Intelligent building energy consumption optimization method and equipment based on cloud platform, and medium

Abstract

The invention discloses an intelligent building energy consumption optimization method and device based on a cloud platform, and a medium. The method comprises the steps of obtaining historical data of an intelligent building and historical working parameters of energy consumption equipment in a previous preset time period; inputting the data into a power industry large model to obtain first predicted indoor data for a current preset time period; actual indoor data and current working parameters are obtained; obtaining a prediction error, and selecting a preferable power industry large model; obtaining future indoor data of the next preset time period, and calculating a corresponding average value; determining a building working condition of a next preset time period, and matching an adaptive industry large model; establishing an energy consumption optimization objective function for solving the minimum energy consumption value of the intelligent building under the condition that the indoor environment value is within the preset comfort interval; and obtaining a minimum energy consumption value, and determining working parameters of the energy consumption equipment. The large models are managed in a unified mode through the cloud platform, the accuracy and reliability of the models can be improved, and meanwhile the data obtaining and processing cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent building energy management technology, and specifically to an intelligent building energy consumption optimization method, device and medium based on a cloud platform. Background Art

[0002] With the rapid development of the Internet of Things, artificial intelligence and big data analysis technologies and their application in construction, more and more buildings are designed and built into smart buildings. With the increase in global energy consumption and the increasing prominence of environmental problems, governments, enterprises and individuals are paying more and more attention to building energy efficiency, and energy consumption management of smart buildings is becoming more and more important.

[0003] Existing energy consumption management methods usually require the deployment of large model algorithms locally in smart buildings, and the use of building data in the main body of the smart building to train the constructed large model, and the energy consumption of the smart building is predicted by the trained model. The large model constructed by this method can only be applied to local smart buildings, and when the server is upgraded, the model upgrade cost is relatively high and the robustness is poor. When facing system fluctuations or changes, its stability and adaptability are insufficient. The model data comes from a single building and is difficult to apply to a group of buildings, resulting in a waste of model resources. Summary of the invention

[0004] In order to solve the above problems, this application proposes a cloud platform-based smart building energy consumption optimization method, which is applied in the cloud platform and includes:

[0005] For the current time node, historical data of the intelligent building and historical working parameters of energy consumption equipment in the previous preset time period are obtained; the historical data includes historical indoor data and historical outdoor data; the historical indoor data includes historical indoor environment data and historical energy consumption data, and the historical outdoor data includes historical outdoor environment data;

[0006] Input the historical data and the historical operating parameters into each deployed large model of the electric power industry to obtain first predicted indoor data of each large model of the electric power industry for a current preset time period;

[0007] Obtain the actual indoor data of the smart building and the current working parameters of the energy consumption equipment within the current preset time period;

[0008] According to the first predicted indoor data and the actual indoor data, respectively obtain the prediction error of each large model of the electric power industry, and select the preferred large model of the electric power industry whose prediction error is lower than a preset threshold;

[0009] Input the actual indoor data and the current working parameters into the optimal power industry large model, obtain future indoor data for the next preset time period, and calculate the average values ​​corresponding to the future indoor data respectively;

[0010] Based on the average value, determine the building working condition of the next preset time period, and match the adaptation industry big model corresponding to the building working condition in the preferred power industry big model;

[0011] According to the second predicted indoor data output by the adaptation industry big model for the next preset time period, an energy consumption optimization objective function for solving the minimum energy consumption of the intelligent building is established on the condition that the indoor environment value is within the preset comfort range;

[0012] The optimal solution of the energy consumption optimization objective function is solved to obtain the minimum energy consumption value, and the working parameters of the energy consuming equipment are determined according to the minimum energy consumption value to regulate the energy consuming equipment.

[0013] On the other hand, the present application also proposes a cloud platform-based intelligent building energy consumption optimization device, comprising:

[0014] at least one processor; and,

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a cloud platform-based smart building energy consumption optimization method as described in the above example.

[0017] On the other hand, the present application also proposes a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as: a cloud platform-based smart building energy consumption optimization method as described in the above example.

