Green building equipment intelligent energy-saving control method and system based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent building energy-saving control, and discloses a green building equipment intelligent energy-saving control method and system based on artificial intelligence, and the method comprises the steps: collecting building environment data, and carrying out the preprocessing; and simulating the energy consumption of the building equipment by using the digital twin model, and training the baseline neural network model to obtain an initial control strategy. And adopting a genetic algorithm to optimize hyper-parameters of the baseline model, and generating a plurality of candidate energy-saving control strategies. And inputting the optimized strategy into the deep reinforcement learning model, carrying out strategy iteration, calculating the energy-saving efficiency and comfort score after each iteration, screening the optimal strategy through a reward mechanism, and improving the accuracy of energy consumption prediction of the building equipment. The hyper-parameter of the neural network is optimized by using the genetic algorithm, and the intelligent degree of the energy-saving control strategy is improved. On the basis of deep reinforcement learning, the intelligent agent can adaptively adjust an energy-saving strategy under different environmental conditions, and the user comfort is guaranteed while the optimal building energy consumption is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent building energy-saving control, and in particular to an intelligent energy-saving control method and system for green building equipment based on artificial intelligence. Background Art

[0002] With the intensification of the global energy crisis and the advancement of sustainable development goals, green building technology has become an important development direction for the construction industry. The energy consumption of traditional building equipment accounts for more than 40% of the world's total energy consumption, of which HVAC (heating, ventilation and air conditioning), lighting and elevator systems are the main sources of energy consumption. In recent years, the rapid development of technologies such as the Internet of Things (IoT), big data analysis and artificial intelligence (AI) has made intelligent building energy-saving control possible. Intelligent control technology mainly includes rule-based control, optimization scheduling algorithm, neural network prediction model, etc. These technologies have improved the energy efficiency of building equipment to a certain extent. In addition, the application of digital twin technology makes the energy consumption simulation of building equipment more accurate, providing data support for further optimization of energy-saving control strategies. At the same time, the application of intelligent decision-making methods such as reinforcement learning in complex system control continues to deepen, providing a new research direction for intelligent energy-saving control of building equipment. However, although the application of these technologies has promoted the development of green buildings, the existing energy-saving control methods still have many limitations and are difficult to meet the dynamic optimization needs of building equipment under different environmental conditions.

[0003] The current energy-saving control technology of building equipment mainly relies on fixed rule control and data-driven predictive control. Among them, the control methods based on fixed rules (such as fuzzy logic, PID control, etc.) are difficult to adapt to the dynamic changes of the internal environment of the building, resulting in limited energy-saving efficiency. At the same time, the optimization methods based on data-driven (such as neural networks, genetic algorithms, etc.) have problems in practical applications, such as the difficulty of adaptive adjustment of hyperparameters, long model training time, and lack of long-term decision-making ability of optimization strategies. In addition, most traditional optimization scheduling algorithms are based on static data for analysis and cannot perceive the changes in the internal and external environment of the building in real time, resulting in poor adaptability of the control strategy. Although the existing reinforcement learning applications can optimize control decisions to a certain extent, they often have defects such as slow training convergence speed and insufficient strategy generalization ability, and it is difficult to balance the relationship between building energy consumption and user comfort. In addition, the current intelligent energy-saving control schemes often lack an effective multi-objective optimization mechanism and cannot ensure user experience while minimizing energy consumption. The present invention proposes an intelligent energy-saving control method for green building equipment based on artificial intelligence, which overcomes the shortcomings of the existing technology by using digital twin models, genetic algorithms, adaptive neural network optimization and deep reinforcement learning, and realizes maximum energy-saving efficiency, dynamic optimization of strategies and user comfort guarantee. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing intelligent energy-saving control methods for building equipment have insufficient adaptability of energy-saving strategies, the optimization models are difficult to adjust dynamically, the control strategies cannot take into account both energy consumption minimization and user comfort, and how to use artificial intelligence to optimize the energy consumption of building equipment and achieve adaptive control.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent energy-saving control method for green building equipment based on artificial intelligence, comprising: collecting building environment data and performing preprocessing.

