In this embodiment, the spatial coordinate system refers to aligning the geographical location of the physical energy system with the coordinate axes of the three-dimensional model to ensure the geographical consistency of the visualization scene; dynamic rendering is a visual representation of real-time updates of device status, energy flow paths, and environmental parameters through a graphics engine. Dynamic rendering can use the Unity3D engine to develop a visualization interface. The highlight color of the device changes with the real-time power (green for power changes ≤50%, yellow for power changes 50%-80%, and red for power changes ≥80%). Particle special effects can also be used to simulate the energy flow path, and the depth of color indicates the transmission rate (red for high load, blue for low load).

[0050] Specifically, a three-dimensional rendering engine (such as Unity3D and Unreal Engine) is used to render the virtual mirror model in real time, and the energy consumption density of the equipment is mapped into a heat map through the color gradient method (red indicates high energy consumption, blue indicates low energy consumption), and the energy transmission path is presented through particle flow special effects (particle density reflects the transmission rate); the equipment label information is superimposed in the three-dimensional visualization scene, and the label information includes the equipment name, model, rated power, current load rate and the time of the most recent maintenance; it supports multi-view switching function, and multiple views include global bird's-eye view, local close-up view and cross-sectional view; the global bird's-eye view is used to display the overall energy consumption distribution, the local close-up view can focus on the energy consumption details of key equipment, and the cross-sectional view shows the energy flow status in hidden pipelines.

[0051] S4: Receive user interaction instructions, perform interactive operations on the target area or equipment in the three-dimensional visualization scene, retrieve the associated multi-source heterogeneous energy data and overlay them for display.

[0052] In this embodiment, interactive instructions input by the user are received through the three-dimensional visualization platform, where the three-dimensional visualization platform supports users to operate the three-dimensional scene through a mouse, touch screen or VR device (such as rotating, zooming, and clicking the device); the associated data retrieval actually retrieves associated multi-source heterogeneous data from the database according to the area or device selected by the user and overlays it into the three-dimensional visualization scene.

[0053] For example, after the user selects a distribution cabinet in the three-dimensional visualization scene, its input voltage waveform, load equipment list and ambient temperature and humidity trends are simultaneously displayed in the scene.

[0054] S5: In the three-dimensional visualization scene, combined with the preset energy management optimization rules, energy consumption abnormality warning information or equipment control strategy is generated, and the equipment control strategy is input into the physical energy system for execution.

[0055] In this embodiment, the energy consumption anomaly warning information detects energy consumption anomalies through a machine learning algorithm, marks the abnormal location in the scene, and uses the isolation forest algorithm to perform cluster analysis on the real-time energy consumption data. If the energy consumption of a certain type of equipment deviates from the normal cluster center by more than 3σ, a red alarm is triggered.

[0056] Specifically, step S5 includes: S51: Anomalies are detected in the real-time energy consumption data in the three-dimensional visualization scene through machine learning algorithms. When the energy consumption data of a certain area or equipment exceeds the preset threshold, an early warning prompt instruction is triggered and the location is marked in the three-dimensional visualization scene.

[0057] In this embodiment, the machine learning algorithms include the Isolation Forest algorithm and the LSTM neural network. The Isolation Forest algorithm detects anomalies by randomly partitioning the data space (applicable to high-dimensional data). The LSTM neural network uses time series modeling to capture periodic anomalies in energy consumption, such as sudden load changes during holidays. For example, the input parameters of the Isolation Forest model include real-time energy consumption data, timestamp, and device type. The anomaly threshold is set to "anomaly probability greater than 0.8." When the model output probability exceeds the threshold, an alert is triggered.

[0058] Specifically, preset thresholds are defined based on historical statistics or industry standards, representing the upper limit of normal energy consumption. These thresholds include static and dynamic thresholds. For example, for a static threshold of 100kW, the threshold is set to ±10% (90-110kW). Dynamic thresholds are adjusted based on seasonality and production schedules, such as a 20% increase in the air conditioning threshold for summer. For example, in a 3D scene, if the air conditioning energy consumption in a workshop suddenly increases to 120kW, the model automatically locks the device, pops up a red warning box with the label "Energy Consumption Exceeded," associates the device ID with the BIM model, and redirects to the device maintenance page.

