A regional energy monitoring system based on big data

Abstract

The present invention relates to the technical field of energy monitoring. Specifically, a regional energy monitoring system based on big data includes a monitoring center, which is communicatively connected to a data acquisition module, a data storage module, a data visualization module, and an air conditioning system control module. The data acquisition module is used to collect data; the data storage module is used to store historical data; the data processing module is used to obtain the pedestrian flow data; the data visualization module is used to construct a scene area layer, a real-time data layer, and a prediction data layer for the target public building, and construct an integrated visual diagram of regional energy monitoring. The prediction data layer is used to construct a prediction model for pedestrian flow and power consumption. The air conditioning system control module is used to obtain the output power of the air conditioning system in different regions at different time periods. The real-time data layer is used to monitor the status of the air conditioning system in real time. The present invention significantly reduces the building energy consumption on the premise of ensuring the environmental comfort requirements in the public building.

Description

Technical Field

[0001] The present invention relates to the technical field of energy monitoring, and specifically to a regional energy monitoring system based on big data. Background Art

[0002] In recent years, with the large increase in public buildings in China and the continuous improvement of building intelligence, the energy consumption of various equipment used in public buildings has increased significantly. Public buildings have become major energy consumers in the building field. According to statistics, the power consumption per unit area of public buildings is 10-15 times that of ordinary residential houses. And in the annual energy consumption of public buildings, the vast majority of energy is consumed in air-conditioning refrigeration and heating systems.

[0003] Therefore, for the main energy-consuming equipment and systems in public buildings, for a given public building, the building area, the location and quantity of air conditioners are not changeable factors. In public buildings, the number of people is large, and the heat emitted by the human body as a heat source will have a great impact on the indoor temperature and cannot be ignored. Moreover, the distribution of the number of people in public buildings is uneven, varies greatly with time, and varies greatly with festivals. If the air-conditioning system always operates in the same mode under any circumstances, it will cause energy waste when the number of people is small or unevenly distributed. How to achieve the goal of reducing building energy consumption on the premise of ensuring the comfort requirements of the indoor environment of the building is an urgent problem to be solved. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a regional energy monitoring system based on big data, including a monitoring center, which is communicatively connected with a data acquisition module, a data storage module, a data processing module, a data visualization module, and an air-conditioning system control module;

[0005] The data acquisition module is used to obtain the personnel data and power consumption data of each area in the target public building;

[0006] The data storage module is used to store the historical personnel data, historical pedestrian flow data, historical power consumption data, and historical air-conditioning system output power of each area in the target public building;

[0007] The data processing module is used to obtain the pedestrian flow data in each area according to the personnel data of each area in the target public building;

[0008] The data visualization module is used to construct a scene area layer, a real-time data layer, and a prediction data layer for the target public building, and obtain an integrated visible view of regional energy monitoring according to the scene area layer, the real-time data layer, and the prediction data layer;

[0009] The air conditioning system control module is used to obtain the execution standard data and inspection standard data for different time periods in each area, and obtain the output power of the air conditioning system in different time periods in each area according to the execution standard data for each time period.

[0010] Further, the process by which the data acquisition module obtains the personnel data and power consumption data in each area of the target public building includes:

[0011] Obtain the AR scene information of the target public building, extract the functional characteristics according to the AR scene information, split the target public building according to the functional characteristics, and divide it into several scene sub-areas;

[0012] Install energy consumption monitoring points in several scene sub-areas to obtain the personnel data and power consumption data in different scene sub-areas, mark the acquisition time, and set the monitoring period;

[0013] The personnel data includes personnel video stream data and personnel location information.