[0007] The digital twin model is used to simulate the energy consumption of building equipment, train the baseline neural network model, and obtain the initial control strategy.

[0008] Genetic algorithm is used to optimize the hyperparameters of the baseline model and generate multiple candidate energy-saving control strategies.

[0009] The optimized strategy is input into the deep reinforcement learning model for strategy iteration. The energy-saving efficiency and comfort scores are calculated after each iteration, and the optimal strategy is selected through the reward mechanism.

[0010] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, the collecting of building environment data and preprocessing includes: Deploy sensors in buildings to collect building environment data and equipment operating status data.

[0011] Environmental data includes indoor and outdoor temperature, humidity, light intensity, and carbon dioxide concentration.

[0012] Equipment operation data includes HVAC system energy consumption, elevator start and stop frequency, and intelligent lighting brightness settings.

[0013] Preprocessing includes data cleaning, feature extraction and data normalization.

[0014] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, the simulation of building equipment energy consumption using a digital twin model includes: The digital twin model builds a dynamic virtual map of building equipment, integrates environmental data and equipment operating status data, and performs real-time simulation analysis of energy consumption, including: The impact of environmental factors is modeled as follows: ; in, Indicates the comprehensive impact of environmental factors on energy consumption, represents the weight of each environmental factor, Represents the influence function of each environmental variable, Represents a time variable.

[0015] The energy consumption change of the equipment is modeled as: ; in, express The total energy consumption at the time, express The total energy consumption at the time, Indicates the energy consumption impact of the operating status of building equipment, Represents a time variable.

[0016] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, wherein: the training baseline neural network model to obtain the initial control strategy includes: Based on the preprocessed data and the data obtained by digital twin model simulation, the baseline neural network is trained to learn the characteristics of building equipment energy consumption and predict the energy consumption value, which is expressed as: ; in, represents the predicted total energy consumption of building equipment, represents the baseline neural network, Indicates the environmental data input, Indicates the device status input, represents the baseline neural network weights.

[0017] According to the loss function, the prediction error of the neural network model is minimized, and the optimal control strategy for the future is predicted through the trained baseline neural network. The strategy goal is to minimize energy consumption while ensuring user comfort, which is expressed as: ; in, Represents the optimal control strategy, including HVAC regulation, lighting optimization, and elevator scheduling. represents the set of control strategies for building equipment, represents the indoor temperature inside the building, represents the comfort constraint weight, represents the optimal temperature set point, Indicates the optimal indoor temperature set based on user comfort and energy saving requirements. represents the comfort constraint weight, Indicates the optimal illumination setting value, It represents the optimal light intensity based on human visual comfort and lighting energy saving requirements. represents the decision time step.

[0018] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, the optimization of the hyperparameters of the baseline model using a genetic algorithm includes: Define optimization goals, including minimizing energy consumption, maximizing comfort, and optimizing control stability: ; in, represents the fitness function, represents the set of hyperparameters of the genetic algorithm, Represents hyperparameters The corresponding fitness value, the larger the value, the better the hyperparameter combination. Indicates The predicted energy consumption for each time step is represents the indoor temperature setpoint under the current control decision, represents the lighting setting value under the current control decision, represents the number of time steps in the time window considered during the optimization process, represents the volatility of the control strategy and is defined as: ; in, Indicates the device In time The control strategy value of is used to measure the stability of the control strategy. Indicates the device In time The control strategy value of Indicates the total number of smart devices controlled inside the building, Indicates Smart devices, Represents the balance factor.

[0019] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, wherein: the optimization of the hyperparameters of the baseline model using a genetic algorithm also includes: The initial population consists of multiple randomly generated hyperparameter combinations Composition, each individual Including the number of neural network layers , learning rate , regularization parameter , batch size , activation function parameters .

[0020] The population size is set to , the initialization method is expressed as: ; in, Indicates The initial individual, represents a uniform random distribution, represents the minimum value of hyperparameter search, Represents the maximum value of the hyperparameter search.

