IBMS system terminal based on Internet of Things technology

Abstract

The invention relates to intelligent building management, in particular to an IBMS system terminal and equipment layer based on the Internet of Things technology, which comprises front-end equipment of each subsystem of a building site, distributed wireless sensors for collecting monitoring data in a building in real time based on the Internet of Things technology, and distributed image collection equipment for collecting image data in the building in real time; the platform layer is used for performing data integration on data sent by the distributed wireless sensor and the distributed image acquisition equipment, timely finding potential problems by performing data analysis on monitoring data in the building, and obtaining personnel distribution conditions in the building by performing data analysis on image data in the building; decision support is provided for a user based on a monitoring data analysis result in the building, and an air conditioning system and a lighting system in the equipment layer are optimized and controlled based on an image data analysis result in the building; according to the technical scheme provided by the invention, the defect that the power of each sub-air-conditioning equipment in the air-conditioning system is difficult to effectively regulate and control can be overcome.

Description

Technical Field

[0001] The present invention relates to intelligent building management, and in particular to an IBMS system terminal based on Internet of Things technology. Background Art

[0002] Green and low-carbon buildings refer to buildings that reduce the use of fossil energy, improve energy efficiency, and reduce carbon dioxide emissions throughout the entire life cycle of building material manufacturing, equipment manufacturing, construction, and building use. Green and low-carbon buildings emphasize the conservation and recycling of resources, reduce environmental pollution and carbon emissions, and at the same time improve the comfort and energy efficiency of buildings, and achieve harmonious coexistence between man and nature. This is one of the development trends of future urban buildings. In recent years, the integration and application of technologies such as the Internet of Things and artificial intelligence with high-rise buildings has gradually increased, among which the "smart Internet of Things" is the most representative, and its impact on the smart building industry is also gradually deepening, becoming one of the key application technologies in today's smart building industry.

[0003] The air conditioning system is one of the most important and energy-intensive equipment in a building. Its operating status will directly affect the energy-saving effect and user experience of the building. Therefore, effective monitoring and management of the air conditioning system is a key factor in improving the energy efficiency of buildings. However, the air conditioning system in a building is usually composed of multiple components, and its operating status is affected by many factors. How to effectively regulate the power of each sub-air conditioning device in the air conditioning system has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides an IBMS system terminal based on Internet of Things technology, which can effectively overcome the defect of the prior art that it is difficult to effectively regulate the power of each sub-air-conditioning equipment in the air-conditioning system.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] An IBMS system terminal based on Internet of Things technology, comprising a device layer, an access layer and a platform layer;

[0009] The equipment layer is the foundation of the IBMS system, including the front-end equipment of each subsystem on the building site, distributed wireless sensors that collect monitoring data in the building in real time based on the Internet of Things technology, and distributed image acquisition equipment that collects image data in the building in real time;

[0010] The access layer is the communication bridge between the device layer and the platform layer, including distributed base stations that receive and transmit data sent by distributed wireless sensors and distributed image acquisition devices, as well as data interfaces provided to the platform layer;

[0011] The platform layer, the core of the IBMS system, integrates the data sent by distributed wireless sensors and distributed image acquisition devices, uses the monitoring data in the building for real-time monitoring, and promptly discovers potential problems by analyzing the monitoring data in the building. It obtains the distribution of people in the building by analyzing the image data in the building, provides decision support to users based on the analysis results of the monitoring data in the building, and optimizes the control of the air-conditioning system and lighting system in the equipment layer based on the analysis results of the image data in the building.

[0012] Preferably, the communication mode of the communication network constructed among the distributed wireless sensors, the distributed image acquisition devices and the distributed base stations includes:

[0013] In normal communication mode, the distributed base station sends its own location information to all surrounding data collection nodes. The data collection node takes the nearest distributed base station as the target base station and sends its own collected data to the target base station. At the same time, the distributed base station calculates its own operating status value in real time and enters the emergency communication mode when the operating status is abnormal.

[0014] In the emergency communication mode, a distributed base station with an abnormal operating status sends an emergency communication instruction to all surrounding data acquisition nodes. The data acquisition nodes that establish a communication connection with the distributed base station with an abnormal operating status adaptively select other surrounding data acquisition nodes as target communication nodes and send their own collected data to the target communication nodes.