[0014] Further, the process by which the data processing module obtains the pedestrian flow data in each area according to the personnel data in each area of the target public building includes:

[0015] Obtain the video stream data of the personnel in the scene sub-area, convert the video stream data into continuous video frame images, obtain the skeletal point position data of the personnel in multiple video frame images through the OpenPose algorithm, obtain the skeletal data of the personnel according to the skeletal point position data, convert the skeletal data in multiple video frame images into a continuous skeletal action sequence, generate the action information of the personnel according to the skeletal action sequence, and generate the action trajectory of the personnel according to the action information of the personnel;

[0016] Obtain the exit position and entrance position of each scene sub-area, set a preset distance, select a target scene sub-area, obtain the target personnel in the target scene sub-area whose action trajectory direction is the exit position of the target scene sub-area, obtain the distance between the target personnel and the exit position according to the position information of the target personnel, compare the distance with the preset distance, when the distance is less than or equal to the preset distance, mark the target personnel as valid personnel, and when the distance is greater than the preset distance, mark the target personnel as pre-leaving personnel;

[0017] At the same time, select the target personnel in other scene sub-areas adjacent to the target scene sub-area whose action trajectory direction is the entrance position of the target scene sub-area, obtain the distance between the target personnel and the entrance position according to the position information of the target personnel, compare the distance with the preset distance, and when the distance is greater than the preset distance, mark the target personnel as pre-entering personnel;

[0018] At the same time, mark the personnel whose trajectory direction in the target scene sub-region is not the entrance position of the target scene sub-region as valid personnel;

[0019] Obtain the number of valid personnel, the number of pre-entering personnel, and the number of pre-leaving personnel, obtain the sum of the number of valid personnel and the number of pre-entering personnel, obtain the value obtained by subtracting the number of pre-leaving personnel from the sum of the number of valid personnel and the number of pre-entering personnel, and mark the value as the pedestrian flow data.

[0020] Furthermore, the process by which the data visualization module constructs a scene area layer, a real-time data layer, and a prediction data layer for the target public building and obtains an integrated view of regional energy monitoring based on the scene area layer, the real-time data layer, and the prediction data layer includes:

[0021] Construct a digital twin virtual space, obtain the structural dimension diagram of the target public building and the position information of several scene sub-regions, construct a three-dimensional model of the public building according to the structural dimension diagram of the target public building and map it into the digital twin virtual space, and divide the three-dimensional model into several three-dimensional models of scene sub-regions according to the position information of several scene sub-regions to obtain the scene area layer;

[0022] Obtain the pedestrian flow data and power consumption data of the energy consumption monitoring points in each scene sub-region, and perform data preprocessing to generate pedestrian flow twin data and power consumption twin data, and match the pedestrian flow twin data and power consumption twin data with several three-dimensional models of scene sub-regions in the basic scene layer to obtain the real-time data layer;

[0023] Construct a pedestrian flow and power consumption prediction model according to the historical pedestrian flow data and historical power consumption data stored in the data storage module for each scene sub-region, obtain the pedestrian flow prediction data and power consumption prediction data for each time period in the current monitoring cycle of each scene sub-region according to the pedestrian flow and power consumption prediction model, perform data format preprocessing on the pedestrian flow prediction data and power consumption prediction data, convert them into pedestrian flow prediction twin data and power consumption prediction twin data, and match them with several three-dimensional models of scene sub-regions in the basic scene layer to obtain the prediction data layer;

[0024] Using the scene area layer as the basic layer, overlay the real-time data layer and the prediction data layer on the scene area layer to obtain an integrated view of regional energy monitoring.

[0025] Furthermore, the process by which the prediction data layer constructs a pedestrian flow and power consumption prediction model according to the historical pedestrian flow data and historical power consumption data stored in the data storage module for each scene sub-region includes:

[0026] The predicted data layer is communicatively connected to the data storage module. A historical dataset is constructed based on the pedestrian flow data and power consumption data at each moment of each day in each month of the previous year for each scenario sub-region in the data storage module. The fault detection model is trained in real time through dividing the historical dataset into a training set and a test set until the loss function is stably trained, and the model parameters are saved. The energy consumption model is tested through the test set until it meets the preset requirements, and the pedestrian flow and power consumption prediction models are output;

[0027] The input layer of the pedestrian flow and power consumption prediction model is the historical personnel data and historical power consumption data within the historical monitoring period;

[0028] The output layer of the pedestrian flow and power consumption prediction model is the predicted pedestrian flow data and predicted power consumption data for each time period within the current monitoring period.

