Intelligent Park Energy Consumption Management Method and Platform Based on Multi-Source Data Driving

Abstract

The present invention discloses a smart park energy consumption management method and platform based on multi-source data drive, which relates to the technical field of energy consumption management. The method includes: connecting multi-modal monitoring devices to obtain multi-source monitoring data; locating the monitoring space of the multi-source monitoring data and projecting it into the space model of the smart park to construct a multi-dimensional space database; performing spatial energy consumption analysis based on the multi-dimensional space database to evaluate the energy consumption status of each space area and identify areas with excessive spatial energy consumption; according to the multi-source monitoring data of the areas with excessive spatial energy consumption, combining with the spatial distribution characteristics to perform energy-saving analysis and obtain an energy-saving management plan. It solves the technical problems existing in the prior art, such as the simplification of multi-modal data collection, the disconnection between energy consumption and spatial information, and the lack of real-time dynamic mapping ability in static analysis, resulting in low energy utilization efficiency and insufficient accuracy of energy consumption management in the park, and achieves the technical effect of improving the accuracy of energy consumption management and energy utilization efficiency in the smart park.

Description

Technical Field

[0001] This application relates to the technical field of energy consumption management, and specifically to a smart park energy consumption management method and platform based on multi-source data drive. Background Art

[0002] As an important carrier for the digital transformation of cities, the energy consumption problem of smart parks has attracted increasing attention. The park covers multi-functional scenarios such as industry, commerce, office, and life, with complex and large-scale energy demands. The traditional extensive energy consumption management model has been difficult to meet the low-carbon, refined, and intelligent management requirements. The park has energy waste due to problems such as inefficient equipment operation, uneven energy distribution, and redundant environmental control. However, the current park energy consumption management mainly relies on single-dimensional data collection (such as electricity meter readings) and strategy formulation driven by manual experience, with significant limitations. On the one hand, the types of traditional monitoring devices are single, making it difficult to cover multi-modal parameters such as water, electricity, air (temperature, humidity, CO2 concentration), and equipment operation status, resulting in the lack of full exploration of the correlation between energy use and environmental factors and equipment efficiency. On the other hand, the energy consumption data is disconnected from the spatial location information, making it impossible to accurately locate high-energy consumption areas and their causes, restricting the pertinence of energy-saving measures. And it is difficult to respond in a timely manner to the energy consumption fluctuations in the complex scenarios of the park, affecting the precise regulation of the park's energy system.

[0003] Therefore, in the current related technologies, there are technical problems such as the simplification of multi-modal data collection, the disconnection between energy consumption and spatial information, and the lack of real-time dynamic mapping ability in static analysis, resulting in low energy utilization efficiency and insufficient accuracy of energy consumption management in the park. Summary of the Invention

[0004] This application provides a smart park energy consumption management method and platform based on multi-source data drive, which solves the technical problems in the prior art, such as the simplification of multi-modal data collection, the disconnection between energy consumption and spatial information, and the lack of real-time dynamic mapping ability in static analysis, resulting in low energy utilization efficiency and insufficient accuracy of energy consumption management in the park, and achieves the technical effect of improving the accuracy of smart park energy consumption management and energy utilization efficiency.

[0005] This application provides a smart park energy consumption management method based on multi-source data drive. The method includes: connecting multi-modal monitoring devices to obtain multi-source monitoring data, where the multi-modal monitoring devices include electricity, water, air, and equipment status monitoring devices; positioning the monitoring space of the multi-source monitoring data and projecting it into the spatial model of the smart park to construct a multi-dimensional spatial database; performing spatial energy consumption analysis based on the multi-dimensional spatial database to evaluate the energy consumption status of each spatial area and identify spatial areas with excessive energy consumption; and performing energy-saving analysis based on the multi-source monitoring data of the spatial areas with excessive energy consumption in combination with the spatial distribution characteristics to obtain an energy-saving management plan.

[0006] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: identifying the structural distribution of the intelligent park and constructing a three-dimensional spatial model of the park; performing primary classification according to the facility attributes of the park and dividing the attribute space, where the facility attributes include buildings, roads, and greenery; performing secondary classification according to the energy consumption levels of the attribute spaces and dividing the energy consumption level space; and performing boundary marking in the three-dimensional spatial model of the park according to the spatial boundaries of the attribute space and the energy consumption level space to obtain the spatial model of the intelligent park.

[0007] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: based on the multi-dimensional spatial database, aligning and fusing the multi-source monitoring data according to the spatial relationship to obtain multi-source fusion features; based on the multi-source monitoring data, setting a monitoring decision range, where the monitoring decision range is the decision threshold of the monitoring data and corresponds to the data source; and respectively performing energy consumption analysis and evaluation according to the monitoring decision range and the multi-source fusion features to obtain an energy consumption evaluation result.

[0008] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: using the monitoring decision range to match and compare with the multi-source monitoring data. When the monitoring decision range is exceeded, the energy consumption evaluation result is out-of-range abnormal energy consumption and the corresponding out-of-range value; when the monitoring decision range is not exceeded, the energy consumption evaluation result is the monitoring data of the corresponding data source; and predicting the spatial energy consumption trend according to the multi-source fusion features and obtaining the energy consumption evaluation result based on the energy consumption prediction trend.

[0009] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: determining the acquisition accuracy distribution according to the spatial relationship of the multi-modal monitoring devices, and compensating the monitoring data using the acquisition accuracy distribution; aligning the multi-source monitoring data after the compensation processing according to the spatial relationship and calculating the change characteristics of the monitoring data of each data source; and fusing the change characteristics of the monitoring data of each data source according to the alignment relationship to obtain the multi-source fusion features.

[0010] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: aligning the multi-source monitoring data with the same coordinates according to the spatial coordinates according to the spatial relationship; performing time alignment on the multi-source monitoring data according to the acquisition frequency and acquisition timestamp of the multi-modal monitoring devices; and performing alignment calculation of the change characteristics of the multi-source monitoring data according to the position alignment and time alignment relationships.

[0011] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: setting a spatial energy consumption comparison list according to the historical energy consumption records of each spatial area; using the energy consumption evaluation result to perform comparison and matching with the spatial energy consumption comparison list to identify the energy consumption excess difference of each spatial area and determine the spatial area with energy consumption excess.