[0015] Preferably, the distributed base station calculates its own operating status value in real time and enters the emergency communication mode when an abnormality occurs in the operating status, including:

[0016] The following formula is used to calculate the running status value in real time:

[0017] S(t)=f1(PLR)+f2(PLR,DTR,HS);

[0018] Among them, S(t) is the running status value at time t, PLR represents packet loss rate, PLR' represents standard packet loss rate, DTR represents transmission rate, DTR' represents standard transmission rate, HS represents hardware status, when hardware abnormality occurs, HS = 1, otherwise HS = 0, ω1, ω2, ω3 are the weights of packet loss rate, transmission rate, and hardware status respectively;

[0019] When the operating status value of a distributed base station is not less than 1 for p consecutive moments, the operating status of the distributed base station is abnormal and enters the emergency communication mode.

[0020] Preferably, the data collection node establishing a communication connection with the distributed base station in which the operation state is abnormally abnormal adaptively selects other surrounding data collection nodes as target communication nodes, and sends its own collected data to the target communication nodes, including:

[0021] The data collection node that receives the emergency communication command calculates its own node status value and broadcasts its own node status value to all surrounding data collection nodes;

[0022] The data collection node that receives the emergency communication command randomly selects one from the three maximum node status values ​​received, takes the corresponding data collection node as the target communication node, and sends its own collected data to the target communication node.

[0023] Preferably, the data analysis of the image data in the building is performed to obtain the distribution of people in the building, and the air conditioning system and the lighting system in the equipment layer are optimized and controlled based on the analysis results of the image data in the building, including:

[0024] S1. Perform human body detection on all image data collected at the same time in the building, count the number of people in each image, and obtain the distribution of people in the building by combining the location information of the distributed image acquisition device corresponding to the image acquisition;

[0025] S2. Construct an air-conditioning system power prediction model, input the distribution of people in the building into the trained air-conditioning system power prediction model, and obtain the power prediction results of each sub-air-conditioning equipment in the air-conditioning system;

[0026] S3, determining the objective function of the power control of the air-conditioning system and the corresponding constraints, constructing the power control model of the air-conditioning system according to the objective function and constraints of the power control of the air-conditioning system, and performing multi-objective optimization on the power control model of the air-conditioning system to obtain the power control scheme of each sub-air-conditioning equipment in the air-conditioning system;

[0027] Among them, in the process of multi-objective optimization solution of the air-conditioning system power control model, the power prediction results of each sub-air-conditioning equipment in the air-conditioning system output by the air-conditioning system power prediction model are introduced to set the initial position, so as to realize the dynamic coupling of the neural network and the multi-objective optimization algorithm.

[0028] Preferably, before constructing an air-conditioning system power prediction model in S2, inputting the distribution of people in the building into the trained air-conditioning system power prediction model, and obtaining the power prediction results of each sub-air-conditioning device in the air-conditioning system, the following steps are included:

[0029] S21, dividing the historical data set into a training set, a validation set, and a test set according to a preset ratio;

[0030] S22, setting the loss function and optimizer of the air conditioning system power prediction model, and inputting the training set into the air conditioning system power prediction model for model training;

[0031] S23, calculating the loss value based on the loss function, and the optimizer updates the model parameters according to the loss value and the network gradient information;

[0032] S24. If the loss value is less than the preset threshold, the model training ends, and the current air-conditioning system power prediction model is the trained air-conditioning system power prediction model. Otherwise, the process returns to S22 and continues to use the training set for model training.

[0033] S25. Input the validation set into the trained air conditioning system power prediction model, evaluate the generalization ability of the model by observing the performance on the validation set, and tune the hyperparameters and structure of the model;

[0034] S26, inputting the test set into the optimized air conditioning system power prediction model to evaluate the model performance;

[0035] Among them, the air-conditioning system power prediction model is built based on the long short-term memory network LSTM.

[0036] Preferably, in S21, the historical data set is divided into a training set, a validation set and a test set according to a preset ratio, including:

[0037] S211, collecting the distribution of people in the building at each time in the historical time period, and the historical power of each sub-air-conditioning equipment in the corresponding air-conditioning system;

[0038] S212. Label the distribution of people in the building at each time according to the historical power of each sub-air-conditioning device in the air-conditioning system to form a historical data set.

[0039] Preferably, in S3, the objective function of the power control of the air-conditioning system and the corresponding constraints are determined, a power control model of the air-conditioning system is constructed according to the objective function and the constraints of the power control of the air-conditioning system, and a multi-objective optimization solution is performed on the power control model of the air-conditioning system to obtain a power control scheme for each sub-air-conditioning device in the air-conditioning system, including:

[0040] S31, taking the minimum energy consumption of the air-conditioning system, the highest user satisfaction and the lowest cost of air-conditioning system transformation as the multi-objective function of air-conditioning system power control;

[0041] S32, determining the minimum power of each sub-air conditioning device in the air conditioning system according to the distribution of people in the building, and obtaining the constraint condition in combination with the rated maximum power of each sub-air conditioning device in the air conditioning system;

[0042] S33, constructing an air conditioning system power control model according to the objective function and constraint conditions of the air conditioning system power control;

[0043] S34. The White Whale Optimization Algorithm (MOWSO) is used to perform multi-objective optimization on the multi-objective function of the power control of the air-conditioning system, and a power control scheme for each sub-air-conditioning equipment in the air-conditioning system that meets the constraint conditions is obtained.