[0018] This application proposes a cloud platform-based intelligent building energy consumption optimization method that can bring the following

[0019] Beneficial effects:

[0020] Through the powerful computing power of the cloud platform, a large amount of data collected in smart buildings can be centrally processed, making energy consumption data prediction more accurate. Pre-deploying multiple different large models of the power industry on the cloud platform, managing the large models in a unified manner through the cloud platform, and allowing the large models to share the smart building data stored in the cloud platform through the data interface provided by the cloud platform can not only improve the accuracy and reliability of the model, but also reduce the cost of data acquisition and processing.

[0021] The average value is obtained through predictions from multiple large models of the power industry, and the building operating conditions are determined based on the average value. The corresponding large industry model is determined based on the operating conditions, making the model more compatible with the smart building, thereby making the predicted data more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 A schematic diagram of a process of optimizing energy consumption of an intelligent building based on a cloud platform in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the relationship between the large model of the power industry and the intelligent building in the embodiment of this application;

[0025] Figure 3 This is a schematic diagram of a variable edge computing power topology structure in an embodiment of the present application;

[0026] Figure 4 This is a schematic diagram of a cloud platform-based intelligent building energy consumption optimization device in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0028] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0029] It should be noted that the industry big model is a machine learning model customized and optimized for a specific field or industry. Compared with the general big model, the industry big model can make full use of its huge parameter scale in a specific field, capture the complex associations in the data, and has stronger professionalism. With the development of artificial intelligence technology, industry big models are being used more in various fields and have achieved remarkable results in many fields. The industry big model refers to a deep learning model that uses large-scale data training and advanced algorithms to meet the needs of a specific industry or field. The industry big model usually includes the key processes, value chains, participants, relationships and other important elements of the industry, which can help understand the industry's operating mechanism, business processes and value creation methods.

[0030] like Figure 1 As shown, the embodiment of the present application provides a method for optimizing energy consumption of intelligent buildings based on a cloud platform, including:

[0031] S101: For the current time node, obtain historical data of the smart building and historical working parameters of energy-consuming equipment in the previous preset time period; the historical data includes historical indoor data and historical outdoor data; the historical indoor data includes historical indoor environment data and historical energy consumption data, and the historical outdoor data includes historical outdoor environment data.

[0032] Specifically, an energy consumption optimization request of an intelligent building is received, and it is determined whether the energy consumption optimization request is the first energy consumption optimization request. If so, historical data of the intelligent building and historical working parameters of energy-consuming devices in the intelligent building in the previous preset time period are obtained for the current time node corresponding to the received energy consumption optimization request. The historical data includes historical indoor data and historical outdoor data, the historical indoor data includes historical indoor environment data and historical energy consumption data, and the historical outdoor data includes historical outdoor environment data.

[0033] If not, execute steps S106 and S107.

[0034] In the embodiments of the present application, sensor devices are installed inside and outside the smart building. Through the installed sensor devices, indoor environment data and outdoor environment data are collected in real time within a preset time period. At the same time, the working parameters of the energy consumption equipment inside the smart building are obtained for the collection time node to obtain the corresponding time series data. After the collection is completed within the preset time period, the energy consumption data of the smart building in the preset time period is counted.

[0035] Among them, indoor environmental data includes parameters such as indoor temperature and humidity, and the rate of people in the room, and outdoor environmental data includes parameters such as weather factors. After the indoor environmental data, outdoor environmental data, equipment working parameters and energy consumption data are collected, the data preprocessing process is carried out, including data cleaning, removing duplicate values, filling missing values ​​and other processes. After data preprocessing, it is uploaded to the cloud platform for storage through encrypted transmission, and corresponding data interfaces are generated according to the preset time periods. In the subsequent process, if the collected smart building data needs to be used, the corresponding smart building data is obtained through the data interfaces corresponding to different preset time periods. The equipment working parameters are the operating status of various energy-consuming equipment in the building, such as the opening / closing of the air-conditioning system, the operating mode (cooling / heating / ventilation), the current set temperature, the wind speed level, etc.; the opening / closing of the lighting system, the brightness level, the light sensor status (whether the brightness is automatically adjusted according to the surrounding light), etc.