[0029] Further, the process by which the air conditioning system control module obtains the execution standard data and inspection standard data for different time periods in each area and obtains the output power of the air conditioning system in each area for different time periods according to the execution standard data for each time period includes:

[0030] Obtain the predicted pedestrian flow data and predicted power consumption data for each time period within the current monitoring period of the scenario sub-region according to the pedestrian flow and power consumption prediction model. Use the predicted pedestrian flow data as the execution standard data and the predicted power consumption data as the inspection standard data;

[0031] Obtain the historical output power of the air conditioning system in each scenario sub-region under different execution standard data for each time period through the data storage module;

[0032] Select the historical output power of the air conditioning system with the highest similarity to the execution standard data of the current time period of the scenario sub-region as the output power of the air conditioning system for the current time period of the scenario sub-region.

[0033] Further, the process by which the real-time data layer is used to compare the real-time data with the execution standard data and inspection standard data to monitor the state of the air conditioning system in real time includes:

[0034] Compare the pedestrian flow data of the current scenario sub-region obtained by the data processing module with the execution standard data, obtain the execution standard deviation value between the pedestrian flow data and the execution standard data, and set the execution standard deviation threshold;

[0035] If the execution standard deviation value is greater than the execution standard deviation threshold, update the execution standard data and inspection standard data for the current monitoring period;

[0036] If the execution standard deviation value is less than or equal to the execution standard deviation threshold, obtain the inspection standard deviation value between the power consumption data collected at the energy consumption monitoring points in the current scene sub-region and the inspection standard data, and set the inspection standard deviation threshold.

[0037] If the inspection standard deviation value is less than or equal to the inspection standard deviation threshold, mark the air conditioning system in the current scene sub-region as normal.

[0038] If the inspection standard deviation value is greater than the inspection standard deviation threshold, mark the air conditioning system in the current scene sub-region as faulty and generate a fault alarm to be sent to the monitoring center.

[0039] Further, when the execution standard deviation value is greater than the execution standard deviation threshold, the process of updating the execution standard data and the inspection standard data for the current monitoring period in the real-time data layer includes:

[0040] Input the personnel data and power consumption data collected during the current monitoring period into the passenger flow and power consumption prediction model, and use the passenger flow prediction data and power consumption prediction data for each time period during the current monitoring period output by the passenger flow and power consumption prediction model as the new execution standard data and inspection standard data.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: Compared with the public building energy consumption control system based on schedule control and temperature control in the traditional technology, the present invention adds a strategy for controlling the energy consumption of public buildings based on passenger flow on the basis of the traditional schedule control and temperature control. In the face of problems such as uneven distribution of passenger flow in each area of public buildings, large variability over time, and large variability over festivals, the present invention can dynamically adjust the output power of the air conditioning systems in each area of public buildings when the passenger flow is small or unevenly distributed, thereby significantly reducing the building energy consumption on the premise of ensuring the environmental comfort requirements in public buildings. Description of the Drawings

[0042] Figure 1 It is a schematic diagram of a regional energy monitoring system based on big data according to an embodiment of the present application. Detailed Embodiments

[0043] The following clearly and completely describes the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0044] Such as Figure 1As shown in the figure, a regional energy monitoring system based on big data includes a monitoring center, which is communicatively connected to a data acquisition module, a data storage module, a data processing module, a data visualization module, and an air conditioning system control module;

[0045] The data acquisition module is used to obtain the personnel data and power consumption data of each area in the target public building;

[0046] The data storage module is used to store the historical personnel data, historical pedestrian flow data, historical power consumption data, and historical air conditioning system output power of each area in the target public building;

[0047] The data processing module is used to obtain the pedestrian flow data in each area according to the personnel data of each area in the target public building;

[0048] The data visualization module is used to construct a scene area layer, a real-time data layer, and a prediction data layer for the target public building, and obtain an integrated visible view of regional energy monitoring based on the scene area layer, the real-time data layer, and the prediction data layer;

[0049] The air conditioning system control module is used to obtain the execution standard data and inspection standard data for each area at different time periods, and obtain the air conditioning system output power for each area at different time periods according to the execution standard data for each time period.