[0044] Preferably, in S34, the White Whale Optimization Algorithm MOWSO is used to perform multi-objective optimization on the multi-objective function of the power control of the air-conditioning system to obtain a power control scheme for each sub-air-conditioning device in the air-conditioning system that meets the constraint conditions, including:

[0045] S341, randomly generate a certain number of beluga individuals to form an initial population, and initialize parameters;

[0046] S342, setting the initial position of each beluga individual in the initial population according to the power prediction result of each sub-air conditioning device in the air conditioning system output by the air conditioning system power prediction model;

[0047] S343, calculating the balance factor, and judging whether to enter global exploration or local development according to the balance factor, if entering global exploration, then entering S344; if entering local development, then entering S345;

[0048] S344, in the global exploration, the swimming behavior of the beluga whale is simulated, and different position update strategies are adopted according to the parity of the current position of the individual beluga whale to search the solution space in the global scope, increase the population diversity, and enter S346;

[0049] S345. In local development, the behavior of beluga whales in hunting by sharing location information is simulated, and individual beluga whales cooperate in foraging based on the location movement of surrounding beluga whales to update their positions;

[0050] S346. During each iteration, a portion of beluga individuals are randomly selected from the population to reset their positions or move randomly to simulate the behavior of whales falling;

[0051] S347, calculating the fitness values ​​of all beluga individuals according to the objective function, and updating the global optimal solution according to the fitness values;

[0052] S348, judging whether the iteration termination condition is satisfied, if not, returning to S343, otherwise taking the current global optimal solution as the power control scheme for each sub-air-conditioning device in the air-conditioning system that satisfies the constraint condition.

[0053] Preferably, calculating the balance factor in S343 and determining whether to enter global exploration or local development according to the balance factor include:

[0054] The balance factor B is calculated using the following formula:

[0055]

[0056] Among them, r is a random number that changes in each iteration, r∈[0,1], k is the current iteration number, k max is the maximum number of iterations;

[0057] When B>0.5, enter global exploration; when B≤0.5, enter local development;

[0058] S344. In global exploration, the swimming behavior of beluga whales is simulated, and different position update strategies are adopted according to the parity of the current position of individual beluga whales to search the solution space in a global scope and increase the diversity of the population, including:

[0059] Use the following formula to update the location:

[0060]

[0061] in, is the position of beluga individual i in dimension m at the kth iteration, is the new position of beluga individual i in dimension j at the k+1th iteration, is the position of the randomly selected beluga individual R in the n dimension at the kth iteration, r1 and r2 are random numbers, r1, r2∈[0,1];

[0062] S345. In local development, the beluga whales are simulated to hunt by sharing their location information. Individual beluga whales cooperate to forage based on the location movement of surrounding beluga whales to update their location, including:

[0063] The following formula is used to update the location:

[0064]

[0065] in, is the position of beluga individual i at the kth iteration, is the new position of beluga individual i at the k+1th iteration, is the global optimal position at the kth iteration, is the position of the randomly selected beluga individual R at the kth iteration, L F is the Levy flight step length, r3 and r4 are random numbers, r3, r4∈[0,1].

[0066] (III) Beneficial effects

[0067] Compared with the prior art, the IBMS system terminal based on the Internet of Things technology provided by the present invention has the following beneficial effects:

[0068] 1) An emergency communication mechanism is introduced into the communication network constructed between distributed wireless sensors, distributed image acquisition devices and distributed base stations to ensure that the platform layer can effectively receive the data sent by distributed wireless sensors and distributed image acquisition devices, provide data support for real-time monitoring, data analysis and optimization control of the air conditioning system and lighting system in the equipment layer based on the image data analysis results in the building, and ensure the normal operation of the system;

[0069] 2) Aiming at the power control problem of each sub-air-conditioning equipment in the air-conditioning system in the building, the multi-objective function and constraint conditions of the air-conditioning system power control are determined, and the power control model of the air-conditioning system is constructed. The multi-objective optimization function of the air-conditioning system power control is solved by the White Whale Optimization Algorithm MOWSO, and the power control scheme of each sub-air-conditioning equipment in the air-conditioning system that meets the constraint conditions is obtained. At the same time, in the process of multi-objective optimization solution of the air-conditioning system power control model, the power prediction results of each sub-air-conditioning equipment in the air-conditioning system output by the air-conditioning system power prediction model are introduced to set the initial position, realizing the dynamic coupling of the neural network and the multi-objective optimization algorithm, which effectively improves the efficiency of the multi-objective optimization solution, so that the power control scheme of each sub-air-conditioning equipment in the air-conditioning system can be obtained quickly and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0071] Figure 1 It is a schematic diagram of the system of the present invention;