[0059] S52: Analyze the causes of abnormal energy consumption by combining the device topology relationship with environmental parameter data, and generate a diagnostic report including fault component location, impact range assessment, and priority sorting.

[0060] In this embodiment, device topology refers to the physical or logical connection between devices (e.g., upstream transformers and downstream loads in a power line). This can be obtained through device layout diagrams in CAD models, BIM models, or device interconnection configuration tables in PLC systems. Environmental parameter data refers to external conditions that affect energy consumption, such as temperature, humidity, and light intensity. Correlation analysis involves calculating the correlation between energy consumption and environmental parameters. In this embodiment, the Pearson correlation coefficient is used. Causal reasoning uses the Granger causality test to verify the direction of the impact of environmental parameters on energy consumption.

[0061] Specifically, fault component location refers to the corresponding part location information when the equipment fails. For example, through the current sensor data, it is found that the current of a motor is abnormal, and combined with the topological relationship, it is located to "Workshop 3-Production Line 2-Motor A"; the impact range assessment uses the causal reasoning engine to determine the impact range of the abnormal equipment. For example, the shutdown of Motor A will cause the production capacity of Production Line 2 to drop by 30%, affecting the order delivery cycle. Priority sorting is based on the importance of the equipment in the production process. For example, critical equipment (such as safety systems) has a "high" priority, and non-critical equipment (such as corridor lighting) has a "low" priority.

[0062] S53: Based on the preset energy management optimization rules, candidate solutions are obtained from the energy management strategy library. The implementation effect information of each candidate solution is simulated through the digital twin model, and the optimal equipment control strategy is selected and output to the physical energy system for execution.

[0063] In this embodiment, energy management optimization rules are stored in an energy management strategy library, which contains energy optimization management goals and energy constraints in different scenarios. The energy management strategy library includes in-pot prediction strategies such as load transfer, equipment startup and shutdown, and power limit.

[0064] For example, for the scenario of "Workshop 3 overloaded", the following candidate solutions are generated: Plan A: Turn off non-critical equipment (such as air conditioners in office areas); Plan B: Start the backup generator; Option C: Temporarily increase the discharge power of the energy storage system.

[0065] Specifically, the digital twin simulation involves injecting control instructions for scenarios A, B, and C into the model, simulating each scenario's impact on energy consumption, equipment load, and environmental parameters. For example, scenario A causes the office temperature to rise by 2°C. Each scenario is then scored based on a pre-set multi-objective optimization function to evaluate its effectiveness. The optimal equipment control strategy selects the scenario with the highest overall score. If multiple scenarios have similar scores, the one with the lowest risk is prioritized (for example, starting a backup generator rather than shutting down critical equipment).

[0066] Furthermore, in one embodiment, the preset energy management optimization rules include: S10: Acquire a physical energy system and an energy management strategy, and determine a first energy demand forecast value and a second energy demand forecast value for different time periods based on the energy system information and the energy management strategy.

[0067] In this embodiment, physical energy system information refers to a database containing device type, power, operating status, storage capacity, and user habits. Device types include air conditioners, motors, and lighting systems; operating statuses include normal, faulty, and standby; and user habits include keeping office air conditioning on from 9:00 AM to 11:00 AM on weekdays. Energy management strategies include pre-set load distribution rules. For example, during peak hours (6:00 PM to 10:00 PM), medical equipment is prioritized for power supply, while during off-peak hours (12:00 AM to 6:00 AM), low-cost grid electricity is used to charge energy storage batteries. The first energy demand forecast is a real-time, short-term energy consumption forecast, generated using an LSTM neural network (time series forecasting) or ARIMA model. The second energy demand forecast is a time-based energy consumption forecast for the next week or longer, generated using a Prophet time series model or linear regression.