[0012] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: extracting the spatial distribution characteristics of the corresponding spatial area with energy consumption excess according to the spatial model of the intelligent park, where the spatial distribution characteristics include spatial attributes, energy consumption levels, and spatial item placement characteristics; tracing the abnormal factors and abnormal monitored quantities according to the multi-source monitoring data of the spatial area with energy consumption excess; analyzing the influence relationship between the abnormal factors and the spatial attributes and spatial item placement characteristics to obtain an energy consumption adjustment relationship; analyzing the energy-saving adjustment constraints of the area based on the energy consumption level; and performing energy-saving compensation control adjustment based on the abnormal factors and abnormal monitored quantities according to the energy consumption adjustment relationship and energy-saving adjustment constraints to obtain the energy-saving management plan.

[0013] In a possible implementation, the multi-source data-driven intelligent park energy consumption management method further performs the following processing: obtaining the energy-saving management plans for multiple spatial areas with energy consumption excess; identifying the energy consumption correlation of the multiple spatial areas with energy consumption excess; evaluating the energy-saving management plans for the multiple spatial areas with energy consumption excess according to the energy consumption correlation and jointly executing the park operation loss amount; configuring the equilibrium weights for each spatial area with energy consumption excess according to the park operation loss amount; and performing equilibrium adjustment on the energy-saving management plans for the multiple spatial areas with energy consumption excess based on the equilibrium weights and park operation loss amount to obtain an energy-saving management plan for multi-area balance in the park.

[0014] This application also provides a multi-source data-driven intelligent park energy consumption management platform, including: a multi-source monitoring data acquisition module for connecting multi-modal monitoring devices to obtain multi-source monitoring data, where the multi-modal monitoring devices include electricity, water, air, and equipment status monitoring devices; a multi-dimensional spatial database construction module for positioning the monitoring space of the multi-source monitoring data and projecting it into the spatial model of the intelligent park to construct a multi-dimensional spatial database; a spatial energy consumption analysis module for performing spatial energy consumption analysis according to the multi-dimensional spatial database, evaluating the energy consumption status of each spatial area, and identifying the spatial areas with energy consumption excess; and an energy-saving management plan acquisition module for performing energy-saving analysis in combination with the spatial distribution characteristics according to the multi-source monitoring data of the spatial areas with energy consumption excess to obtain an energy-saving management plan.

[0015] The intelligent park energy consumption management method and platform based on multi-source data drive proposed in this application connect multi-modal monitoring devices to obtain multi-source monitoring data; locate the monitoring space of the multi-source monitoring data, project it into the space model of the intelligent park, and construct a multi-dimensional space database; perform spatial energy consumption analysis based on the multi-dimensional space database, evaluate the energy consumption status of each spatial area, and identify areas with excessive spatial energy consumption; according to the multi-source monitoring data of the areas with excessive spatial energy consumption, combine the spatial distribution characteristics to perform energy-saving analysis and obtain an energy-saving management plan. It solves the technical problems existing in the prior art, such as the single collection of multi-modal data, the disconnection between energy consumption and spatial information, and the lack of real-time dynamic mapping ability in static analysis, resulting in low energy utilization efficiency and insufficient accuracy of energy consumption management in the park, and achieves the technical effect of improving the accuracy of energy consumption management and energy utilization efficiency in the intelligent park. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the platform according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0017] Figure 1 It is a schematic flowchart of the intelligent park energy consumption management method based on multi-source data drive provided by the embodiment of the present application.

[0018] Figure 2 It is a schematic structural diagram of the intelligent park energy consumption management platform based on multi-source data drive provided by the embodiment of the present application.

[0019] Description of the reference numerals: The multi-source monitoring data acquisition module 10, the multi-dimensional space database construction module 20, the spatial energy consumption analysis module 30, and the energy-saving management plan acquisition module 40. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the detailed implementation manners of this application.

[0021] In order to make the purpose, technical solution and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0022] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first" and "second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, platform, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0023] The embodiments of this application provide a smart park energy consumption management method driven by multi-source data, as Figure 1 shown, the method includes:

[0024] Step S100, connect multi-modal monitoring devices to obtain multi-source monitoring data. The multi-modal monitoring devices include electricity, water, air, and equipment status monitoring devices.

[0025] Preferably, the multi-modal monitoring devices refer to a variety of sensors and intelligent terminal devices for real-time monitoring of different energy types, environmental parameters, and equipment operating states, including electricity monitoring devices, water monitoring devices, air monitoring devices, and equipment status monitoring devices. Specifically, multiple different types of sensors and monitoring devices are connected through the Internet of Things (IoT) to collect real-time data on energy consumption, environmental parameters, and equipment operating states in different dimensions within the park, obtaining multi-source monitoring data. Among them, the electricity monitoring devices are used to monitor the electricity consumption and related electricity parameters in the park, and may include smart meters (collecting data such as electricity consumption, power, voltage, and current in real time), power quality analyzers (monitoring harmonics, power factor, voltage fluctuations, etc.), etc., and can analyze and identify the distribution of electricity loads and identify high-energy-consuming equipment; the water monitoring devices are used to monitor the water resource consumption, water quality, and pipe network status in the park, and may include smart water meters (recording data such as water consumption, flow rate, and water pressure), water quality sensors (detecting water quality parameters such as pH value, turbidity, and residual chlorine), leak detection sensors, etc., and can track abnormal water use (such as leaks and excessive consumption).

[0026] Preferably, the air monitoring equipment is used to collect indoor and outdoor environmental parameters of the park, which may include temperature and humidity sensors (monitoring indoor and outdoor temperature and humidity changes), CO2 concentration sensors (evaluating air circulation and the operation efficiency of the fresh air system), and PM2.5 / PM10 sensors (detecting air quality and linking with air purification equipment); the equipment status monitoring equipment is used to monitor the operation status of key equipment (such as air conditioning units, elevators, production lines) in the park, which may include vibration sensors (detecting abnormal vibrations of equipment such as motors and pumps), infrared thermal imagers (identifying equipment overheating or heat dissipation failures), and current / voltage monitoring modules (evaluating equipment operation efficiency and aging degree), and can detect inefficient equipment operation and fault early warning, avoiding additional energy consumption caused by "running with problems". Through multi-modal monitoring equipment, multi-source monitoring data such as electricity, water, air, and equipment status are collected in real time, breaking through the limitations of traditional single-dimensional monitoring, thus ensuring the accuracy of energy consumption management and the dynamic nature of energy regulation in the park.

[0027] Step S200, locate the monitoring space of the multi-source monitoring data, project it into the space model of the smart park, and construct a multi-dimensional space database.