[0036] It should be noted that, in the embodiment of the present application, the process of determining the installation location of the sensor equipment in the intelligent building is also included.

[0037] Specifically, according to the building purpose of the intelligent building (such as office, commercial, residential, industrial, etc., the building types corresponding to the building purpose are office buildings, commercial buildings, residential buildings, industrial buildings, etc.), the operation mode of the intelligent building is determined, and the operation mode is analyzed to determine the energy consumption mode of the intelligent building. For example, when the building purpose is office, its corresponding operation mode is office mode, then the working day is the peak energy consumption time period, the rest day is the low-peak energy consumption time period, the floor where large enterprises are located is the high-energy consumption area, and the small company with fewer employees belongs to the low-energy consumption area, etc.

[0038] Furthermore, based on the energy consumption pattern, high-energy consumption areas and low-energy consumption areas in the smart building are determined, and the high-energy consumption areas are set as key locations. Sensor equipment is installed in key locations, such as key components of heating, ventilation, air conditioning, lighting and other systems, as well as areas with dense personnel or equipment.

[0039] It should be noted that by accurately collecting data from key energy consumption points, the collected data can be accurate and targeted, and energy consumption anomalies and waste can be discovered in a timely manner, so that energy-saving management and optimization measures can be quickly implemented to improve energy-saving efficiency. Among them, the energy-consuming equipment in the building includes power equipment (such as generators, motors, etc.), thermal equipment (such as boilers, heat exchangers, etc.), cooling systems, lighting equipment and transportation equipment (such as pumps, fans), which use different energy consumption. The power consumption of power equipment can be expressed as the product of power (P) and time (t), that is, E = P*t, and the thermal energy consumption of thermal equipment can be expressed as the product of the amount of fuel consumed and its thermal efficiency.

[0040] S102: Input the historical data and the historical operating parameters into each deployed large model of the electric power industry to obtain first predicted indoor data of each large model of the electric power industry for a current preset time period.

[0041] Specifically, the historical indoor environmental data, historical energy consumption data, historical outdoor environmental data and historical working parameters of the smart building in the previous preset time period are taken as input data and input into each power industry big model deployed in the cloud platform. Through each power industry big model, the indoor environmental data and energy consumption data of the current preset time period are predicted, and the first predicted indoor data of each power industry big model for the current preset time period is obtained, including the predicted indoor environmental data and predicted energy consumption data of the current preset time period.

[0042] It should be noted that if Figure 2As shown, different large models of the power industry are large models of multiple large model service providers, which are pre-deployed in the cloud platform. Specifically, the large model of the power industry is uploaded to the designated storage location on the cloud platform, and the model is adapted to ensure that it can run normally in the computing environment of the cloud platform, and the relevant interfaces of the large model of the power industry are configured in the cloud platform to realize direct call of the model. The large model of the power industry is a trained model for predicting energy consumption data of smart buildings. The model architecture includes an input layer, a deep neural network layer, and an output layer. It is relatively mature for energy consumption prediction, has a relatively complete process, and has achieved significant application effects.

[0043] In addition, in the embodiments of the present application specification, before the historical data of the smart building is input into the big model of the power industry, the data volume of the smart building of different big models of the power industry is counted to determine the calculation amount of different big models of the power industry for predicting the smart building.

[0044] Specifically, the indoor and outdoor data of each smart building in different time intervals are obtained, including temperature, humidity, light intensity, personnel flow, weather conditions, ambient temperature, etc. The computing amount of different power industry large models of each smart building is determined based on the indoor data, and the corresponding computing amount time curve is constructed to represent the changes in the amount of computing resources required for each smart building at different time points.

[0045] More specifically, the indoor and outdoor data are cleaned and feature extracted. According to the data scale after feature extraction, the input data size of each smart building at different time points is evaluated, and the computational complexity of the model on each smart building is evaluated according to the model type, parameter configuration and input data scale. By simulating the model or computing volume evaluation tool, the input data scale and model complexity are combined to estimate the computing volume required for each smart building at different time points. The computing volume of each smart building at different time points is summarized, and the summarized computing volume data is fitted into a computing volume time curve through curve fitting methods (such as linear regression, polynomial regression, etc.).