[0072] Figure 2 A schematic diagram of the working process of the communication network constructed between the distributed wireless sensors, the distributed image acquisition devices and the distributed base stations in the present invention;

[0073] Figure 3 It is a schematic diagram of the process of optimizing the control of the air conditioning system in the equipment layer based on the analysis results of the image data in the building in the present invention. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] An IBMS system terminal based on Internet of Things technology, such as Figure 1 As shown, it includes device layer, access layer and platform layer;

[0076] The equipment layer is the foundation of the IBMS system, including the front-end equipment of each subsystem on the building site, distributed wireless sensors that collect monitoring data in the building in real time based on the Internet of Things technology, and distributed image acquisition equipment that collects image data in the building in real time;

[0077] The access layer is the communication bridge between the device layer and the platform layer, including distributed base stations that receive and transmit data sent by distributed wireless sensors and distributed image acquisition devices, as well as data interfaces provided to the platform layer;

[0078] The platform layer, the core of the IBMS system, integrates the data sent by distributed wireless sensors and distributed image acquisition devices, uses the monitoring data in the building for real-time monitoring, and promptly discovers potential problems by analyzing the monitoring data in the building. It obtains the distribution of people in the building by analyzing the image data in the building, provides decision support to users based on the analysis results of the monitoring data in the building, and optimizes the control of the air-conditioning system and lighting system in the equipment layer based on the analysis results of the image data in the building.

[0079] The communication mode of the communication network constructed between distributed wireless sensors, distributed image acquisition devices and distributed base stations, such as Figure 2 As shown, including:

[0080] In normal communication mode, the distributed base station sends its own location information to all surrounding data collection nodes. The data collection node takes the nearest distributed base station as the target base station and sends its own collected data to the target base station. At the same time, the distributed base station calculates its own operating status value in real time and enters the emergency communication mode when the operating status is abnormal.

[0081] In the emergency communication mode, a distributed base station with an abnormal operating status sends an emergency communication instruction to all surrounding data acquisition nodes. The data acquisition nodes that establish a communication connection with the distributed base station with an abnormal operating status adaptively select other surrounding data acquisition nodes as target communication nodes and send their own collected data to the target communication nodes.

[0082] 1) In normal communication mode, the distributed base station calculates its own operating status value in real time and enters emergency communication mode when the operating status is abnormal, including:

[0083] The following formula is used to calculate the running status value in real time:

[0084] S(t)=f1(PLR)+f2(PLR,DTR,HS);

[0085] Among them, S(t) is the running status value at time t, PLR represents packet loss rate, PLR' represents standard packet loss rate, DTR represents transmission rate, DTR' represents standard transmission rate, HS represents hardware status, when hardware abnormality occurs, HS = 1, otherwise HS = 0, ω1, ω2, ω3 are the weights of packet loss rate, transmission rate, and hardware status respectively;

[0086] When the operating status value of a distributed base station is not less than 1 for p consecutive moments, the operating status of the distributed base station is abnormal and enters the emergency communication mode.

[0087] 2) In the emergency communication mode, the data collection node that establishes a communication connection with the distributed base station whose operation status is abnormally abnormal adaptively selects other surrounding data collection nodes as target communication nodes, and sends its own collected data to the target communication nodes, including:

[0088] The data collection node that receives the emergency communication command calculates its own node status value and broadcasts its own node status value to all surrounding data collection nodes;

[0089] The data collection node that receives the emergency communication command randomly selects one from the three maximum node status values ​​received, takes the corresponding data collection node as the target communication node, and sends its own collected data to the target communication node.

[0090] The above technical solution introduces an emergency communication mechanism in the communication network constructed between distributed wireless sensors, distributed image acquisition devices and distributed base stations, ensuring that the platform layer can effectively receive data sent by distributed wireless sensors and distributed image acquisition devices, and provide data support for real-time monitoring, data analysis and optimization control of the air-conditioning system and lighting system in the equipment layer based on the image data analysis results in the building, thereby ensuring the normal operation of the system.