[0068] Specifically, step S10 includes: S101: Obtain system information and energy management strategies of the physical energy system. The system information includes energy device type, energy device power, device operating status, energy storage capacity, and user usage habits. The energy management strategy includes power restriction priority rules during peak hours, energy storage charging strategies during off-peak hours, and backup energy switching rules during emergency periods.

[0069] In this embodiment, energy device types include air conditioners, motors, lighting equipment, energy storage batteries, etc. Different physical energy systems contain different types of energy devices. Energy device power refers to the power demand of the equipment during operation (such as 1.5kW / unit for air conditioners). Energy storage capacity refers to the total capacity of the energy storage battery (such as 100kWh), charging and discharging efficiency, and the current remaining power (such as 30%). User usage habits are obtained based on historical energy consumption records.

[0070] Specifically, peak-period power restrictions include prioritizing power supply to critical equipment from 18:00 to 22:00, and limiting the power of non-critical equipment to 50% of the rated value; off-peak period energy storage rules include using low-priced grid electricity from 0:00 to 6:00 to charge the energy storage battery to 80% of its capacity; and emergency standby switching rules include automatically starting the diesel generator when the grid is out of power.

[0071] S102: Determine energy usage patterns at different time periods during the day based on user usage habits, energy device power, and device operating status.

[0072] In this embodiment, user usage habits are divided into energy usage patterns based on historical energy usage data and user behavior logs using the K-means clustering algorithm. Historical energy usage data includes time-based electricity consumption, and user behavior logs include equipment manual start and stop records. User behavior habits include, for example, weekday patterns: high load from 8:00 to 17:00, with a sudden drop in load after 17:00; and weekend patterns: stable load throughout the day, with reduced frequency of air conditioning use.

[0073] Matching device status with power refers to combining real-time device status and power curves to correct the energy consumption distribution in the energy usage model. For example, if a motor stops due to a fault, its base load is adjusted from 10kW to 0kW, and the total energy consumption of the model is recalculated.

[0074] Energy usage patterns at different time periods during the day include high load on weekdays, low load on weekends, and intermittent patterns on holidays.

[0075] S103: Predicting a first energy demand forecast value in a future short-term period based on the energy usage pattern, the effective power of the equipment, and the short-term rules in the energy management strategy.

[0076] In this embodiment, the day is divided into two-hour periods. A corresponding mode is selected based on the current date type (weekday or weekend). Real-time device status data (e.g., an air conditioner is out of service due to a malfunction) is retrieved and the power values ​​of the corresponding devices in the corresponding energy usage mode are adjusted. The corresponding energy management policy rules are applied, and the effective power of all devices is summed to obtain the first short-term energy demand forecast. Device effective power = device rated power × state correction factor. Short-term policies, such as peak-hour power rationing policies and actual forecasted power reductions of non-critical devices by a specified multiple, are superimposed.

[0077] S104: Based on the energy storage capacity, energy equipment type, energy usage pattern and external environmental data, a second energy demand forecast value in the future medium to long term is predicted.

[0078] In this embodiment, the external environment data includes weather forecasts, holiday schedules, and production plan data. The equipment life cycle data includes equipment maintenance cycles and equipment retirement plans.

[0079] Specifically, the equipment power, energy storage capacity, and environmental data are aligned along the time axis and standardized. A hierarchical forecast and dynamic correction strategy are used to predict the secondary energy demand in the medium and long term: First, based on historical data and equipment usage patterns for the same period, the baseline demand in the absence of external interference is predicted. Then, the actual energy storage capacity is calculated based on the constraints of the energy storage system's charging and discharging power upper limit and the impact of the remaining power. For example, if the current energy storage has 20% remaining, the charging capacity needs to be supplemented within the predicted period.

[0080] Actual energy storage capacity = predicted base load + energy storage system charging power - energy storage system discharging power. The impact of external environmental data is analyzed separately for temperature-sensitive devices and light-sensitive devices. For example, for temperature-sensitive devices such as air conditioners, predictions are made based on the following formula: The predicted air conditioning power = predicted basic air conditioning load × (1 + 0.01 × (average temperature in the future period − 25)). The coefficient of 0.01 means that the air conditioning load increases by 1% for every 1°C increase in temperature.