[0021] According to the fitness function Perform roulette selection to select individuals with high fitness to enter the next generation: ; in, Represents an individual The probability of being selected, represents the number of individuals in the current genetic algorithm population, Indicates the number of Individual.

[0022] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, wherein: the generating of multiple candidate energy-saving control strategies includes: Energy consumption weighted adaptive crossover is introduced, and the crossover weight is allocated according to the energy consumption trend. Low energy consumption individuals give priority to contributing hyperparameters: ; in, Represents a new individual, Indicates an attached individual.

[0023] Perform dynamic compilation and use exponential decay mutation rate to prevent premature convergence, expressed as: ; in, represents the dynamic mutation rate, represents the initial mutation rate, Indicates the current genetic generation.

[0024] The optimized hyperparameters are used to train multiple candidate neural networks, and the objective function is expressed as: ; in, It represents the energy-saving control strategy set finally generated by the baseline neural network after genetic algorithm optimization. represents the building energy consumption predicted by the baseline neural network after optimizing the hyperparameters, represents the HVAC temperature setpoint output by the neural network according to the optimization strategy, represents the lighting setting value output by the neural network according to the optimization strategy, Represents the weights for controlling temperature and lighting optimization.

[0025] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, wherein: the inputting of the optimized strategy into the deep reinforcement learning model and the strategy iteration comprises: Build a deep reinforcement learning model to define the state, action, and reward mechanism so that the system can learn to optimize the control strategy.

[0026] The states include indoor temperature and humidity, light intensity, carbon dioxide concentration, HVAC power, lighting power and elevator power, and the actions include HVAC temperature setting, lighting brightness adjustment and elevator scheduling.

[0027] The reward function is calculated based on energy consumption, comfort deviation and control strategy stability to ensure a balance between energy saving goals and user experience.

[0028] As a preferred solution of the green building equipment intelligent energy-saving control method based on artificial intelligence described in the present invention, wherein: the energy-saving efficiency and comfort score are calculated after each iteration, and the optimal strategy is selected through the reward mechanism, including: The Q-value function of reinforcement learning is used to evaluate the long-term benefits of different control strategies, and the Q-value is iteratively updated through the Bellman equation to continuously optimize the strategy. To avoid local optimality, a greedy strategy is used to balance exploration and utilization. During the training process, the convergence of the Q-value is continuously monitored. When the strategy converges, that is, the Q-value change is lower than the set threshold, the training is terminated.

[0029] The optimal control strategy is selected from the training results and applied to the energy-saving control of building equipment to ensure the lowest energy consumption of the building while maintaining user comfort.

[0030] The green building equipment intelligent energy-saving control system based on artificial intelligence is characterized by: including a preprocessing module for collecting building environment data and performing preprocessing.

[0031] The prediction module uses the digital twin model to simulate the energy consumption of building equipment, train the baseline neural network model, and obtain the initial control strategy.

[0032] The optimization module uses genetic algorithm to optimize the hyperparameters of the baseline model and generate multiple candidate energy-saving control strategies.

[0033] The screening module inputs the optimized strategy into the deep reinforcement learning model to perform strategy iteration. After each iteration, the energy-saving efficiency and comfort score are calculated, and the optimal strategy is screened through the reward mechanism.

[0034] The beneficial effects of the present invention are as follows: the digital twin model is used to simulate the energy consumption of building equipment. Compared with the traditional energy consumption calculation method based on static data, the digital twin model can dynamically update the equipment operation status, simulate the complex building environment impact, and improve the prediction ability of energy consumption trends. When the building equipment configuration changes or the environmental conditions fluctuate, the digital twin model can be adjusted in real time to ensure the accuracy of the energy-saving strategy and overcome the problem of insufficient adaptability of traditional optimization methods in dynamic environments.

[0035] Genetic algorithms are used to optimize the hyperparameters of the baseline neural network. Compared with traditional neural networks with fixed hyperparameters, the model optimized by genetic algorithms can dynamically adjust hyperparameters and improve the prediction ability of neural networks. The genetic algorithm automatically optimizes hyperparameters to avoid the inefficient process of repeated manual parameter adjustment of traditional neural networks and improves computing efficiency. Multiple candidate energy-saving control strategies are generated to provide a diverse decision-making basis for subsequent reinforcement learning optimization.