[0050] It should be further noted that in the specific implementation process, the process of the data acquisition module obtaining the personnel data and power consumption data of each area in the target public building includes:

[0051] Obtain the AR scene information of the target public building, extract the functional characteristics according to the AR scene information, split the target public building according to the functional characteristics, and divide it into several scene sub-areas;

[0052] The scene sub-areas include public places such as restaurants, stores, gyms, and exhibition halls;

[0053] Install energy consumption monitoring points in several scene sub-areas to obtain the personnel data and power consumption data in different scene sub-areas, mark the collection time, and set the monitoring period;

[0054] The personnel data includes personnel video stream data and personnel location information.

[0055] It should be further noted that in the specific implementation process, the process of the data processing module obtaining the pedestrian flow data in each area according to the personnel data of each area in the target public building includes:

[0056] Obtain the video stream data of the personnel in the sub-region of the scene, convert the video stream data into continuous video frame images, obtain the skeletal point position data of the personnel in multiple video frame images through the OpenPose algorithm, obtain the skeletal data of the personnel according to the skeletal point position data, convert the skeletal data in multiple video frame images into a continuous skeletal action sequence, generate the action information of the personnel according to the skeletal action sequence, and generate the action trajectory of the personnel according to the action information of the personnel;

[0057] Obtain the exit position and the entrance position of each scene sub-region, set a preset distance, select a target scene sub-region, obtain the target personnel in the target scene sub-region whose action trajectory direction is the exit position of the target scene sub-region, obtain the distance between the target personnel and the exit position according to the position information of the target personnel, compare the distance with the preset distance, when the distance is less than or equal to the preset distance, mark the target personnel as valid personnel, and when the distance is greater than the preset distance, mark the target personnel as pre-leaving personnel;

[0058] At the same time, select the target personnel in other scene sub-regions adjacent to the target scene sub-region whose action trajectory direction is the entrance position of the target scene sub-region, obtain the distance between the target personnel and the entrance position according to the position information of the target personnel, compare the distance with the preset distance, and when the distance is greater than the preset distance, mark the target personnel as pre-entering personnel;

[0059] At the same time, mark the personnel whose trajectory direction in the target scene sub-region is not the entrance position of the target scene sub-region as valid personnel;

[0060] Obtain the number of valid personnel, the number of pre-entering personnel, and the number of pre-leaving personnel, obtain the sum of the number of valid personnel and the number of pre-entering personnel, obtain the value of the sum of the number of valid personnel and the number of pre-entering personnel minus the number of pre-leaving personnel, and mark the value as the pedestrian flow data.

[0061] It should be further noted that in the specific implementation process, the process of the data visualization module constructing the scene area layer, the real-time data layer, and the prediction data layer of the target public building and obtaining the integrated view of regional energy monitoring according to the scene area layer, the real-time data layer, and the prediction data layer includes:

[0062] Construct a digital twin virtual space, obtain the construction dimension diagram of the target public building and the position information of several scene sub-regions, construct a three-dimensional model of the public building according to the construction dimension diagram of the target public building and map it into the digital twin virtual space, and divide the three-dimensional model into several three-dimensional models of scene sub-regions according to the position information of several scene sub-regions to obtain the scene area layer;

[0063] Obtain the pedestrian flow data and power consumption data of the energy consumption monitoring points in each sub-region of the scene, and perform data preprocessing to generate pedestrian flow twin data and power consumption twin data. Match the pedestrian flow twin data and power consumption twin data with the 3D models of several sub-regions of the basic scene layer to obtain a real-time data layer;

[0064] The real-time data layer is used to compare the real-time data with the execution standard data and inspection standard data, so as to monitor the status of the air conditioning system in real time;

[0065] Construct a pedestrian flow and power consumption prediction model based on the historical pedestrian flow data and historical power consumption data stored in the data storage module for each sub-region of the scene. According to the pedestrian flow and power consumption prediction model, obtain the pedestrian flow prediction data and power consumption prediction data for each time period in the current monitoring cycle of each sub-region of the scene. Perform data format preprocessing on the pedestrian flow prediction data and power consumption prediction data to convert them into pedestrian flow prediction twin data and power consumption prediction twin data, and match them with the 3D models of several sub-regions of the basic scene layer to obtain a prediction data layer;

[0066] The prediction data layer constructs a pedestrian flow and power consumption prediction model based on the historical pedestrian flow data and historical power consumption data stored in the data storage module for each sub-region of the scene;

[0067] Using the scene area layer as the basic layer, overlay the real-time data layer and the prediction data layer on the scene area layer to obtain an integrated view of regional energy monitoring.