[0028] Preferably, the collected multi-source monitoring data (such as electricity, water, air, equipment status, etc.) is associated with its corresponding physical space location information, and is visually mapped and stored through a digital smart park space model, thereby constructing a multi-dimensional space database. Specifically, the physical space location corresponding to each piece of monitoring data is determined by positioning, that is, a unique identifier (ID) is assigned to each monitoring device (such as an electric meter, a water meter, a temperature and humidity sensor, etc.), and its installation location (such as floor, room, equipment number, etc.) is recorded. The indoor positioning technology (such as Bluetooth beacon, UWB ultra-wideband) or the space coordinate system (such as GPS, local coordinate system) is used to accurately locate the equipment location, and the monitoring data is associated with a specific space area (such as a certain building, a certain floor, a certain room); then the monitoring data with space location information is mapped into the digital smart park space model. For example, the monitoring data (such as electricity consumption, temperature and humidity, equipment status, etc.) is bound to the corresponding areas (such as floors, rooms, equipment, etc.) of the building information model (BIM), geographic information system GIS or the three-dimensional visualization model of the park, forming a spatialized monitoring data layer, realizing the spatial visualization of the monitoring data, and facilitating the intuitive analysis of the spatial characteristics of energy consumption distribution and environmental parameters; finally, the spatialized monitoring data is stored in a structured database (i.e., a multi-dimensional space database), supporting multi-dimensional query and analysis. For example, the spatial dimension of the multi-dimensional space database records the physical location corresponding to the data (such as longitude and latitude, floor, room number), the time dimension records the timestamp of the data (such as real-time data, historical data), the data dimension stores the specific values of the multi-source monitoring data (such as electricity consumption, water consumption, temperature, equipment status, etc.), and the metadata dimension records additional information such as equipment type, data unit, and collection frequency. By combining multi-source monitoring data with the space model, a multi-dimensional space database can be constructed, which can visually display the spatial distribution of energy consumption and environmental parameters, and real-time monitor the energy use and environmental status of each area in the smart park, ensuring the refined management of park energy consumption.

[0029] Further, step S200 further includes step S201, identifying the structural distribution of the smart park and constructing a three-dimensional space model of the park; step S202, performing first-level classification according to the park facility attributes and dividing the attribute space, where the facility attributes include buildings, roads, and greenery; step S203, performing second-level classification according to the energy consumption level of the attribute space and dividing the energy consumption level space; step S204, according to the spatial boundaries of the attribute space and the energy consumption level space, performing boundary marking in the three-dimensional space model of the park to obtain the space model of the smart park.

[0030] Preferably, the physical structure of the smart park is identified, classified, and modeled through digital technologies to form a visual three-dimensional space model containing multi-dimensional information such as facility attributes and energy consumption levels. Specifically, the physical structure of the smart park (such as buildings, roads, greenery, etc.) is identified and digitally modeled, that is, technologies such as LiDAR, drone aerial photography, and satellite imagery are used to obtain spatial data of the park's terrain, buildings, roads, etc., combined with Building Information Modeling (BIM) or Geographic Information System (GIS) data to supplement detailed information of park facilities. Then, three-dimensional modeling software (such as AutoCAD, Revit, SketchUp) or GIS platforms (such as ArcGIS) are used to construct a three-dimensional space model of the park, including basic spatial elements such as building outlines, road directions, and green areas. Then, according to the functional attributes of the smart park facilities (including buildings, roads, and greenery), the three-dimensional space model of the park is divided into different attribute areas. For example, buildings include office buildings, factories, dormitories, warehouses, etc., roads include main roads, secondary roads, sidewalks, parking lots, etc., and greenery includes lawns, woods, flower beds, landscape lakes, etc. In the three-dimensional space model of the park, independent layers or areas are assigned to each facility attribute. For example, all building areas are marked as "building attribute space", and all road areas are marked as "road attribute space" to achieve functional zoning management of the park space.

[0031] Preferably, based on the attribute space, the energy consumption level space is further divided according to the energy consumption level (such as high, medium, low). Specifically, based on historical energy consumption data, energy consumption level thresholds for different attribute spaces are set. For example, in the building attribute space, the energy consumption level of an office building is "high", and that of a warehouse is "low". Then, within the attribute space, the area is further subdivided according to the energy consumption level. For example, the energy consumption level of a certain office building is marked as "high energy consumption space", and that of a certain green area is marked as "low energy consumption space", thereby achieving refined classification management of energy consumption. Finally, the boundary information of the attribute space and the energy consumption level space is marked in the three-dimensional space model, that is, different colors, lines, or layers are used to mark the boundaries of the attribute space and the energy consumption level space. For example, the high energy consumption space is marked in red, and the low energy consumption space is marked in green. Then, the attribute space, the energy consumption level space, and their boundary information are integrated into the three-dimensional space model to obtain the space model of the smart park, which can achieve refined space management and improve the efficiency of energy consumption analysis.

[0032] Step S300, perform spatial energy consumption analysis based on the multi-dimensional space database, evaluate the energy consumption status of each spatial area, and identify areas with excessive spatial energy consumption.

[0033] Preferably, spatial energy consumption analysis is carried out by using the constructed multi-dimensional spatial database (including information such as spatial location, time, and multi-source monitoring data), the energy consumption status of each spatial area in the park is evaluated, and areas with abnormal or excessive energy consumption are identified. Specifically, based on the multi-dimensional spatial database, the energy consumption data of each area in the park is statistically analyzed and visualized, including extracting energy consumption data (such as electricity consumption, water consumption) from the database according to spatial areas (such as floors, rooms, equipment) and time ranges (such as days, months, years), and then conducting data analysis, such as calculating the average energy consumption, peak energy consumption, and energy consumption trend of each area, analyzing the correlation between energy consumption and time and environmental parameters (such as temperature, humidity), comparing the energy consumption differences between different areas, and then visualizing the spatial distribution and change trend of energy consumption in the smart park through heat maps, bar charts, line charts, etc.; then, a quantitative evaluation of the energy consumption data of each spatial area is carried out to judge whether its energy consumption level is reasonable. Specifically, based on historical data and regional function differences (such as office areas, production areas, living areas), energy consumption benchmark values (such as electricity consumption per unit area, water consumption per capita) for each area in the smart park are set, and the energy consumption intensity (energy consumption per unit area or per unit output value), energy consumption efficiency (the ratio of energy consumption to actual output or usage demand), and energy consumption volatility (the change range of energy consumption over time) of each area are evaluated. Then, the actual energy consumption of each area is compared with the benchmark value to judge whether it exceeds the standard, and a quantitative evaluation of the energy consumption status is carried out according to the comparison results (such as classified as high, medium, low); finally, by analyzing the energy consumption data, areas with abnormal energy consumption or significantly higher than the benchmark are found, that is, the energy consumption data of each area is compared with the benchmark value, and areas exceeding a certain threshold (such as 20%) are determined as areas with excessive energy consumption, and multi-source data (such as equipment status, environmental parameters) are associated to analyze the possible reasons for excessive energy consumption (such as equipment failure, excessive environmental control, human waste), so as to comprehensively understand the energy consumption situation of each area in the park and improve the energy utilization efficiency of the park.