[0081] For light-sensitive equipment, power generation can be adjusted based on weather forecasts, such as a 50% reduction in photovoltaic power on cloudy days. Production plans and event-driven adjustments can be pre-set based on expert knowledge and experience. For example, if a new production line is launched, daily electricity consumption will increase by 1000 kWh for the next month. If holidays are adjusted, weekend load will be based on the weekday load forecast. Secondary energy demand forecasts can be calculated using Prophet or linear regression models.

[0082] S20: Generate an energy scheduling comparison table for adjusting energy distribution based on the energy management strategy, the first energy demand prediction value, and the second energy demand prediction value.

[0083] In this embodiment, the energy scheduling comparison table is a load distribution rule table based on the energy demand forecast values ​​and energy management strategies for different time periods, which includes information such as time periods, equipment, priority, and allocation amount. The priority is divided into critical equipment and non-critical equipment according to the usage requirements of the equipment usage scenario, and the load distribution rules are divided into peak periods and valley periods according to the historical energy usage peak and valley periods for load distribution. For example, during peak periods, the power of low-priority equipment is limited to 50% of the rated value; the energy storage battery is charged to 80% of the capacity during valley periods.

[0084] Specifically, step S20 further includes: S201: Obtain an energy buffer zone based on energy storage capacity, energy device power, and energy usage change reference range.

[0085] In this embodiment, the energy buffer zone is dynamically calculated based on the following prediction formula: Maximum allowable energy consumption = remaining energy storage system capacity × energy storage system charging efficiency + target device power × time period length. Minimum allowable energy consumption = remaining energy storage system capacity × energy storage system discharge efficiency - target device power × time period length. Energy buffer zone = [minimum allowable energy consumption, maximum allowable energy consumption].

[0086] S202: Obtain an energy shortage risk level according to the energy buffer period and the adjusted energy demand value.

[0087] In this embodiment, the adjusted energy demand value is a weighted combination of the short-term forecast value (the first energy demand forecast value) and the long-term forecast value (the second energy demand forecast value). For example, the weight of the first energy demand forecast value is 0.7, and the weight of the second energy demand forecast value is 0.3. Specifically, the energy shortage risk level is a risk level divided according to the degree of deviation between the energy buffer zone and the energy demand.

[0088] For example, low risk level: demand value ≤ maximum allowable energy consumption value × 0.9; medium risk level: maximum allowable energy consumption value × 0.9 < demand value ≤ maximum allowable energy consumption value × 1.1; high risk level: demand value > maximum allowable energy consumption value × 1.1.

[0089] S203: Generate emergency energy dispatch priorities based on the energy shortage risk level and the backup energy switching rules during emergency periods.

[0090] In this embodiment, the backup energy switching rule refers to the preset emergency energy activation rule (such as starting the energy storage system first and then starting the diesel generator). For example, when the risk level is high, the energy storage system is activated first (priority 1), followed by the diesel generator (priority 2), and then the non-critical loads are cut off (priority 3).

[0091] Specifically, the emergency energy scheduling priority dynamically adjusts the equipment scheduling order based on the risk level. For example, when the risk is high, priority is given to ensuring the power supply of medical equipment (priority 1), followed by limiting the air conditioning power in the office area (priority 2); and then cutting off the landscape lighting (priority 3).

[0092] S204: Based on the energy priority allocation level and the emergency energy dispatch priority, update the energy dispatch comparison table.

[0093] In this embodiment, the energy priority allocation level refers to the scheduling priority generated according to the importance, real-time status and policy of the equipment, including key equipment, high energy consumption equipment and non-key equipment.

[0094] Specifically, the energy scheduling comparison table refers to embedding emergency situations into the scheduling comparison table and adjusting the power allocation priority of the equipment based on the emergency situations obtained in real time.