[0068] It should be further noted that in the specific implementation process, the process of the prediction data layer constructing a pedestrian flow and power consumption prediction model based on the historical pedestrian flow data and historical power consumption data stored in the data storage module for each sub-region of the scene includes:

[0069] The prediction data layer is communicatively connected to the data storage module, constructs a historical data set based on the pedestrian flow data and power consumption data at each moment of each day in each month of the previous year for each sub-region of the scene in the data storage module, and performs real-time learning and training on the fault detection model by dividing the historical data set into a training set and a test set until the loss function training is stable, and saves the model parameters. Test the energy consumption model through the test set until it meets the preset requirements, and output the pedestrian flow and power consumption prediction model;

[0070] The input layer of the pedestrian flow and power consumption prediction model is the historical personnel data and historical power consumption data in the historical monitoring cycle;

[0071] The output layer of the predicted model of the number of people flow and power consumption is the predicted data of the number of people flow and the predicted data of power consumption in each time period within the current monitoring cycle.

[0072] It should be further noted that, in the specific implementation process, the process by which the air-conditioning system control module obtains the execution standard data and inspection standard data for different time periods in each area and obtains the output power of the air-conditioning system in different time periods in each area according to the execution standard data for each time period includes:

[0073] Obtain the predicted data of the number of people flow and the predicted data of power consumption in each time period within the current monitoring cycle of the scene sub-area according to the predicted model of the number of people flow and power consumption, use the predicted data of the number of people flow as the execution standard data, and use the predicted data of power consumption as the inspection standard data;

[0074] Obtain the historical output power of the air-conditioning system in each scene sub-area under different execution standard data in each time period through the data storage module;

[0075] Select the historical output power of the air-conditioning system with the highest similarity to the execution standard data in the current time period of the scene sub-area as the output power of the air-conditioning system in the current time period of the scene sub-area.

[0076] It should be further noted that, in the specific implementation process, the process by which the real-time data layer compares the real-time data with the execution standard data and the inspection standard data to monitor the state of the air-conditioning system in real time includes:

[0077] Compare the number of people flow data of the current scene sub-area obtained by the data processing module with the execution standard data, obtain the execution standard deviation value between the number of people flow data and the execution standard data, and set the execution standard deviation threshold;

[0078] If the execution standard deviation value is greater than the execution standard deviation threshold, update the execution standard data and the inspection standard data of the current monitoring cycle;

[0079] If the execution standard deviation value is less than or equal to the execution standard deviation threshold, obtain the inspection standard deviation value between the power consumption data collected by the energy consumption monitoring point of the current scene sub-area and the inspection standard data, and set the inspection standard deviation threshold;

[0080] If the inspection standard deviation value is less than or equal to the inspection standard deviation threshold, mark the air-conditioning system of the current scene sub-area as the normal state;

[0081] If the inspection standard deviation value is greater than the inspection standard deviation threshold, mark the air-conditioning system of the current scene sub-area as the fault state and generate a fault alarm to send to the monitoring center.

[0082] It should be further noted that, in the specific implementation process, when the execution standard deviation value is greater than the execution standard deviation threshold, the process of updating the execution standard data and inspection standard data for the current monitoring period of the real-time data layer includes:

[0083] Input the personnel data and power consumption data collected during the current monitoring period into the passenger flow and power consumption prediction model, and use the passenger flow prediction data and power consumption prediction data for each time period during the current monitoring period output by the passenger flow and power consumption prediction model as the new execution standard data and inspection standard data.