[0036] The optimized strategy is input into the deep reinforcement learning model for strategy iteration. Compared with the traditional energy-saving control method based on static rules, reinforcement learning can continuously optimize the control strategy under different environmental conditions to ensure that the strategy always has the best energy-saving effect. Traditional energy-saving methods often only focus on minimizing energy consumption, while reinforcement learning can maintain user comfort while saving energy through a reward mechanism, ensuring that intelligent control does not affect the user experience. Since reinforcement learning can continuously adjust the strategy based on environmental feedback, this method can adapt to different building types and environmental conditions, improving the versatility of the control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 An overall flow chart of an artificial intelligence-based green building equipment intelligent energy-saving control method and system provided for the first embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0039] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides an intelligent energy-saving control method for green building equipment based on artificial intelligence, including: S1: Collect building environment data and perform preprocessing.

[0040] Deploy sensors in buildings to collect building environment data and equipment operating status data.

[0041] Environmental data includes indoor and outdoor temperature, humidity, light intensity, and carbon dioxide concentration.

[0042] Equipment operation data includes HVAC system energy consumption, elevator start and stop frequency, and intelligent lighting brightness settings.

[0043] Preprocessing includes data cleaning, feature extraction and data normalization.

[0044] It should be noted that the specific preprocessing steps are as follows: All collected data is initially screened through the edge computing gateway to remove obviously erroneous or invalid data (such as abnormal jumps and data that has not changed for a long time).

[0045] Subsequently, the data is time-aligned and denoised. Since different sensors have different sampling frequencies, time synchronization is required to ensure that the data is comparable within the same time window. For high-frequency fluctuating signals (such as temperature and humidity sensor data), wavelet transform is used for smoothing to reduce the impact of noise. For missing data, interpolation is used to complete it to ensure data integrity.

[0046] After data cleaning, feature engineering is performed on the data, including feature selection, feature extraction, and dimensionality reduction. The Pearson correlation coefficient is used to analyze the relationship between different environmental variables and remove redundant and highly correlated features. Feature dimensionality reduction is performed based on principal component analysis (PCA) to extract the most representative feature variables and reduce computational complexity.

[0047] The Z-score normalization method is used to unify the numerical range of different data to facilitate the subsequent training of the neural network model.

[0048] S2: Use the digital twin model to simulate the energy consumption of building equipment, train the baseline neural network model, and obtain the initial control strategy.

[0049] It should be noted that by constructing a digital twin model, the dynamic changes of building equipment energy consumption under different environmental conditions are simulated, and training is carried out in combination with real data to improve the generalization ability of energy-saving control strategies.

[0050] The digital twin model builds a dynamic virtual map of building equipment, integrates environmental data and equipment operating status data, and performs real-time simulation analysis of energy consumption, including: The impact of environmental factors is modeled as follows: ; in, Indicates the comprehensive impact of environmental factors on energy consumption, represents the weight of each environmental factor, Represents the influence function of each environmental variable, Represents a time variable.

[0051] It should be noted that When taking 1, for The indoor temperature at the moment, Take 2, for The outdoor temperature at the time, Take 3 o'clock, for The light intensity at the time, Take 4: for The carbon dioxide concentration at the moment. Calculated based on regression of historical data.

[0052] An exponential decay function is selected, expressed as: ; in, Represents the index weight of each environmental factor, calculated based on historical data. Indicates environment variables.

[0053] The energy consumption change of the equipment is modeled as: ; in, express The total energy consumption at the time, express The total energy consumption at the time, Indicates the energy consumption impact of the operating status of building equipment, Represents a time variable.

[0054] Furthermore, by integrating and calculating the changes in energy consumption over time, the building energy consumption can be dynamically simulated, which is convenient for subsequent neural network training.