[0034] Further, step S300 further includes step S310 of aligning and fusing the features of multi-source monitoring data according to the spatial relationship based on the multi-dimensional spatial database to obtain multi-source fusion features; step S320 of setting a monitoring decision range based on the multi-source monitoring data, where the monitoring decision range is the decision threshold of the monitoring data and corresponds to the data source; step S330 of respectively carrying out energy consumption analysis and evaluation according to the monitoring decision range and the multi-source fusion features to obtain an energy consumption evaluation result.

[0035] Preferably, using multi-source monitoring data in a multi-dimensional spatial database (such as electricity, water, air, equipment status, etc.), through spatial alignment and feature fusion technologies, comprehensive features are extracted, and combined with preset decision thresholds to analyze and evaluate the energy consumption status. Specifically, the monitoring data from different data sources (such as electricity meters, water meters, temperature and humidity sensors, etc.) are aligned and fused according to their spatial position relationships, and comprehensive features are extracted, that is, the spatial position information of multi-source data (such as floor, room, equipment number) is matched with the spatial model in the multi-dimensional spatial database to ensure that the multi-source data within the same spatial area are aligned in time and space. Then, data fusion algorithms (such as weighted average, principal component analysis PCA, deep learning models) are used to integrate the multi-source data into comprehensive features, which may include energy consumption intensity (energy consumption per unit area or unit time), energy consumption efficiency (the ratio of energy consumption to actual output or usage demand), and environmental energy consumption index (the correlation between energy consumption and environmental parameters).

[0036] Preferably, according to the multi-source monitoring data, a monitoring decision range is set, that is, decision thresholds for the monitoring data are set, corresponding to the data sources, and are used to judge whether the energy consumption status is normal or excessive. Specifically, based on historical data, decision thresholds for different data sources are set, including electricity decision threshold, water decision threshold, air decision threshold, etc. If the decision threshold is exceeded, it means excessive power consumption, excessive water use, or air pollution. Then, using the multi-source fusion features and decision thresholds, the energy consumption status of each area in the park is analyzed and evaluated to obtain an energy consumption evaluation result, that is, the multi-source fusion features are compared with the decision thresholds to judge whether the energy consumption status is normal. For example, if the comprehensive energy consumption characteristics of a certain area exceed the threshold, it is determined that the energy consumption is excessive; the energy consumption status is quantitatively evaluated according to the level classification (such as high, medium, low). For example, if the energy consumption score of a certain area is "high", it means that the energy consumption efficiency of this area is relatively low; finally, the energy consumption abnormal areas are identified, the reasons for the anomalies are analyzed (such as equipment failures, excessive environmental regulation), and reasonable energy-saving measures are formulated to continuously optimize the energy consumption management of the park.

[0037] Furthermore, step S310 further includes step S311, determining the acquisition accuracy distribution according to the spatial relationship of the multi-modal monitoring devices, and using the acquisition accuracy distribution to perform compensation processing on the monitoring data; step S312, aligning the multi-source monitoring data after compensation processing according to the spatial relationship, and calculating the change characteristics of the monitoring data of each data source; step S313, fusing the change characteristics of the monitoring data of each data source according to the alignment relationship to obtain the multi-source fusion features.

[0038] Preferably, by analyzing the spatial distribution of multi-modal monitoring devices and their data acquisition accuracy, precision compensation and spatial alignment are performed on the monitoring data, and then the change characteristics of each data source are extracted and fused into comprehensive characteristics. Specifically, analyze the spatial distribution of multi-modal monitoring devices (such as electricity meters, water meters, temperature and humidity sensors, etc.), and evaluate their data acquisition accuracy, including determining the spatial positions of each monitoring device (such as floor, room, device number), analyzing the spatial distances and coverage ranges between devices; evaluate their data acquisition accuracy according to factors such as device type, installation location, environmental conditions, etc., and then compensate for the monitoring data with lower accuracy according to the accuracy distribution to improve data quality. For example, use interpolation algorithms (such as linear interpolation, Kriging interpolation) to fill in missing data, use filtering algorithms (such as Kalman filtering) to remove noise data, and correct the data in areas with lower accuracy to make it closer to the true value, so as to improve the accuracy and consistency of the monitoring data.

[0039] Preferably, align the multi-source monitoring data (such as electricity, water, air, device status, etc.) after compensation processing according to the spatial position, that is, map the monitoring data of each data source to a unified spatial coordinate system and synchronize them according to the time stamp to ensure the consistency of the data in time and space. Extract the change characteristics from the aligned multi-source monitoring data to describe the dynamic changes of energy consumption, environmental parameters, etc. Specifically, calculate the time series characteristics of each data source, such as mean, variance, trend, periodicity, etc., and then calculate the spatial distribution characteristics of each data source, such as regional differences, spatial correlations, etc., to capture the dynamic change laws of the multi-source monitoring data; finally, use weighted average, principal component analysis (PCA), deep learning models, etc., to fuse the change characteristics of the monitoring data of each data source into comprehensive characteristics, extract a more comprehensive and accurate description of the energy consumption status, and then improve the data quality to ensure the refinement of the energy consumption management in the park.

[0040] Further, step S312 further includes step A, aligning the multi-source monitoring data with the same coordinates according to the spatial relationship according to the spatial coordinates; step B, performing time alignment on the multi-source monitoring data according to the acquisition frequency and acquisition time stamp of the multi-modal monitoring device; step C, performing change characteristic alignment calculation on the multi-source monitoring data according to the position alignment and time alignment relationships.

[0041] Preferably, multi-source monitoring data (such as electricity, water, air, equipment status, etc.) are aligned in the spatial and temporal dimensions through spatial coordinates and timestamps, and the change characteristics of each data source are calculated based on the alignment relationship. Specifically, the monitoring data from different data sources (such as electricity meters, water meters, temperature and humidity sensors, etc.) are aligned according to their spatial coordinates (such as longitude and latitude, floor, room number) to ensure that the data matches at the same spatial position. Then, according to the acquisition frequency and acquisition timestamp of the multi-modal monitoring device, the multi-source monitoring data are time-aligned to ensure that the data are synchronized in the time dimension. For example, the electricity consumption at a certain moment is aligned with the temperature and humidity data at the same moment. And if the acquisition frequencies of the data sources are different, interpolation or downsampling methods are used to adjust the data to the same time dimension. Finally, on the basis of spatial and temporal alignment, the change characteristics of the monitoring data of each data source are calculated, and these characteristics are ensured to be aligned in space and time, including calculating the change characteristics of the monitoring data of each data source, such as mean, variance, trend, periodicity, etc., and then aligning the change characteristics of each data source according to spatial coordinates and timestamps, and integrating the aligned change characteristics into comprehensive characteristics to describe the multi-dimensional information of the energy consumption status, so as to achieve the precise matching of multi-source data in space and time and ensure the refined energy consumption management of the park.