[0046] Furthermore, based on the computing amount time curve, the peak value, valley value and overall trend of the curve of each intelligent building in different time periods are determined. According to the changes in the curve, the changes in the computing amount in different time periods are determined. For example, in time periods with frequent human activities (such as morning and evening), the computing amount may increase, while in time periods with less human activities (such as late at night), the computing amount may decrease.

[0047] According to the change, the average or maximum value of the amount of computing in the time period is calculated to determine the computing power required in each time period, and the computing power demand curve is constructed based on the computing power. According to the computing power demand curve, the minimum number of participants of each edge data center is determined through the edge time-varying topology structure algorithm, and the edge computing power topology structure of the edge data center is constructed based on the determined minimum number of participants, such as Figure 3 As shown in the figure, the computing power topology structure is used to describe the connection relationship between edge data centers, data transmission paths, and computing power allocation strategies to ensure that the computing power requirements of smart buildings can be met efficiently and flexibly.

[0048] In one or more embodiments of the present application specification, the computing power value of the edge data center in different time intervals is extracted from the computing power demand curve, and based on the computing power values ​​in different time intervals, an optimization objective function is established to solve the shortest computing response time and the least number of edge data center participants, with the computing time required for the computing amount in a single time interval not exceeding a preset time threshold, and the hardware carrying capacity in a single time interval not being less than a preset carrying threshold (for example, the model predicts that the amount of historical data per hour is not higher than 0.5 seconds, and the CPU load rate is not lower than 75%). The optimal solution of the optimization objective function is solved by the particle swarm algorithm to obtain the minimum number of participants of the edge data center at different times.

[0049] It should be noted that the cloud platform includes multiple edge data centers, each of which manages multiple smart buildings or smart building clusters. Through the smart green building energy consumption optimization platform with a variable edge computing power topology and the reasonable deployment of computing-intensive services and delay-sensitive services, it has efficient energy consumption data integration, mining, sharing capabilities and distributed, hierarchical massive data processing capabilities. The average response time of smart building cloud services has significantly improved compared to traditional centralized cloud service systems based on large data centers.

[0050] S103: Acquire actual indoor data of the intelligent building and current working parameters of energy consumption equipment within a current preset time period.

[0051] Specifically, after a preset time period, the sensor collects the smart building data for the current preset time period and uploads the smart building data to the cloud platform. The cloud platform obtains the actual indoor environment data, actual energy consumption data and current working parameters of the energy-consuming equipment of the smart building during the current preset time period.

[0052] S104: According to the first predicted indoor data and the actual indoor data, respectively obtain the prediction error of each large model of the electric power industry, and select the preferred large model of the electric power industry whose prediction error is lower than a preset threshold.

[0053] Specifically, the prediction data output by the power industry big model for the current preset time period is obtained, including the prediction of indoor environment data and energy consumption data, and the difference between the prediction data and the actual data output by multiple power industry big models is obtained as the prediction error of the power industry big model. The multiple prediction errors are compared to determine the maximum prediction error and the power industry big model corresponding to the maximum prediction error, and the power industry big model corresponding to the maximum prediction error is deleted to obtain the remaining preferred power industry big models.

[0054] It should be noted that in the embodiment of the present application, the prediction error of different power industry large models is represented by a loss function. According to the algorithm and structure adopted by the industry large model, the type of loss function used is determined, including cross entropy loss function, mean square error loss function, etc. The loss function used in the embodiment of the present application is a mean square error loss function. Use the loss function calculation formula: Where n is the number of samples, y i is the historical energy consumption data of the i-th sample, y i ^ is the predicted energy consumption data of the i-th sample. Based on the historical energy consumption data, the prediction error between the predicted energy consumption data and the historical energy consumption data is determined. According to the prediction error, according to the prediction error and the extreme formula of the loss function, the loss functions of multiple industry models are calculated respectively. The values ​​corresponding to the loss functions are compared to obtain the maximum loss function value and the corresponding power industry model, and the power industry model is deleted.