[0091] By analyzing the image data in the building, the distribution of people in the building can be obtained, and the air conditioning system and lighting system in the equipment layer can be optimized and controlled based on the analysis results of the image data in the building. Figure 3 As shown, including:

[0092] S1. Perform human body detection on all image data collected at the same time in the building, count the number of people in each image, and obtain the distribution of people in the building by combining the location information of the distributed image acquisition device corresponding to the image acquisition;

[0093] S2. Construct an air-conditioning system power prediction model, input the distribution of people in the building into the trained air-conditioning system power prediction model, and obtain the power prediction results of each sub-air-conditioning equipment in the air-conditioning system;

[0094] S3, determining the objective function of the power control of the air-conditioning system and the corresponding constraints, constructing the power control model of the air-conditioning system according to the objective function and constraints of the power control of the air-conditioning system, and performing multi-objective optimization on the power control model of the air-conditioning system to obtain the power control scheme of each sub-air-conditioning equipment in the air-conditioning system;

[0095] Among them, in the process of multi-objective optimization solution of the air-conditioning system power control model, the power prediction results of each sub-air-conditioning equipment in the air-conditioning system output by the air-conditioning system power prediction model are introduced to set the initial position, so as to realize the dynamic coupling of the neural network and the multi-objective optimization algorithm.

[0096] It is worth noting that in the technical solution of this application, when using distributed image acquisition equipment to collect image data in a building, it should be noted that the distributed image acquisition equipment should be installed in a suitable position to protect the privacy of personnel. In addition to obtaining the distribution of personnel in a building by collecting image data in the building, wireless radio frequency identification technology, indoor Bluetooth positioning technology, etc. can also be used to achieve the same purpose.

[0097] 1) In S2, an air conditioning system power prediction model is constructed, and the distribution of people in the building is input into the trained air conditioning system power prediction model to obtain the power prediction results of each sub-air conditioning equipment in the air conditioning system, including:

[0098] S21, dividing the historical data set into a training set, a validation set, and a test set according to a preset ratio;

[0099] S22, setting the loss function and optimizer of the air conditioning system power prediction model, and inputting the training set into the air conditioning system power prediction model for model training;

[0100] S23, calculating the loss value based on the loss function, and the optimizer updates the model parameters according to the loss value and the network gradient information;

[0101] S24. If the loss value is less than the preset threshold, the model training ends, and the current air-conditioning system power prediction model is the trained air-conditioning system power prediction model. Otherwise, the process returns to S22 and continues to use the training set for model training.

[0102] S25. Input the validation set into the trained air conditioning system power prediction model, evaluate the generalization ability of the model by observing the performance on the validation set, and tune the hyperparameters and structure of the model;

[0103] S26, inputting the test set into the optimized air conditioning system power prediction model to evaluate the model performance;

[0104] Among them, the air-conditioning system power prediction model is built based on the long short-term memory network LSTM.

[0105] Specifically, in S21, the historical data set is divided into a training set, a validation set, and a test set according to a preset ratio, including:

[0106] S211, collecting the distribution of people in the building at each time in the historical time period, and the historical power of each sub-air-conditioning equipment in the corresponding air-conditioning system;

[0107] S212. Label the distribution of people in the building at each time according to the historical power of each sub-air-conditioning device in the air-conditioning system to form a historical data set.

[0108] 2) In S3, the objective function of the power control of the air-conditioning system and the corresponding constraints are determined. According to the objective function and constraints of the power control of the air-conditioning system, the power control model of the air-conditioning system is constructed, and the power control model of the air-conditioning system is solved by multi-objective optimization to obtain the power control scheme of each sub-air-conditioning equipment in the air-conditioning system, including:

[0109] S31, taking the minimum energy consumption of the air-conditioning system, the highest user satisfaction and the lowest cost of air-conditioning system transformation as the multi-objective function of air-conditioning system power control;

[0110] S32, determining the minimum power of each sub-air conditioning device in the air conditioning system according to the distribution of people in the building, and obtaining the constraint condition in combination with the rated maximum power of each sub-air conditioning device in the air conditioning system;

[0111] S33, constructing an air conditioning system power control model according to the objective function and constraint conditions of the air conditioning system power control;

[0112] S34. The White Whale Optimization Algorithm (MOWSO) is used to perform multi-objective optimization on the multi-objective function of the air-conditioning system power control, and a power control scheme for each sub-air-conditioning equipment in the air-conditioning system that meets the constraint conditions is obtained.