[0042] Further, step S330 further includes step S331, using the monitoring decision range to perform data source matching and comparison with the multi-source monitoring data. When exceeding the monitoring decision range, the energy consumption evaluation result is out-of-range abnormal energy consumption and the corresponding out-of-range value; step S332, when not exceeding the monitoring decision range, the energy consumption evaluation result is the monitoring data of the corresponding data source; step S333, performing spatial energy consumption trend prediction according to the multi-source fusion characteristics, and obtaining the energy consumption evaluation result based on the energy consumption prediction trend.

[0043] Preferably, by comparing the multi-source monitoring data with a preset decision threshold, it is judged whether the energy consumption status is abnormal, and the future energy consumption trend is predicted in combination with the multi-source fusion characteristics, so as to obtain a more comprehensive energy consumption evaluation result. Specifically, the multi-source monitoring data (such as electricity, water, air, equipment status, etc.) are compared with the preset decision threshold to judge whether the energy consumption status is normal, including matching the monitoring data of each data source (such as electricity consumption, water consumption) with its corresponding decision threshold. If the monitoring data exceeds the threshold, it is determined as "out-of-range abnormal energy consumption", and the exceeded value is recorded as the energy consumption analysis result. If the monitoring data does not exceed the threshold, it is determined as "normal energy consumption", and the actual monitoring data is recorded as the energy consumption analysis result.

[0044] Preferably, multi-source fusion features (such as energy consumption intensity, energy consumption efficiency, environmental energy consumption index) are used to predict future energy consumption trends. Specifically, considering the impact of multi-source fusion features (such as environmental parameters, equipment status) on energy consumption, time series analysis (such as ARIMA), machine learning (such as LSTM neural network) or deep learning models are used to predict future energy consumption trends based on historical data, and predict the future energy consumption changes in each region (such as the electricity consumption of an office building will increase by 20% in summer); then, according to the predicted energy consumption trends, evaluate the future energy consumption status, including judging whether the predicted energy consumption trend may exceed the decision threshold. If the predicted trend exceeds the threshold, it is marked as "potential out-of-range abnormal energy consumption", and if the predicted trend does not exceed the threshold, it is marked as "expected normal energy consumption", and these are used as the energy consumption evaluation results, so as to achieve the automation and intelligence of energy consumption management and avoid the occurrence of energy consumption anomalies.

[0045] Further, step S300 further includes step S340 of setting a spatial energy consumption comparison list according to the historical energy consumption records of each spatial region; step S350 of using the energy consumption evaluation result to perform comparison and matching with the spatial energy consumption comparison list to identify the energy consumption excess difference in each spatial region and determine the spatial energy consumption excess region.

[0046] Preferably, an energy consumption benchmark (comparison list) for each spatial region is established through historical energy consumption data, and the current energy consumption evaluation result is compared with the benchmark to calculate the energy consumption excess difference, so as to identify the regions with energy consumption excess. Specifically, collect the energy consumption data (such as electricity consumption, water consumption) of each spatial region in the past period (such as one year), and calculate the statistical characteristics (such as mean, median, standard deviation) of the historical data based on the historical energy consumption data of each spatial region (such as floors, rooms, equipment) as the energy consumption benchmark, so as to generate an energy consumption comparison list for each spatial region, including the benchmark value and its allowable fluctuation range; compare the current energy consumption evaluation result (such as the electricity consumption, water consumption of a certain region) with the benchmark value in the spatial energy consumption comparison list to judge whether the energy consumption status is normal. If the current energy consumption data exceeds the allowable range of the benchmark value, it is determined that there is an energy consumption excess, so as to quickly identify the energy consumption abnormal region, and then calculate the excess difference of the energy consumption excess region (that is, the difference between the current energy consumption and the benchmark value), and determine the spatial positions of these regions, that is, calculate the difference between the current energy consumption data and the benchmark value, then associate the excess difference with the spatial position, and mark the excess region, so as to accurately locate the spatial energy consumption excess region and further improve the energy efficiency management level of the park.

[0047] Step S400, according to the multi-source monitoring data of the spatial energy consumption excess region, combined with the spatial distribution characteristics, perform energy-saving analysis to obtain an energy-saving management plan.

[0048] Preferably, after identifying the energy consumption overrun area, multi-source monitoring data of this area (such as electricity, water, air, equipment status, etc.) and spatial distribution characteristics (such as area function, equipment layout, environmental conditions, etc.) are used to conduct energy-saving analysis to obtain the reasons for energy consumption overrun and formulate targeted energy-saving management plans. Specifically, multi-source data such as electricity, water, air, and equipment status in the energy consumption overrun area are integrated for correlation analysis, including time synchronization and spatial matching of data such as electricity consumption, water consumption, temperature and humidity, and equipment operation status, analyzing whether environmental parameters (such as temperature and humidity) are abnormal during the energy consumption overrun period, checking the equipment operation status (such as whether it is overloaded or operating inefficiently), comparing historical data, identifying the reasons for sudden increase in energy consumption, and clarifying the reasons for energy consumption overrun; then considering the spatial characteristics of the energy consumption overrun area (such as area function, equipment layout, building structure, etc.), analyzing the spatial influencing factors of energy consumption overrun, including area function analysis, such as the energy consumption characteristics of the office area, production area, and living area are different, equipment layout analysis, such as high equipment density in a certain area leads to excessive local electricity load, building structure analysis, such as poor thermal insulation performance in a certain area leads to increased air-conditioning energy consumption, and environmental condition analysis, such as insufficient lighting in a certain area leads to increased lighting energy consumption.

[0049] Preferably, based on the reasons for energy consumption overrun and spatial characteristics, specific energy-saving measures and optimization plans are formulated, including equipment optimization, environmental control optimization, behavior management, and technology application, etc. Specifically, equipment optimization includes upgrading or replacing high-energy-consuming equipment (such as replacing high-efficiency motors, installing frequency converters), and adjusting equipment operation strategies (such as operating in different time periods, load balancing); environmental control optimization includes optimizing the control logic of air-conditioning and lighting systems (such as adjusting air-conditioning temperature according to the number of people, adjusting lighting brightness according to natural light), and improving the building's thermal insulation performance (such as adding thermal insulation materials, optimizing window design); behavior management includes formulating energy-saving behavior norms (such as reminding employees to turn off unused equipment), and improving the energy-saving awareness of park users through visualization of energy consumption data; technology application includes introducing intelligent control systems (such as AI-based energy consumption prediction and regulation) and deploying renewable energy (such as solar photovoltaic panels, wind power generation); using these measures to form an energy-saving management plan, and through targeted energy-saving measures, reducing the energy consumption of the energy consumption overrun area and improving the overall energy efficiency of the park.