[0055] S104: Input the actual indoor data and the current working parameters into the preferred power industry large model to obtain future indoor data for the next preset time period, and calculate the average values ​​corresponding to the future indoor data.

[0056] Specifically, the current actual indoor environmental data, the current working parameters of the energy-consuming equipment and the current actual energy consumption data in the intelligent building within the current preset time period are input into multiple preferred power industry big models, and through the multiple preferred power industry big models, the future indoor environmental data and the future energy consumption data of the next preset time period are output, and the first average value of the future indoor environmental data and the second average value of the first future energy consumption data are calculated respectively.

[0057] In one or more embodiments of the present application, first future indoor environment data and first future energy consumption data are obtained, and the first future indoor environment data is analyzed for rationality based on a physical mechanism; when the first future indoor environment data is reasonable, it is determined whether the first future energy consumption data is within a preset standard range; if not, the first future energy consumption data is determined to be abnormal data, and the abnormal type corresponding to the abnormal data is determined through a preset classification algorithm, so as to be processed according to the abnormal type; if so, the first future energy consumption data is determined to be normal.

[0058] Among them, the types of anomalies include sudden anomalies, periodic anomalies, static anomalies, noise anomalies, etc. Sudden anomalies are a sudden surge or drop in energy consumption in a short period of time, which may be related to equipment failure, accidents or human factors; periodic anomalies usually refer to anomalies that occur within a specific time period (such as weekly or monthly), which may be related to regular maintenance activities or operational changes; static anomalies refer to high or low energy consumption states that remain unchanged for a long time, which may indicate equipment aging or decreased efficiency; noise anomalies refer to random fluctuations in the data, which may be caused by sensor failure or data entry errors.

[0059] Specifically, the process of determining the abnormality type includes: dividing the next preset time period into several time intervals on average, obtaining the first future energy consumption data of the interval corresponding to the time interval, and determining the degree of energy consumption change of several time intervals based on the first future energy consumption data of the interval. When there is a degree of energy consumption change higher than the preset threshold, determine the corresponding abnormal time interval, determine whether the abnormal time interval is a random time, if so, determine that the abnormality type corresponding to the abnormal data is a noise abnormality, if not, determine whether the interval length of the time interval is higher than the preset time length, if not, determine that the abnormality type corresponding to the abnormal data is a sudden abnormality, if so, determine that the abnormality type corresponding to the abnormal data is a periodic abnormality. When there is no degree of energy consumption change higher than the preset threshold, determine that the abnormality type corresponding to the abnormal data is a static abnormality.

[0060] S105: Based on the average value, determine the building working condition in the next preset time period, and match the adaptation industry big model corresponding to the building working condition in the preferred power industry big model.

[0061] Specifically, based on the first average value of the first future indoor environment data, the indoor environment conditions of the intelligent building in the next preset time period are determined; based on the second average value of the first future energy consumption data, the energy consumption conditions of the intelligent building in the next preset time period are determined; based on the indoor environment conditions and energy consumption conditions, the building conditions in the next preset time period are determined.

[0062] Furthermore, the key feature vectors in the construction conditions are extracted, and based on the key feature vectors, the matching industry large model corresponding to the construction conditions is determined in the model library through a matching algorithm. For example, the K-Nearest Neighbors (KNN) algorithm, in the intelligent building scenario, represents the characteristics of the construction conditions as vectors, and uses the KNN algorithm to search for the K neighbors most similar to the target conditions in the model library, and determines the best matching model based on the labels of these neighbors.

[0063] S106: Based on the second predicted indoor data output by the adaptation industry big model for the next preset time period, an energy consumption optimization objective function for solving the minimum energy consumption of the intelligent building is established on the condition that the indoor environment value is within the preset comfort range.

[0064] Specifically, based on the second predicted indoor data output by the adaptation industry big model for the next preset time period, the energy consumption index is determined as the optimization target. An energy consumption optimization objective function is established under the condition that the indoor environmental values ​​(such as temperature, humidity, etc.) must be maintained within the preset comfort range. This ensures that the energy consumption of the smart building is minimized while meeting the indoor comfort requirements.