[0113] Specifically, in S34, the White Whale Optimization Algorithm MOWSO is used to perform multi-objective optimization on the multi-objective function of the air-conditioning system power control, and the power control scheme of each sub-air-conditioning equipment in the air-conditioning system that meets the constraint conditions is obtained, including:

[0114] S341, randomly generate a certain number of beluga individuals to form an initial population, and initialize parameters;

[0115] S342, setting the initial position of each beluga individual in the initial population according to the power prediction result of each sub-air conditioning device in the air conditioning system output by the air conditioning system power prediction model;

[0116] S343, calculating the balance factor, and judging whether to enter global exploration or local development according to the balance factor, if entering global exploration, then entering S344; if entering local development, then entering S345;

[0117] S344, in the global exploration, the swimming behavior of the beluga whale is simulated, and different position update strategies are adopted according to the parity of the current position of the individual beluga whale to search the solution space in the global scope, increase the population diversity, and enter S346;

[0118] S345. In local development, the behavior of beluga whales in hunting by sharing location information is simulated, and individual beluga whales cooperate in foraging based on the location movement of surrounding beluga whales to update their positions;

[0119] S346. During each iteration, a portion of beluga individuals are randomly selected from the population to reset their positions or move randomly to simulate the behavior of whales falling;

[0120] S347, calculating the fitness values ​​of all beluga individuals according to the objective function, and updating the global optimal solution according to the fitness values;

[0121] S348, judging whether the iteration termination condition is satisfied, if not, returning to S343, otherwise taking the current global optimal solution as the power control scheme for each sub-air-conditioning device in the air-conditioning system that satisfies the constraint condition.

[0122] Specifically, the balance factor is calculated in S343, and global exploration or local development is determined based on the balance factor, including:

[0123] The balance factor B is calculated using the following formula:

[0124]

[0125] Among them, r is a random number that changes in each iteration, r∈[0,1], k is the current iteration number, k max is the maximum number of iterations;

[0126] When B>0.5, enter global exploration; when B≤0.5, enter local development.

[0127] Specifically, S344, in the global exploration, the swimming behavior of the beluga whale is simulated, and different position update strategies are adopted according to the parity of the current position of the individual beluga whales to search the solution space in a global scope and increase the population diversity, including:

[0128] The following formula is used to update the location:

[0129]

[0130] in, is the position of beluga individual i in dimension m at the kth iteration, is the new position of beluga individual i in dimension j at the k+1th iteration, is the position of the randomly selected beluga individual R in the n dimension at the kth iteration, r1 and r2 are random numbers, r1, r2∈[0,1].

[0131] Specifically, S345, in local development, the beluga whales are simulated to hunt by sharing location information, and individual beluga whales cooperate to forage according to the location movement of surrounding beluga whales to update their locations, including:

[0132] The following formula is used to update the location:

[0133]

[0134] in, is the position of beluga individual i at the kth iteration, is the new position of beluga individual i at the k+1th iteration, is the global optimal position at the kth iteration, is the position of the randomly selected beluga individual R at the kth iteration, L F is the Levy flight step length, r3 and r4 are random numbers, r3, r4∈[0,1].

[0135] The above technical scheme aims at the power control problem of each sub-air-conditioning equipment in the air-conditioning system in the building, determines the multi-objective function and constraints of the power control of the air-conditioning system, and constructs the power control model of the air-conditioning system. The White Whale Optimization Algorithm MOWSO is used to perform multi-objective optimization solution on the multi-objective function of the power control of the air-conditioning system, and obtains the power control scheme of each sub-air-conditioning equipment in the air-conditioning system that meets the constraints. At the same time, in the process of multi-objective optimization solution of the power control model of the air-conditioning system, the power prediction results of each sub-air-conditioning equipment in the air-conditioning system output by the power prediction model of the air-conditioning system are introduced to set the initial position, so as to realize the dynamic coupling of the neural network and the multi-objective optimization algorithm, and effectively improve the efficiency of the multi-objective optimization solution, so as to quickly and accurately obtain the power control scheme of each sub-air-conditioning equipment in the air-conditioning system.

[0136] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An IBMS system terminal based on Internet of Things technology, characterized in that: Includes device layer, access layer and platform layer; The equipment layer is the foundation of the IBMS system, including the front-end equipment of each subsystem on the building site, distributed wireless sensors that collect monitoring data in the building in real time based on the Internet of Things technology, and distributed image acquisition equipment that collects image data in the building in real time; The access layer is the communication bridge between the device layer and the platform layer, including distributed base stations that receive and transmit data sent by distributed wireless sensors and distributed image acquisition devices, as well as data interfaces provided to the platform layer; The platform layer, the core of the IBMS system, integrates the data sent by distributed wireless sensors and distributed image acquisition devices, uses the monitoring data in the building for real-time monitoring, and promptly discovers potential problems by analyzing the monitoring data in the building. It obtains the distribution of people in the building by analyzing the image data in the building, provides decision support to users based on the analysis results of the monitoring data in the building, and optimizes the control of the air-conditioning system and lighting system in the equipment layer based on the analysis results of the image data in the building.