[0050] Further, step S400 further includes step S410 of extracting the spatial distribution characteristics of the area with excessive spatial energy consumption according to the spatial model of the smart park, where the spatial distribution characteristics include spatial attributes, energy consumption levels, and spatial placement characteristics; step S420 of tracing the abnormal factors and abnormal monitored quantities according to the multi-source monitoring data of the area with excessive spatial energy consumption; step S430 of analyzing the influence relationship between the abnormal factors and the spatial attributes and spatial placement characteristics to obtain an energy consumption adjustment relationship; step S440 of analyzing the energy-saving adjustment constraints of the area based on the energy consumption level; and step S450 of performing energy-saving compensation control adjustment based on the abnormal factors and abnormal monitored quantities according to the energy consumption adjustment relationship and energy-saving adjustment constraints to obtain the energy-saving management plan.

[0051] Preferably, by analyzing the spatial characteristics and multi-source monitoring data of the area with excessive energy consumption, trace the causes of energy consumption anomalies, and combine factors such as spatial attributes and energy consumption levels to formulate a targeted energy-saving management plan. Specifically, extract the spatial characteristics of the area with excessive energy consumption from the spatial model of the smart park, including spatial attributes, energy consumption levels, and spatial placement characteristics. Among them, spatial attributes describe the functional types of areas (such as office areas, production areas, living areas), energy consumption levels describe the energy consumption levels of areas (such as high, medium, low), and spatial placement characteristics describe the equipment layout, building structure, environmental conditions, etc. of the area; through multi-source monitoring data (such as electricity, water, air, equipment status, etc.), analyze the specific reasons (abnormal factors) for excessive energy consumption and their corresponding abnormal data (abnormal monitored quantities), including analyzing multi-source data to identify abnormal factors and finding the key factors leading to excessive energy consumption, and then extracting the monitoring data related to the abnormal factors. For example, extract data such as the electricity consumption, running time, and environmental temperature of the air conditioning system.

[0052] Preferably, analyze the association between abnormal factors and spatial attributes and spatial placement characteristics to clarify the direction and method of energy consumption adjustment. For example, the excessive air conditioning energy consumption in an office area is related to spatial attributes (office area) and spatial placement characteristics (dense equipment, poor ventilation). Analyze the causal relationship between the abnormal factor (high-power operation of the air conditioner) and the spatial characteristic (poor ventilation), and then determine the energy consumption adjustment relationship, that is, the specific direction and measures of energy consumption adjustment; then analyze the energy-saving adjustment constraints of the area based on the energy consumption level of the area with excessive energy consumption. For example, analyze the technical and economic constraint conditions of energy-saving adjustment to ensure the feasibility of the energy-saving plan; finally, according to the abnormal factors, energy consumption adjustment relationship, and energy-saving adjustment constraints, formulate a specific energy-saving management plan, including determining energy-saving measures, compensating for excessive energy consumption by adjusting equipment operation parameters, improving spatial layout, etc., and finally generating an energy-saving management plan including specific measures, implementation steps, and expected effects to reduce the energy consumption of the area with excessive energy consumption and improve the energy efficiency of the park.

[0053] Further, step S450 further includes step S451 of obtaining an energy-saving management plan for the multi-space energy consumption overrun areas; step S452 of identifying the energy consumption correlation of the multi-space energy consumption overrun areas; step S453 of evaluating the energy-saving management plan for the multi-space energy consumption overrun areas according to the energy consumption correlation and jointly executing the operation loss amount of the park; step S454 of configuring the balance weights for each space energy consumption overrun area according to the operation loss amount of the park; step S456 of performing a balance adjustment on the energy-saving management plan for the multi-space energy consumption overrun areas based on the balance weights and the operation loss amount of the park to obtain an energy-saving management plan for multi-area balance in the park.

[0054] Preferably, after formulating an energy-saving management plan for the multi-space energy consumption overrun areas, by analyzing the energy consumption correlation between these areas, evaluating the impact of plan implementation on the overall operation of the park, and optimizing and adjusting the plan based on the balance weights and the operation loss amount, finally achieving the balanced management of energy consumption in multiple areas of the park. Specifically, obtain an energy-saving management plan for the multi-space energy consumption overrun areas, analyze the energy consumption correlation between multiple energy consumption overrun areas, that is, through multi-source monitoring data, analyze whether the energy consumption changes between areas are synchronous or interact with each other, and at the same time analyze the spatial position relationship between areas (such as adjacent, sharing equipment); then evaluate the energy-saving management plan for the multi-space energy consumption overrun areas according to the energy consumption correlation, that is, evaluate the impact of multiple energy-saving management plans on the overall operation of the park during implementation, and quantify the operation loss amount (such as energy efficiency decline, cost increase). For example, analyze the impact on related areas after implementing each plan, quantify the energy efficiency loss and economic cost of the park after plan implementation, and calculate the percentage of energy efficiency decline caused by power load fluctuations to evaluate the comprehensive impact of the plan.

[0055] Preferably, according to the magnitude of the operation loss amount of the park, allocate balance weights to each energy consumption overrun area for adjusting the priority of the energy-saving management plan. Specifically, areas with a large operation loss amount are allocated higher weights, and their energy-saving plans are adjusted first, and the weights of each area are normalized to a weight distribution with a total sum of 1; finally, according to the balance weights and the operation loss amount, optimize and adjust the energy-saving management plans for each area to achieve the balanced management of energy consumption in multiple areas of the park, including preferentially optimizing the plans for high-weight areas to reduce their impact on the overall operation of the park. For example, adjust the air-conditioning operation strategy in area A to reduce the power load impact on area B; comprehensively consider the energy-saving goals and operation loss amounts of each area to formulate a balanced energy-saving management plan, thereby achieving the collaborative optimization of energy consumption in multiple areas of the park and improving the overall energy efficiency level and operation management efficiency.

[0056] In the above text, reference is made to Figure 1 described in detail the energy consumption management method for a smart park based on multi-source data-driven according to an embodiment of the present invention. Next, reference will be made to Figure 2Describe an intelligent park energy consumption management platform based on multi-source data driving according to an embodiment of the present invention.