[0084] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A regional energy monitoring system based on big data, including a monitoring center, characterized in that, The monitoring center is communicatively connected to a data acquisition module, a data storage module, a data processing module, a data visualization module, and an air-conditioning system control module; The data acquisition module is used to obtain personnel data and power consumption data of each area in the target public building; The data storage module is used to store historical personnel data, historical pedestrian flow data, historical power consumption data, and historical air-conditioning system output power of each area in the target public building; The data processing module is used to obtain the pedestrian flow data in each area according to the personnel data of each area in the target public building; The data visualization module is used to construct a scene area layer, a real-time data layer, and a prediction data layer for the target public building, and obtain an integrated view of regional energy monitoring according to the scene area layer, the real-time data layer, and the prediction data layer; The air-conditioning system control module is used to obtain the execution standard data and inspection standard data for each area at different time periods, and obtain the air-conditioning system output power for each area at different time periods according to the execution standard data for each time period; The process by which the data acquisition module obtains the personnel data and power consumption data of each area in the target public building includes: Obtaining the AR scene information of the target public building, extracting the functional characteristics according to the AR scene information, splitting the target public building according to the functional characteristics, and dividing it into several scene sub-areas; Installing energy consumption monitoring points in several scene sub-areas to obtain personnel data and power consumption data in different scene sub-areas, marking the collection time, and setting the monitoring period; The personnel data includes personnel video stream data and personnel location information; The process by which the data processing module obtains the pedestrian flow data in each area according to the personnel data of each area in the target public building includes: Obtaining the video stream data of the personnel in the scene sub-area, converting the video stream data into continuous video frame images, obtaining the skeletal point position data of the personnel in multiple video frame images through the OpenPose algorithm, obtaining the skeletal data of the personnel according to the skeletal point position data, converting the skeletal data in multiple video frame images into a continuous skeletal action sequence, generating the action information of the personnel according to the skeletal action sequence, and generating the action trajectory of the personnel according to the action information of the personnel; Obtaining the exit position and entrance position of each scene sub-area, setting a preset distance, selecting a target scene sub-area, obtaining the target personnel in the target scene sub-area whose action trajectory direction is the exit position of the target scene sub-area, obtaining the distance between the target personnel and the exit position according to the position information of the target personnel, comparing the distance with the preset distance, and when the distance is less than or equal to the preset distance, marking the target personnel as valid personnel, and when the distance is greater than the preset distance, marking the target personnel as pre-departing personnel; At the same time, select the target personnel with the action trajectory direction in other scene sub-regions adjacent to the target scene sub-region as the entrance position of the target scene sub-region, obtain the distance between the target personnel and the entrance position according to the position information of the target personnel, compare the distance with a preset distance, and when the distance is greater than the preset distance, mark the target personnel as pre-entering personnel; At the same time, mark the personnel whose trajectory direction in the target scene sub-region is not the entrance position of the target scene sub-region as valid personnel; Obtain the number of valid personnel, the number of pre-entering personnel, and the number of pre-leaving personnel, obtain the sum of the number of valid personnel and the number of pre-entering personnel, obtain the value obtained by subtracting the number of pre-leaving personnel from the sum of the number of valid personnel and the number of pre-entering personnel, and mark the value as the pedestrian flow data; The process in which the data visualization module constructs a scene area layer, a real-time data layer, and a prediction data layer for the target public building and obtains the integrated visual diagram of regional energy monitoring based on the scene area layer, the real-time data layer, and the prediction data layer includes: Construct a digital twin virtual space, obtain the structural dimension diagram of the target public building and the position information of several scene sub-regions, construct a three-dimensional model of the public building according to the structural dimension diagram of the target public building and map it into the digital twin virtual space, and divide the three-dimensional model into several three-dimensional models of scene sub-regions according to the position information of several scene sub-regions to obtain the scene area layer; Obtain the pedestrian flow data and power consumption data of the energy consumption monitoring points in each scene sub-region, and perform data preprocessing to generate pedestrian flow twin data and power consumption twin data, and match the pedestrian flow twin data and power consumption twin data with several three-dimensional models of scene sub-regions in the basic scene layer to obtain the real-time data layer; Construct a pedestrian flow and power consumption prediction model according to the historical pedestrian flow data and historical power consumption data stored in the data storage module for each scene sub-region, obtain the pedestrian flow prediction data and power consumption prediction data for each time period in the current monitoring cycle of each scene sub-region according to the pedestrian flow and power consumption prediction model, perform data format preprocessing on the pedestrian flow prediction data and power consumption prediction data, convert them into pedestrian flow prediction twin data and power consumption prediction twin data, and match them with several three-dimensional models of scene sub-regions in the basic scene layer to obtain the prediction data layer; Taking the scene area layer as the basic layer, overlay the real-time data layer and the prediction data layer on the scene area layer to obtain the integrated visual diagram of regional energy monitoring.