[0055] It should be noted that Represents the energy consumption impact of the operating state of building equipment, defined as: ; in, Indicates the consumption of the equipment, When taking 1, for The power consumption of the HVAC system at the moment, Take 2, for The instantaneous energy consumption of the elevator starting and stopping at the moment, Take 3 o'clock, for The power consumption of the smart lighting system at all times. It indicates the energy consumption coefficient of each device, which is determined by technicians based on the rated power and operating time of the equipment.

[0056] Based on the preprocessed data and the data obtained by digital twin model simulation, the baseline neural network is trained to learn the characteristics of building equipment energy consumption and predict the energy consumption value, which is expressed as: ; in, represents the predicted total energy consumption of building equipment, represents the baseline neural network, Indicates the environmental data input, Indicates the device status input, represents the baseline neural network weights.

[0057] According to the loss function, the prediction error of the neural network model is minimized, and the optimal control strategy for the future is predicted through the trained baseline neural network. The strategy goal is to minimize energy consumption while ensuring user comfort, which is expressed as: ; in, Represents the optimal control strategy, including HVAC regulation, lighting optimization, and elevator scheduling. represents the set of control strategies for building equipment, represents the indoor temperature inside the building, represents the comfort constraint weight, represents the optimal temperature set point, Indicates the optimal indoor temperature set based on user comfort and energy saving requirements. represents the comfort constraint weight, Indicates the optimal illumination setting value, It represents the optimal light intensity based on human visual comfort and lighting energy saving requirements. represents the decision time step. and It is a value set by technicians based on historical data and experience. In specific applications, it can be dynamically adjusted according to seasonal changes, weather changes, etc.

[0058] It should be noted that the accuracy of traditional energy consumption prediction methods is limited, and the optimization method based on static energy consumption models cannot accurately simulate the dynamic changes of the building environment, resulting in the failure of the strategy. Existing technologies are often optimized for specific buildings, but when the physical characteristics of the building change, the optimization strategy is difficult to generalize.

[0059] Furthermore, our invention combines environmental data with equipment status data, and the digital twin model can simulate building energy consumption in real time, making the optimization strategy more accurate. Compared with traditional optimization methods, this technology can adapt to different building environments, improve the portability of the model, and avoid overfitting the strategy to specific buildings.

[0060] In step S2, the digital twin model is used to simulate the energy consumption of building equipment. Compared with the traditional energy consumption calculation method based on static data, the digital twin model can dynamically update the equipment operation status, simulate the complex building environment impact, and improve the ability to predict energy consumption trends. In the case of changes in building equipment configuration or fluctuations in environmental conditions, the digital twin model can be adjusted in real time to ensure the accuracy of energy-saving strategies and overcome the lack of adaptability of traditional optimization methods in dynamic environments.

[0061] S3: Genetic algorithm is used to optimize the hyperparameters of the baseline model and generate multiple candidate energy-saving control strategies.

[0062] It should be noted that genetic algorithm is used to optimize the hyperparameters of neural network, including learning rate, number of layers, and regularization parameters, to improve the prediction accuracy and stability of neural network in energy-saving control.

[0063] Define optimization goals, including minimizing energy consumption, maximizing comfort, and optimizing control stability: ; in, represents the fitness function, represents the set of hyperparameters of the genetic algorithm, Represents hyperparameters The corresponding fitness value, the larger the value, the better the hyperparameter combination. Indicates The predicted energy consumption for each time step is represents the indoor temperature setpoint under the current control decision, represents the lighting setting value under the current control decision, represents the number of time steps in the time window considered during the optimization process, represents the volatility of the control strategy and is defined as: ; in, Indicates the device In time The control strategy value of is used to measure the stability of the control strategy. Indicates the device In time The control strategy value of Indicates the total number of smart devices controlled inside the building, Indicates Smart devices, Represents the balance factor.

[0064] It should be noted that It is obtained by technicians based on experimental calculations and can be adjusted in specific implementations.

[0065] Furthermore, the volatility of the control strategy is introduced , which can prevent unnecessary energy consumption or user discomfort caused by frequent adjustments to device parameters. Taking the inverse, low energy consumption solutions are encouraged, and at the same time comfort and stability constraints are introduced to make the optimization results more in line with actual needs.