[0065] It should be noted that in the embodiment of the present application, the formula of the objective function is Among them, f(x) is the objective function, E i (x) is the energy consumption of the ith device, x is a variable parameter, and n is the total number of devices.

[0066] S107: Solving the optimal solution of the energy consumption optimization objective function to obtain a minimum energy consumption value, and determining the working parameters of the energy consuming device according to the minimum energy consumption value to regulate the energy consuming device.

[0067] Specifically, according to the model parameters of the large model of the adaptive industry and the optimization objective function, the optimization model is constructed, and the optimization variables are adjusted through the personalized optimization algorithm to achieve the adjustment of the model parameters. By adjusting the variable parameters in the energy consumption objective function and solving the adjusted energy consumption objective function, the corresponding target result is obtained, and the minimum value in the target result is set as the optimal result, and the variable parameters corresponding to the optimal result are determined. Among them, the personalized optimization algorithm includes the particle swarm algorithm and the chimpanzee algorithm.

[0068] Furthermore, determine whether the value corresponding to the optimal result meets the constraints. If not, delete the value corresponding to the optimal result, set the second smallest value in the target result as the new optimal result, obtain the variable parameters corresponding to the new optimal result, and check whether the new optimal result meets the constraints.

[0069] When the energy consumption optimization request received from the intelligent building is not the first energy consumption optimization request, the historical data of the intelligent building and the historical operating parameters of the energy consumption equipment in the corresponding previous preset time period are obtained based on the current time node of the non-first energy consumption optimization request, and the historical data and historical operating parameters corresponding to the non-first energy consumption optimization request are input into the adaptive power industry big model to obtain the predicted indoor data of the adaptive power industry big model for the predicted time period, and according to the predicted indoor data, the minimum energy consumption corresponding to the non-first energy consumption optimization request is obtained through the energy consumption optimization objective function.

[0070] Through the powerful computing power of the cloud platform, a large amount of data collected in smart buildings can be centrally processed, making energy consumption data prediction more accurate. Pre-deploying multiple different large models of the power industry on the cloud platform, managing the large models in a unified manner through the cloud platform, and allowing the large models to share the smart building data stored in the cloud platform through the data interface provided by the cloud platform can not only improve the accuracy and reliability of the model, but also reduce the cost of data acquisition and processing.

[0071] The average value is obtained through predictions from multiple large models of the power industry, and the building operating conditions are determined based on the average value. The corresponding large industry model is determined based on the operating conditions, making the model more compatible with the smart building, thereby making the predicted data more accurate.

[0072] like Figure 4 As shown, the embodiment of the present application also proposes a smart building energy consumption optimization device based on a cloud platform, including:

[0073] at least one processor; and,

[0074] a memory communicatively connected to the at least one processor; wherein,

[0075] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a cloud platform-based smart building energy consumption optimization method as described in any of the above embodiments.

[0076] An embodiment of the present application also provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to be: a cloud platform-based smart building energy consumption optimization method as described in any of the above embodiments.

[0077] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0078] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0079] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0084] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0085] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0086] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0087] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A cloud platform-based intelligent building energy consumption optimization method, characterized in that: Applied in a cloud platform, the method includes: For the current time node, historical data of the intelligent building and historical working parameters of energy consumption equipment in the previous preset time period are obtained; the historical data includes historical indoor data and historical outdoor data; the historical indoor data includes historical indoor environment data and historical energy consumption data, and the historical outdoor data includes historical outdoor environment data; Input the historical data and the historical operating parameters into each deployed large model of the electric power industry to obtain first predicted indoor data of each large model of the electric power industry for a current preset time period; Obtain the actual indoor data of the smart building and the current working parameters of the energy consumption equipment within the current preset time period; According to the first predicted indoor data and the actual indoor data, respectively obtain the prediction error of each large model of the electric power industry, and select the preferred large model of the electric power industry whose prediction error is lower than a preset threshold; Input the actual indoor data and the current working parameters into the optimal power industry large model, obtain future indoor data for the next preset time period, and calculate the average values ​​corresponding to the future indoor data respectively; Based on the average value, determine the building working condition of the next preset time period, and match the adaptation industry big model corresponding to the building working condition in the preferred power industry big model; According to the second predicted indoor data output by the adaptation industry big model for the next preset time period, an energy consumption optimization objective function for solving the minimum energy consumption of the intelligent building is established on the condition that the indoor environment value is within the preset comfort range; The optimal solution of the energy consumption optimization objective function is solved to obtain the minimum energy consumption value, and the working parameters of the energy consuming equipment are determined according to the minimum energy consumption value to regulate the energy consuming equipment.