2. The IBMS system terminal based on Internet of Things technology according to claim 1, characterized in that: The communication mode of the communication network constructed between the distributed wireless sensors, the distributed image acquisition devices and the distributed base stations includes: In normal communication mode, the distributed base station sends its own location information to all surrounding data collection nodes. The data collection node takes the nearest distributed base station as the target base station and sends its own collected data to the target base station. At the same time, the distributed base station calculates its own operating status value in real time and enters the emergency communication mode when the operating status is abnormal. In the emergency communication mode, a distributed base station with an abnormal operating status sends an emergency communication instruction to all surrounding data acquisition nodes. The data acquisition nodes that establish a communication connection with the distributed base station with an abnormal operating status adaptively select other surrounding data acquisition nodes as target communication nodes and send their own collected data to the target communication nodes.

3. The IBMS system terminal based on Internet of Things technology according to claim 2, characterized in that: The distributed base station calculates its own operating status value in real time and enters the emergency communication mode when an abnormality occurs in the operating status, including: The following formula is used to calculate the running status value in real time: S(t)=f1(PLR)+f2(PLR,DTR,HS); Among them, S(t) is the running status value at time t, PLR represents packet loss rate, PLR' represents standard packet loss rate, DTR represents transmission rate, DTR' represents standard transmission rate, HS represents hardware status, when hardware abnormality occurs, HS = 1, otherwise HS = 0, ω1, ω2, ω3 are the weights of packet loss rate, transmission rate, and hardware status respectively; When the operating status value of a distributed base station is not less than 1 for p consecutive moments, the operating status of the distributed base station is abnormal and enters the emergency communication mode.

4. The IBMS system terminal based on Internet of Things technology according to claim 2, characterized in that: The data collection node that establishes a communication connection with the distributed base station whose operation state is abnormally abnormal adaptively selects other surrounding data collection nodes as target communication nodes, and sends its own collected data to the target communication nodes, including: The data collection node that receives the emergency communication command calculates its own node status value and broadcasts its own node status value to all surrounding data collection nodes; The data collection node that receives the emergency communication command randomly selects one from the three maximum node status values ​​received, takes the corresponding data collection node as the target communication node, and sends its own collected data to the target communication node.

5. The IBMS system terminal based on Internet of Things technology according to claim 1, characterized in that: The data analysis of the image data in the building is performed to obtain the distribution of people in the building, and the air conditioning system and the lighting system in the equipment layer are optimized and controlled based on the analysis results of the image data in the building, including: S1. Perform human body detection on all image data collected at the same time in the building, count the number of people in each image, and obtain the distribution of people in the building by combining the location information of the distributed image acquisition device corresponding to the image acquisition; S2. Construct an air-conditioning system power prediction model, input the distribution of people in the building into the trained air-conditioning system power prediction model, and obtain the power prediction results of each sub-air-conditioning equipment in the air-conditioning system; S3, determining the objective function of the power control of the air-conditioning system and the corresponding constraints, constructing the power control model of the air-conditioning system according to the objective function and constraints of the power control of the air-conditioning system, and performing multi-objective optimization on the power control model of the air-conditioning system to obtain the power control scheme of each sub-air-conditioning equipment in the air-conditioning system; Among them, in the process of multi-objective optimization solution of the air-conditioning system power control model, the power prediction results of each sub-air-conditioning equipment in the air-conditioning system output by the air-conditioning system power prediction model are introduced to set the initial position, so as to realize the dynamic coupling of the neural network and the multi-objective optimization algorithm.

6. The IBMS system terminal based on Internet of Things technology according to claim 5, characterized in that: In S2, the power prediction model of the air-conditioning system is constructed, and the distribution of people in the building is input into the trained power prediction model of the air-conditioning system to obtain the power prediction results of each sub-air-conditioning equipment in the air-conditioning system, including: S21, dividing the historical data set into a training set, a validation set, and a test set according to a preset ratio; S22, setting the loss function and optimizer of the air conditioning system power prediction model, and inputting the training set into the air conditioning system power prediction model for model training; S23, calculating the loss value based on the loss function, and the optimizer updates the model parameters according to the loss value and the network gradient information; S24. If the loss value is less than the preset threshold, the model training ends, and the current air-conditioning system power prediction model is the trained air-conditioning system power prediction model. Otherwise, the process returns to S22 and continues to use the training set for model training. S25. Input the validation set into the trained air conditioning system power prediction model, evaluate the generalization ability of the model by observing the performance on the validation set, and tune the hyperparameters and structure of the model; S26, inputting the test set into the optimized air conditioning system power prediction model to evaluate the model performance; Among them, the air-conditioning system power prediction model is built based on the long short-term memory network LSTM.