[0057] The intelligent park energy consumption management platform based on multi-source data driving according to an embodiment of the present invention is used to solve the technical problems existing in the prior art, such as the singleization of multi-modal data collection, the disconnection between energy consumption and spatial information, and the lack of real-time dynamic mapping ability in static analysis, resulting in low energy utilization efficiency in the park and insufficient accuracy of energy consumption management, and achieves the technical effect of improving the accuracy of intelligent park energy consumption management and energy utilization efficiency. As Figure 2 shown, the intelligent park energy consumption management platform based on multi-source data driving includes: a multi-source monitoring data acquisition module 10, a multi-dimensional spatial database construction module 20, a spatial energy consumption analysis module 30, and an energy-saving management plan acquisition module 40.

[0058] The multi-source monitoring data acquisition module 10 is used to connect multi-modal monitoring devices and obtain multi-source monitoring data. The multi-modal monitoring devices include electricity, water, air, and equipment status monitoring devices; the multi-dimensional spatial database construction module 20 is used to locate the monitoring space of the multi-source monitoring data, project it into the spatial model of the intelligent park, and construct a multi-dimensional spatial database; the spatial energy consumption analysis module 30 is used to perform spatial energy consumption analysis according to the multi-dimensional spatial database, evaluate the energy consumption status of each spatial area, and identify areas with excessive spatial energy consumption; the energy-saving management plan acquisition module 40 is used to perform energy-saving analysis based on the multi-source monitoring data of the areas with excessive spatial energy consumption and combine the spatial distribution characteristics to obtain an energy-saving management plan.

[0059] Next, the specific configuration of the multi-dimensional spatial database construction module 20 will be described in detail. The multi-dimensional spatial database construction module 20 further includes: identifying the structural distribution of the intelligent park and constructing a three-dimensional spatial model of the park; performing first-level classification according to the facility attributes of the park and dividing the attribute space. The facility attributes include buildings, roads, and greenery; performing second-level classification according to the energy consumption levels of the attribute spaces and dividing the energy consumption level spaces; marking the boundaries in the three-dimensional spatial model of the park according to the spatial boundaries of the attribute spaces and energy consumption level spaces to obtain the spatial model of the intelligent park.

[0060] Next, the specific configuration of the spatial energy consumption analysis module 30 will be described in detail. The spatial energy consumption analysis module 30 further includes: based on the multi-dimensional spatial database, aligning and fusing the features of the multi-source monitoring data according to the spatial relationship to obtain multi-source fusion features; based on the multi-source monitoring data, setting a monitoring decision range, and the monitoring decision range is the decision threshold of the monitoring data and corresponds to the data source; performing energy consumption analysis and evaluation according to the monitoring decision range and the multi-source fusion features respectively to obtain an energy consumption evaluation result.

[0061] Next, the specific configuration of the spatial energy consumption analysis module 30 will be further described in detail. The spatial energy consumption analysis module 30 further includes: matching and comparing the data sources of the monitoring decision range and the multi-source monitoring data. When the monitoring decision range is exceeded, the energy consumption evaluation result is out-of-range abnormal energy consumption and the corresponding out-of-range value; when the monitoring decision range is not exceeded, the energy consumption evaluation result is the monitoring data of the corresponding data source; predicting the spatial energy consumption trend according to the multi-source fusion feature, and obtaining the energy consumption evaluation result based on the energy consumption prediction trend.

[0062] Next, the specific configuration of the spatial energy consumption analysis module 30 will be further described in detail. The spatial energy consumption analysis module 30 further includes: determining the acquisition accuracy distribution according to the spatial relationship of the multimodal monitoring devices, and compensating the monitoring data by using the acquisition accuracy distribution; aligning the multi-source monitoring data after the compensation process according to the spatial relationship, and calculating the change characteristics of the monitoring data of each data source; fusing the change characteristics of the monitoring data of each data source according to the alignment relationship to obtain the multi-source fusion feature.

[0063] Next, the specific configuration of the spatial energy consumption analysis module 30 will be further described in detail. The spatial energy consumption analysis module 30 further includes: aligning the multi-source monitoring data with the same coordinates according to the spatial coordinates according to the spatial relationship; aligning the multi-source monitoring data in time according to the acquisition frequency and acquisition timestamp of the multimodal monitoring devices; calculating the alignment of the change characteristics of the multi-source monitoring data according to the position alignment and time alignment relationships.

[0064] Next, the specific configuration of the spatial energy consumption analysis module 30 will be further described in detail. The spatial energy consumption analysis module 30 further includes: setting a spatial energy consumption comparison list according to the historical energy consumption records of each spatial region; comparing and matching the energy consumption evaluation result with the spatial energy consumption comparison list to identify the energy consumption excess difference of each spatial region and determine the spatial energy consumption excess region.

[0065] Next, the specific configuration of the energy-saving management plan acquisition module 40 will be described in detail. The energy-saving management plan acquisition module 40 further includes: extracting the spatial distribution characteristics of the corresponding spatial energy consumption excess region according to the spatial model of the smart park, where the spatial distribution characteristics include spatial attributes, energy consumption levels, and spatial placement characteristics; tracing the abnormal factors and abnormal monitored quantities according to the multi-source monitoring data of the spatial energy consumption excess region; analyzing the influence relationship between the abnormal factors and the spatial attributes and spatial placement characteristics to obtain the energy consumption adjustment relationship; analyzing the energy-saving adjustment constraints of the region based on the energy consumption level; performing energy-saving compensation control adjustment based on the abnormal factors and abnormal monitored quantities according to the energy consumption adjustment relationship and energy-saving adjustment constraints to obtain the energy-saving management plan.

[0066] The specific configuration of the energy-saving management scheme acquisition module 40 will be described in detail below. The energy-saving management scheme acquisition module 40 further includes: obtaining energy-saving management schemes for multiple spatial energy-consumption excess areas; identifying the energy consumption correlation of the multiple spatial energy-consumption excess areas; evaluating the energy-saving management schemes for the multiple spatial energy-consumption excess areas according to the energy consumption correlation, and jointly executing the park operation loss amount; configuring the balancing weights of each spatial energy-consumption excess area according to the park operation loss amount; based on the balancing weights and the park operation loss amount, balancing and adjusting the energy-saving management schemes for the multiple spatial energy-consumption excess areas to obtain a balanced energy-saving management scheme for multiple areas in the park.