[0095] S30: Obtaining an energy usage change reference range representing an energy usage change threshold, and generating an energy management control model according to the energy usage change reference range and an energy scheduling comparison table.

[0096] In this embodiment, the energy usage variation reference range refers to the permissible fluctuation threshold for device energy consumption, such as ±10%. For example, if the device's rated power is 100 kW, the permissible fluctuation range is 90-110 kW. The energy management control model is a decision-making model for dynamic adjustment strategies, triggering regulation based on the deviation between predicted energy demand and actual energy consumption.

[0097] Specifically, the energy management control model is trained using an LSTM neural network and compares the energy scheduling comparison table, the reference range of energy usage changes, and the actual energy consumption data. If the actual value exceeds the threshold (e.g., >110kW), an alarm is triggered and the backup strategy is called. If the actual value is lower than the threshold (e.g., <90kW), redundant power is released for use by other equipment.

[0098] S40: Acquire first actual energy consumption data, and input the first actual energy consumption data into an energy management control model to optimize energy distribution.

[0099] In this embodiment, the first actual energy consumption data is the current energy consumption data collected in real time by the Internet of Things sensor. The actual energy consumption data is input into the energy management control model, and the deviation of the energy demand forecast value is calculated to determine whether it is sufficient to trigger a threshold alarm (if it exceeds ±10%, an alarm is triggered).

[0100] Specifically, if an alarm is triggered, a backup strategy is invoked (e.g., switching to a backup generator); If no alarm is triggered, the current energy allocation plan is maintained.

[0101] It should be understood that the serial numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] In one embodiment, a three-dimensional visualization system for energy management based on digital twins and the Internet of Things is provided. The three-dimensional visualization system for energy management based on digital twins and the Internet of Things corresponds to the three-dimensional visualization method for energy management based on digital twins and the Internet of Things in the above-mentioned embodiment.

[0103] The energy management 3D visualization system based on digital twins and the Internet of Things includes a data acquisition module, a virtual modeling module, a 3D visualization platform, and a strategy analysis and feedback module. The detailed description of each functional module is as follows: Data acquisition module, used to obtain multi-source heterogeneous energy data of energy management objects; A virtual modeling module is used to build a virtual mirror model of the corresponding physical energy system based on multi-source heterogeneous energy data and digital twin models; A 3D visualization platform is used to generate 3D visualization scenes based on virtual mirror models. The 3D visualization scenes map the geographical distribution of physical energy systems through a spatial coordinate system and present the real-time energy consumption status of equipment, energy flow transmission paths, and environmental parameter changes through dynamic rendering. The 3D visualization platform is also used to receive user interaction instructions, perform interactive operations on target areas or equipment in the 3D visualization scene, and retrieve associated multi-source heterogeneous energy data for overlay display on the visualization interface; The strategy analysis and feedback module is used to generate energy consumption abnormality warning information or equipment control strategy in the three-dimensional visualization scene in combination with preset energy management optimization rules, and output the equipment control strategy to the physical energy system for execution.

[0104] For the specific limitations of the three-dimensional visualization system for energy management based on digital twins and the Internet of Things, please refer to the limitations of the three-dimensional visualization method for energy management based on digital twins and the Internet of Things in the above text, which will not be repeated here; each module in the above-mentioned three-dimensional visualization system for energy management based on digital twins and the Internet of Things can be implemented in whole or in part through software, hardware and their combination; each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1: Acquire multi-source heterogeneous energy data of energy management objects. Multi-source heterogeneous energy data includes real-time energy consumption data, device status data, environmental parameter data, and historical energy consumption statistics collected by IoT devices. S2: Build a virtual mirror model of the corresponding physical energy system based on multi-source heterogeneous energy data and digital twin models; S3: Generates a 3D visualization scene based on the virtual mirror model. The 3D visualization scene maps the geographical distribution of the physical energy system through a spatial coordinate system and presents the real-time energy consumption status of the equipment, energy flow transmission path, and environmental parameter changes through dynamic rendering. S4: Receive user interaction instructions, perform interactive operations on the target area or equipment in the 3D visualization scene, retrieve the associated multi-source heterogeneous energy data and overlay them for display; S5: In the three-dimensional visualization scene, combined with the preset energy management optimization rules, energy consumption abnormality warning information or equipment control strategy is generated, and the equipment control strategy is input into the physical energy system for execution.