2. According to claim 1, a cloud platform-based intelligent building energy consumption optimization method is characterized in that: The cloud platform includes a plurality of edge data centers. After acquiring historical data of the smart building and historical operating parameters of the energy-consuming equipment within a previous preset time period for the current time node, the method further includes: Obtain indoor and outdoor data of each smart building in different time intervals; Determine the computational amount of different power industry large models of each intelligent building according to the indoor data, and construct a corresponding computational amount time curve; Determine the computing power demand curve of each intelligent building according to the computing time curve; According to the computing power demand curve, the minimum number of participants of each edge data center is determined by an edge time-varying topology structure algorithm, and an edge computing power topology structure of the edge data center is constructed based on the minimum number of participants. Energy consumption optimization prediction is performed on each smart building based on the edge computing power topology structure.

3. The method for optimizing energy consumption of intelligent buildings based on a cloud platform according to claim 2, characterized in that: The determining, according to the computing power demand curve, the minimum number of participants of each edge data center by using an edge time-varying topology structure algorithm specifically includes: Extracting the computing power value of the edge data center in different time intervals from the computing power demand curve; According to the computing power values ​​in different time intervals, an optimization objective function is established to solve the problem of shortest computing response time and least number of edge data centers participating, provided that the computing time required for the computing amount in a single time interval is not higher than a preset time threshold and the hardware carrying capacity in a single time interval is not lower than a preset carrying threshold; The optimal solution of the optimization objective function is solved by the particle swarm algorithm to obtain the minimum number of participants of the edge data center at different times.

4. The cloud platform-based intelligent building energy consumption optimization method according to claim 1, characterized in that: Determining the building working condition of the next preset time period based on the average value specifically includes: Determining the indoor environmental condition of the intelligent building in the next preset time period according to the first average value of the future indoor environmental data; Determining the energy consumption condition of the intelligent building in the next preset time period according to the second average value of the future energy consumption data; Based on the indoor environmental conditions and the energy consumption conditions, the building conditions for the next preset time period are determined.

5. The method for optimizing energy consumption of intelligent buildings based on a cloud platform according to claim 1, characterized in that: Determining the operating parameters of the energy consuming device according to the minimum energy consumption value specifically includes: Determining the environmental data value corresponding to the energy consumption optimization objective function when the energy consumption is at the minimum value; The operating parameters of the energy consuming device are determined according to the environmental data value.

6. The cloud platform-based intelligent building energy consumption optimization method according to claim 1, characterized in that: The method further comprises: Determine to receive a non-first energy consumption optimization request of the smart building; Based on the non-first energy consumption optimization request, obtaining historical data of the intelligent building and historical operating parameters of the energy consumption equipment in the corresponding last preset time period; Inputting the historical data and historical working parameters corresponding to the non-first energy consumption optimization request into the adaptive power industry big model to obtain the predicted indoor data of the adaptive power industry big model for the predicted time period; According to the predicted indoor data, the minimum energy consumption value corresponding to the non-first energy consumption optimization request is obtained through the energy consumption optimization objective function.

7. The cloud platform-based intelligent building energy consumption optimization method according to claim 1, characterized in that: After inputting the actual indoor data and the current working parameters into the preferred power industry large model to obtain future indoor data for the next preset time period, the method further includes: Performing rationality analysis on the future indoor environment data in the future indoor data based on a physical mechanism; When the future indoor environment data is reasonable, determining whether the future energy consumption data in the future indoor data is within a preset standard range; If not, it is determined that the future energy consumption data is abnormal data, and the abnormal type corresponding to the abnormal data is determined through a preset classification algorithm, so as to perform processing according to the abnormal type.