2. The regional energy monitoring system based on big data according to claim 1, characterized in that The process in which the prediction data layer constructs a pedestrian flow and power consumption prediction model according to the historical pedestrian flow data and historical power consumption data stored in the data storage module for each scene sub-region includes: The predicted data layer is communicatively connected to the data storage module. A historical dataset is constructed based on the pedestrian flow data and power consumption data at each moment of each day in each month of the previous year for each scenario sub-region in the data storage module. The pedestrian flow and power consumption prediction model is trained in real time through dividing the historical dataset into a training set and a test set until the loss function is stably trained, and the model parameters are saved. The pedestrian flow and power consumption prediction model is tested through the test set until it meets the preset requirements, and the pedestrian flow and power consumption prediction model is outputted. The input layer of the pedestrian flow and power consumption prediction model is the historical pedestrian data and historical power consumption data within the historical monitoring period. The output layer of the pedestrian flow and power consumption prediction model is the predicted pedestrian flow data and predicted power consumption data for each time period within the current monitoring period.

3. A regional energy monitoring system based on big data according to claim 2, characterized in that, The process by which the air conditioning system control module obtains the execution standard data and inspection standard data for different time periods in each area and obtains the output power of the air conditioning system in different time periods in each area according to the execution standard data for each time period includes: Obtain the predicted pedestrian flow data and predicted power consumption data for each time period within the current monitoring period of the scenario sub-region according to the pedestrian flow and power consumption prediction model. Use the predicted pedestrian flow data as the execution standard data and the predicted power consumption data as the inspection standard data. Obtain the historical output power of the air conditioning system in each scenario sub-region under different execution standard data for each time period through the data storage module. Select the historical output power of the air conditioning system with the highest similarity to the execution standard data of the current time period of the scenario sub-region as the output power of the air conditioning system in the current time period of the scenario sub-region.

4. A regional energy monitoring system based on big data according to claim 3, characterized in that, The process by which the real-time data layer is used to compare the real-time data with the execution standard data and inspection standard data to monitor the state of the air conditioning system in real time includes: Compare the pedestrian flow data of the current scenario sub-region obtained by the data processing module with the execution standard data, obtain the execution standard deviation value between the pedestrian flow data and the execution standard data, and set the execution standard deviation threshold. If the execution standard deviation value is greater than the execution standard deviation threshold, update the execution standard data and inspection standard data of the current monitoring period. If the execution standard deviation value is less than or equal to the execution standard deviation threshold, obtain the inspection standard deviation value between the power consumption data collected by the energy consumption monitoring point of the current scenario sub-region and the inspection standard data, and set the inspection standard deviation threshold. If the inspection standard deviation value is less than or equal to the inspection standard deviation threshold, mark the air conditioning system of the current scenario sub-region as normal. If the inspection standard deviation value is greater than the inspection standard deviation threshold, mark the air conditioning system of the current scenario sub-region as a fault state and generate a fault alarm to send to the monitoring center.

5. The regional energy monitoring system based on big data according to claim 4, characterized in that, The process by which the real-time data layer updates the execution standard data and inspection standard data of the current monitoring period when the execution standard deviation value is greater than the execution standard deviation threshold includes: Input the personnel data and power consumption data collected during the current monitoring period into the prediction model of pedestrian flow and power consumption. Take the predicted pedestrian flow data and predicted power consumption data for each time period during the current monitoring period output by the prediction model of pedestrian flow and power consumption as the new execution standard data and inspection standard data.

Images