[0106] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0107] In one embodiment, particularly according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product comprising a computer program / instructions that, when executed by a processor, implement the steps of the described three-dimensional visualization method for energy management based on digital twins and the Internet of Things. In such an embodiment, the computer program can be downloaded and installed from a network via a communication module and / or installed from removable media. When executed by a central processing unit (CPU), the computer program performs the various functions defined in the present invention.

[0108] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0109] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A three-dimensional visualization method for energy management based on digital twins and the Internet of Things, characterized by: include: Acquire multi-source heterogeneous energy data of energy management objects, including real-time energy consumption data, device status data, environmental parameter data, and historical energy consumption statistics collected by IoT devices; Building a virtual mirror model of the corresponding physical energy system based on the multi-source heterogeneous energy data and the digital twin model; Generate a three-dimensional visualization scene based on the virtual mirror model, mapping the geographical distribution of the physical energy system through a spatial coordinate system, and presenting the real-time energy consumption status of the equipment, energy flow transmission path, and environmental parameter changes through dynamic rendering; receiving user interaction instructions, performing interactive operations on a target area or device in the three-dimensional visualization scene, retrieving associated multi-source heterogeneous energy data, and displaying them in an overlay; In the three-dimensional visualization scene, energy consumption abnormality warning information or equipment control strategy is generated in combination with preset energy management optimization rules, and the equipment control strategy is input into the physical energy system for execution.

2. The three-dimensional visualization method for energy management based on digital twins and the Internet of Things according to claim 1 is characterized in that: The acquiring of multi-source heterogeneous data of energy management objects includes: Collect real-time energy consumption data, equipment status data, and environmental parameter data of each node device in the physical energy system through the Internet of Things sensor network; Retrieving historical energy consumption statistics from the energy management system database, the historical energy consumption statistics including the total energy consumption over a specified period, the year-on-year change rate of equipment energy consumption, and energy consumption baseline values ​​under typical operating conditions; Data preprocessing is performed on the real-time energy consumption data, equipment status data, environmental parameter data and historical energy consumption statistics to generate a standardized multi-source heterogeneous data set.

3. The three-dimensional visualization method for energy management based on digital twins and the Internet of Things according to claim 1 is characterized in that: The constructing of a virtual mirror model of the corresponding physical energy system based on the multi-source heterogeneous energy data and the digital twin model includes: Constructing an initial three-dimensional geometric model of the physical energy system based on a building information model or a geographic information system, wherein the initial three-dimensional geometric model includes equipment spatial location, pipeline direction, and building structure parameters; Inputting standardized multi-source heterogeneous data sets into the digital twin platform and driving the optimization and update of the initial 3D geometric model, synchronously mapping the morphological changes caused by the real-time load of the equipment, the energy flow transmission rate and the influence of environmental parameters; An information association rule base for the physical energy system is established, wherein the information association rule base includes correlation coefficients between equipment energy consumption and environmental parameters, and functional relationships between energy transmission loss and environmental conditions, and is used to correct the dynamic simulation accuracy of the virtual mirror model.

4. The three-dimensional visualization method for energy management based on digital twins and the Internet of Things according to claim 1 is characterized in that: In the three-dimensional visualization scene, generating abnormal energy consumption warning information or equipment control strategy in combination with preset energy management optimization rules includes: Anomaly detection is performed on the real-time energy consumption data in the three-dimensional visualization scene using a machine learning algorithm. When the energy consumption data of a certain area or device exceeds a preset threshold, an early warning instruction is triggered and the location is marked in the three-dimensional visualization scene; Analyze the causes of abnormal energy consumption by combining equipment topology and environmental parameter data, and generate a diagnostic report that includes fault component location, impact range assessment, and priority ranking; Based on the preset energy management optimization rules, candidate solutions are obtained from the energy management strategy library. The implementation effect information of each candidate solution is simulated through the digital twin model, and the optimal equipment control strategy is selected and output to the physical energy system for execution.