8. The cloud platform-based intelligent building energy consumption optimization method according to claim 7 is characterized in that: The abnormality types include sudden abnormality, periodic abnormality, static abnormality, and noise abnormality; Determining the abnormality type corresponding to the abnormal data by using a preset classification algorithm specifically includes: Divide the next preset time period into a plurality of time intervals evenly, obtain first future energy consumption data corresponding to the time intervals, and determine the energy consumption change degree of the plurality of time intervals based on the first future energy consumption data; When the energy consumption change degree is higher than a preset threshold, determining a corresponding abnormal time interval, and determining whether the abnormal time interval is a random time; If yes, determining that the abnormality type corresponding to the abnormal data is a noise abnormality; If not, determining whether the interval length of the time interval is longer than a preset time length; If not, determining that the abnormality type corresponding to the abnormal data is a sudden abnormality; If yes, determining that the abnormality type corresponding to the abnormal data is a periodic abnormality; When there is no energy consumption change degree higher than the preset threshold, it is determined that the abnormality type corresponding to the abnormal data is a static abnormality.

9. A cloud platform-based intelligent building energy consumption optimization device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform, for example: For the current time node, historical data of the intelligent building and historical working parameters of energy consumption equipment in the previous preset time period are obtained; the historical data includes historical indoor data and historical outdoor data; the historical indoor data includes historical indoor environment data and historical energy consumption data, and the historical outdoor data includes historical outdoor environment data; Input the historical data and the historical operating parameters into each deployed large model of the electric power industry to obtain first predicted indoor data of each large model of the electric power industry for a current preset time period; Obtain the actual indoor data of the smart building and the current working parameters of the energy consumption equipment within the current preset time period; According to the first predicted indoor data and the actual indoor data, respectively obtain the prediction error of each large model of the electric power industry, and select the preferred large model of the electric power industry whose prediction error is lower than a preset threshold; Input the actual indoor data and the current working parameters into the optimal power industry large model, obtain future indoor data for the next preset time period, and calculate the average values ​​corresponding to the future indoor data respectively; Based on the average value, determine the building working condition of the next preset time period, and match the adaptation industry big model corresponding to the building working condition in the preferred power industry big model; According to the second predicted indoor data output by the adaptation industry big model for the next preset time period, an energy consumption optimization objective function for solving the minimum energy consumption of the intelligent building is established on the condition that the indoor environment value is within the preset comfort range; The optimal solution of the energy consumption optimization objective function is solved to obtain the minimum energy consumption value, and the working parameters of the energy consuming equipment are determined according to the minimum energy consumption value to regulate the energy consuming equipment.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: For the current time node, historical data of the intelligent building and historical working parameters of energy consumption equipment in the previous preset time period are obtained; the historical data includes historical indoor data and historical outdoor data; the historical indoor data includes historical indoor environment data and historical energy consumption data, and the historical outdoor data includes historical outdoor environment data; Input the historical data and the historical operating parameters into each deployed large model of the electric power industry to obtain first predicted indoor data of each large model of the electric power industry for a current preset time period; Obtain the actual indoor data of the smart building and the current working parameters of the energy consumption equipment within the current preset time period; According to the first predicted indoor data and the actual indoor data, respectively obtain the prediction error of each large model of the electric power industry, and select the preferred large model of the electric power industry whose prediction error is lower than a preset threshold; Input the actual indoor data and the current working parameters into the optimal power industry large model, obtain future indoor data for the next preset time period, and calculate the average values ​​corresponding to the future indoor data respectively; Based on the average value, determine the building working condition of the next preset time period, and match the adaptation industry big model corresponding to the building working condition in the preferred power industry big model; According to the second predicted indoor data output by the adaptation industry big model for the next preset time period, an energy consumption optimization objective function for solving the minimum energy consumption of the intelligent building is established on the condition that the indoor environment value is within the preset comfort range; The optimal solution of the energy consumption optimization objective function is solved to obtain the minimum energy consumption value, and the working parameters of the energy consuming equipment are determined according to the minimum energy consumption value to regulate the energy consuming equipment.

Images