7. The IBMS system terminal based on Internet of Things technology according to claim 6, characterized in that: In S21, the historical data set is divided into a training set, a validation set, and a test set according to a preset ratio, including: S211, collecting the distribution of people in the building at each time in the historical time period, and the historical power of each sub-air-conditioning equipment in the corresponding air-conditioning system; S212. Label the distribution of people in the building at each time according to the historical power of each sub-air-conditioning device in the air-conditioning system to form a historical data set.

8. The IBMS system terminal based on Internet of Things technology according to claim 5, characterized in that: In S3, the objective function of the power control of the air-conditioning system and the corresponding constraints are determined. According to the objective function and constraints of the power control of the air-conditioning system, the power control model of the air-conditioning system is constructed, and the power control model of the air-conditioning system is solved by multi-objective optimization to obtain the power control scheme of each sub-air-conditioning equipment in the air-conditioning system, including: S31, taking the minimum energy consumption of the air-conditioning system, the highest user satisfaction and the lowest cost of air-conditioning system transformation as the multi-objective function of air-conditioning system power control; S32, determining the minimum power of each sub-air conditioning device in the air conditioning system according to the distribution of people in the building, and obtaining the constraint condition in combination with the rated maximum power of each sub-air conditioning device in the air conditioning system; S33, constructing an air conditioning system power control model according to the objective function and constraint conditions of the air conditioning system power control; S34. The White Whale Optimization Algorithm (MOWSO) is used to perform multi-objective optimization on the multi-objective function of the air-conditioning system power control, and a power control scheme for each sub-air-conditioning equipment in the air-conditioning system that meets the constraint conditions is obtained.

9. The IBMS system terminal based on Internet of Things technology according to claim 8, characterized in that: In S34, the White Whale Optimization Algorithm MOWSO is used to solve the multi-objective optimization function of the air-conditioning system power control, and the power control scheme of each sub-air-conditioning equipment in the air-conditioning system that meets the constraint conditions is obtained, including: S341, randomly generate a certain number of beluga individuals to form an initial population, and initialize parameters; S342, setting the initial position of each beluga individual in the initial population according to the power prediction result of each sub-air conditioning device in the air conditioning system output by the air conditioning system power prediction model; S343, calculating the balance factor, and judging whether to enter global exploration or local development according to the balance factor, if entering global exploration, then entering S344; if entering local development, then entering S345; S344, in the global exploration, the swimming behavior of the beluga whale is simulated, and different position update strategies are adopted according to the parity of the current position of the individual beluga whale to search the solution space in the global scope, increase the population diversity, and enter S346; S345. In local development, the behavior of beluga whales in hunting by sharing location information is simulated, and individual beluga whales cooperate in foraging based on the location movement of surrounding beluga whales to update their positions; S346. During each iteration, a portion of beluga individuals are randomly selected from the population to reset their positions or move randomly to simulate the behavior of whales falling; S347, calculating the fitness values ​​of all beluga individuals according to the objective function, and updating the global optimal solution according to the fitness values; S348, judging whether the iteration termination condition is satisfied, if not, returning to S343, otherwise taking the current global optimal solution as the power control scheme for each sub-air-conditioning device in the air-conditioning system that satisfies the constraint condition.

10. The IBMS system terminal based on Internet of Things technology according to claim 9, characterized in that: In S343, the balance factor is calculated and global exploration or local development is determined based on the balance factor, including: The balance factor B is calculated using the following formula: Among them, r is a random number that changes in each iteration, r∈[0,1], k is the current iteration number, k max is the maximum number of iterations; When B>0.5, enter global exploration; when B≤0.5, enter local development; S344. In global exploration, the swimming behavior of beluga whales is simulated, and different position update strategies are adopted according to the parity of the current position of individual beluga whales to search the solution space in a global scope and increase the diversity of the population, including: The following formula is used to update the location: in, is the position of beluga individual i in dimension m at the kth iteration, is the new position of beluga individual i in dimension j at the k+1th iteration, is the position of the randomly selected beluga individual R in the n dimension at the kth iteration, r1 and r2 are random numbers, r1, r2∈[0,1]; S345. In local development, the beluga whales are simulated to hunt by sharing their location information. Individual beluga whales cooperate to forage based on the location movement of surrounding beluga whales to update their location, including: The following formula is used to update the location: in, is the position of beluga individual i at the kth iteration, is the new position of beluga individual i at the k+1th iteration, is the global optimal position at the kth iteration, is the position of the randomly selected beluga individual R at the kth iteration, L F is the Levy flight step length, r3 and r4 are random numbers, r3, r4∈[0,1].

Images