[0067] The smart park energy consumption management platform based on multi-source data drive provided in the embodiment of the present invention can execute the smart park energy consumption management method based on multi-source data drive provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0068] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0069] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for energy consumption management in an intelligent park driven by multi-source data, characterized in that, The method includes: Connect a multi-modal monitoring device to obtain multi-source monitoring data. The multi-modal monitoring device includes electrical, water, air, and equipment status monitoring devices. Locate the monitoring space of the multi-source monitoring data, project it into the spatial model of the smart park, and construct a multi-dimensional spatial database. Conduct spatial energy consumption analysis based on the multi-dimensional spatial database, evaluate the energy consumption status of each spatial area, and identify areas with excessive spatial energy consumption. Based on the multi-source monitoring data of the areas with excessive spatial energy consumption, perform energy-saving analysis in combination with spatial distribution characteristics to obtain an energy-saving management plan. Among them, before projecting it into the spatial model of the smart park, it includes: Identify the structural distribution of the smart park and construct a three-dimensional spatial model of the park. Conduct first-level classification according to the facility attributes of the park, and divide the attribute space. The facility attributes include buildings, roads, and greenery. Conduct second-level classification according to the energy consumption levels of the attribute spaces, and divide the energy consumption level spaces. Based on the spatial boundaries of the attribute space and the energy consumption level space, perform boundary marking in the three-dimensional spatial model of the park to obtain the spatial model of the smart park. Among them, based on the multi-source monitoring data of the areas with excessive spatial energy consumption, performing energy-saving analysis in combination with spatial distribution characteristics to obtain an energy-saving management plan includes: Based on the spatial model of the smart park, extract the spatial distribution characteristics of the corresponding areas with excessive spatial energy consumption. The spatial distribution characteristics include spatial attributes, energy consumption levels, and spatial item placement characteristics. Based on the multi-source monitoring data of the areas with excessive spatial energy consumption, trace the abnormal factors and abnormal monitored quantities. Analyze the influence relationship between the abnormal factors and the spatial attributes and spatial item placement characteristics to obtain an energy consumption adjustment relationship. Based on the energy consumption level, analyze the energy-saving adjustment constraints of the area. Based on the abnormal factors and abnormal monitored quantities, perform energy-saving compensation control adjustment based on the energy consumption adjustment relationship and energy-saving adjustment constraints to obtain the energy-saving management plan. Among them, obtaining the energy-saving management plan also includes: Obtain the energy-saving management plans for multiple areas with excessive spatial energy consumption. Identify the energy consumption correlation of the multiple areas with excessive spatial energy consumption. Evaluate the energy-saving management plans for the multiple areas with excessive spatial energy consumption according to the energy consumption correlation, and jointly execute the operation loss amount of the park. According to the operation loss amount of the park, configure the balance weights for each area with excessive spatial energy consumption. Based on the balance weights and the operation loss amount of the park, perform balance adjustment on the energy-saving management plans for the multiple areas with excessive spatial energy consumption to obtain an energy-saving management plan for multi-area balance in the park.

2. The method for energy consumption management of an intelligent park based on multi-source data-driven according to claim 1, wherein Conduct spatial energy consumption analysis based on the multi-dimensional spatial database, including: Based on the multi-dimensional spatial database, align and fuse the features of the multi-source monitoring data according to the spatial relationship to obtain multi-source fusion features. Based on the multi-source monitoring data, set the monitoring decision range. The monitoring decision range is the decision threshold of the monitoring data and corresponds to the data source. Conduct energy consumption analysis and evaluation respectively according to the monitoring decision range and the multi-source fusion features to obtain an energy consumption evaluation result.

3. The method for intelligent park energy consumption management based on multi-source data driving according to claim 2, wherein, Conduct energy consumption analysis and evaluation respectively according to the monitoring decision range and the multi-source fusion features to obtain an energy consumption evaluation result, including: Match and compare the data sources using the monitoring decision range and the multi-source monitoring data. When the range is exceeded, the energy consumption evaluation result is the out-of-range abnormal energy consumption and the corresponding out-of-range value; When the monitoring decision range is not exceeded, the energy consumption evaluation result is the monitoring data of the corresponding data source; Predict the spatial energy consumption trend based on the multi-source fusion features, and obtain the energy consumption evaluation result based on the energy consumption prediction trend.

4. The method for energy consumption management of an intelligent park based on multi-source data-driven according to claim 2, wherein, Align and fuse the features of the multi-source monitoring data according to the spatial relationship to obtain the multi-source fusion features, including: Determine the acquisition accuracy distribution according to the spatial relationship of the multi-modal monitoring devices, and use the acquisition accuracy distribution to compensate the monitoring data; Align the multi-source monitoring data after compensation processing according to the spatial relationship, and calculate the change characteristics of the monitoring data of each data source; Fuse the change characteristics of the monitoring data of each data source according to the alignment relationship to obtain the multi-source fusion features.

5. The method for energy consumption management of an intelligent park based on multi-source data driving according to claim 4, wherein Align the multi-source monitoring data after compensation processing according to the spatial relationship, and calculate the change characteristics of the monitoring data of each data source, including: Align the positions of the multi-source monitoring data with the same coordinates according to the spatial coordinates according to the spatial relationship; Align the multi-source monitoring data in time according to the acquisition frequency and acquisition timestamp of the multi-modal monitoring devices; Perform alignment calculation of the change characteristics of the multi-source monitoring data according to the position alignment and time alignment relationships.

6. The method for energy consumption management of an intelligent park based on multi-source data-driven according to claim 3, wherein, Evaluate the energy consumption status of each spatial area and identify the areas with excessive spatial energy consumption, including: Set up a spatial energy consumption comparison list according to the historical energy consumption records of each spatial area; Use the energy consumption evaluation result to compare and match with the spatial energy consumption comparison list, identify the excessive energy consumption difference in each spatial area, and determine the areas with excessive spatial energy consumption.

7. The intelligent park energy consumption management platform based on multi-source data-driven is characterized in that, The platform is used to implement the intelligent park energy consumption management method based on multi-source data drive according to any one of claims 1 to 6. The platform includes: A multi-source monitoring data acquisition module, which is used to connect multi-modal monitoring devices to obtain multi-source monitoring data. The multi-modal monitoring devices include electricity, water, air, and equipment status monitoring devices; A multi-dimensional spatial database construction module, which is used to locate the monitoring space of the multi-source monitoring data, project it into the spatial model of the intelligent park, and construct a multi-dimensional spatial database; A spatial energy consumption analysis module, which is used to perform spatial energy consumption analysis according to the multi-dimensional spatial database, evaluate the energy consumption status of each spatial area, and identify the areas with excessive spatial energy consumption; An energy-saving management plan acquisition module, which is used to perform energy-saving analysis according to the multi-source monitoring data of the areas with excessive spatial energy consumption and combine the spatial distribution characteristics to obtain an energy-saving management plan.

Images