5. The three-dimensional visualization method for energy management based on digital twins and the Internet of Things according to claim 1 or 4, characterized in that: The preset energy management optimization rules include: Obtaining a physical energy system and an energy management strategy, and determining a first energy demand forecast value and a second energy demand forecast value for different time periods based on the energy system information and the energy management strategy; generating an energy scheduling comparison table for adjusting energy allocation based on the energy management strategy, the first energy demand forecast value, and the second energy demand forecast value; Obtaining an energy usage change reference range representing an energy usage change threshold, and generating an energy management control model based on the energy usage change reference range and the energy scheduling comparison table; First actual energy consumption data is obtained, and the first actual energy consumption data is input into the energy management control model to optimize energy distribution.

6. The three-dimensional visualization method for energy management based on digital twins and the Internet of Things according to claim 5 is characterized in that: The acquiring of the physical energy system and the energy management strategy, and determining the first energy demand forecast value and the second energy demand forecast value for different time periods based on the energy system information and the energy management strategy, includes: Obtaining system information and energy management strategies for the physical energy system, including energy device type, energy device power, device operating status, energy storage capacity, and user usage habits. The energy management strategies include power restriction priority rules during peak hours, energy storage charging strategies during off-peak hours, and backup energy switching rules during emergency periods. Determining energy usage patterns at different time periods during the day based on the user's usage habits, the power of the energy device, and the operating status of the device; Predicting a first energy demand forecast value within a future short-term period based on the energy usage pattern, the equipment effective power, and the short-term rules in the energy management strategy; The second energy demand forecast value in the future medium to long term is predicted by combining the energy storage capacity, the energy equipment type, the energy usage pattern and the external environmental data.

7. The three-dimensional visualization method for energy management based on digital twins and the Internet of Things according to claim 6 is characterized in that: The step of generating an energy scheduling comparison table for adjusting energy allocation based on the energy management strategy, the first energy demand forecast value, and the second energy demand forecast value further includes: Obtaining an energy buffer zone according to the energy storage capacity, the energy device power, and the energy usage change reference range; Obtaining an energy shortage risk level according to the energy buffer period and the adjusted energy demand value; generating an emergency energy dispatch priority according to the energy shortage risk level and the backup energy switching rule during the emergency period; The energy dispatch comparison table is updated based on the energy priority allocation level and the emergency energy dispatch priority.

8. The energy management 3D visualization system based on digital twin and Internet of Things is characterized by: The system includes: Data acquisition module, used to obtain multi-source heterogeneous energy data of energy management objects; A virtual modeling module, configured to construct a virtual mirror model of the corresponding physical energy system based on the multi-source heterogeneous energy data and the digital twin model; A three-dimensional visualization platform for generating a three-dimensional visualization scene based on the virtual mirror model. The three-dimensional visualization scene maps the geographical distribution of the physical energy system through a spatial coordinate system and presents the real-time energy consumption status of the equipment, the energy flow transmission path, and the changes in environmental parameters through dynamic rendering; The three-dimensional visualization platform is further configured to receive user interaction instructions, perform interactive operations on target areas or devices in the three-dimensional visualization scene, and retrieve associated multi-source heterogeneous energy data for overlay display on the visualization interface; The strategy analysis and feedback module is used to generate energy consumption abnormality warning information or equipment control strategy in the three-dimensional visualization scene in combination with preset energy management optimization rules, and output the equipment control strategy to the physical energy system for execution.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the three-dimensional visualization method for energy management based on digital twins and the Internet of Things are implemented as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the three-dimensional visualization method for energy management based on digital twins and the Internet of Things are implemented as described in any one of claims 1 to 7.

Images