[0066] The initial population consists of multiple randomly generated hyperparameter combinations Composition, each individual Including the number of neural network layers , learning rate , regularization parameter , batch size , activation function parameters .

[0067] The population size is set to , use uniform distribution to initialize hyperparameters to ensure the diversity of the initial population and avoid premature convergence. The initialization method is expressed as: ; in, Indicates The initial individual, represents a uniform random distribution, represents the minimum value of the hyperparameter search, Represents the maximum value of the hyperparameter search.

[0068] According to the fitness function Perform roulette selection to select individuals with high fitness to enter the next generation: ; in, Represents an individual The probability of being selected, represents the number of individuals in the current genetic algorithm population, Indicates the number of Individual.

[0069] Energy consumption weighted adaptive crossover is introduced, and the crossover weight is allocated according to the energy consumption trend. Low energy consumption individuals give priority to contributing hyperparameters: ; in, Represents a new individual, Indicates an attached individual.

[0070] Perform dynamic compilation and use exponential decay mutation rate to prevent premature convergence, expressed as: ; in, represents the dynamic mutation rate, represents the initial mutation rate, Indicates the current genetic generation.

[0071] The optimized hyperparameters are used to train multiple candidate neural networks, and the objective function is expressed as: ; in, It represents the energy-saving control strategy set finally generated by the baseline neural network after genetic algorithm optimization. represents the building energy consumption predicted by the baseline neural network after optimizing the hyperparameters, represents the HVAC temperature setpoint output by the neural network according to the optimization strategy, represents the lighting setting value output by the neural network according to the optimization strategy, Represents the weights for controlling temperature and lighting optimization.

[0072] It should be noted that neural network hyperparameters are difficult to adjust manually. Traditional methods rely on manual parameter adjustment, which is inefficient and unstable. Neural network models with fixed hyperparameters are difficult to adapt to different building environments, resulting in reduced prediction accuracy.

[0073] Furthermore, the genetic algorithm can search for the optimal hyperparameter combination in a short time, improving the training efficiency. Compared with the fixed hyperparameter model, the neural network optimized by the genetic algorithm can adapt to different building environments and improve the effectiveness of energy-saving strategies.

[0074] In step S3, a genetic algorithm is used to optimize the hyperparameters of the baseline neural network. Compared with the traditional fixed hyperparameter neural network, the model optimized by the genetic algorithm can dynamically adjust the hyperparameters and improve the prediction ability of the neural network. The genetic algorithm automatically optimizes the hyperparameters to avoid the inefficient process of repeated manual parameter adjustment of the traditional neural network and improve the computing efficiency. Multiple candidate energy-saving control strategies are generated to provide a diverse decision-making basis for subsequent reinforcement learning optimization.

[0075] S4: Input the optimized strategy into the deep reinforcement learning model and perform strategy iteration. After each iteration, calculate the energy-saving efficiency and comfort score, and select the optimal strategy through the reward mechanism.

[0076] It should be noted that deep reinforcement learning is used to optimize the control strategy of building equipment, and through Q-value function update and reward mechanism, energy consumption is minimized while ensuring user comfort.

[0077] Build a deep reinforcement learning model to define the state, action, and reward mechanism so that the system can learn to optimize the control strategy.

[0078] Define the state: at time , the state of the agent It is composed of the environment status and the equipment status: ; in, Indicates the current indoor temperature. Indicates the current humidity. Indicates the current light intensity. represents the carbon dioxide concentration, Indicates the current power of the HVAC system, Indicates the current power of the lighting system. Indicates the current power of the elevator system.

[0079] Define actions: The control strategies that a reinforcement learning agent can choose are expressed as: ; in, express HVAC temperature settings at time nodes, express Lighting settings for time nodes, express Elevator dispatching status at a time node.

[0080] The reward function is calculated based on energy consumption, comfort deviation, and control strategy stability to ensure a balance between energy saving goals and user experience, expressed as: ; in, Indicates immediate reward, It represents weight, which is obtained by technicians based on experiments and experience and can be modified in practical applications. represents the control strategy volatility, expressed as: ; in, Indicates the device In time The control strategies adopted Indicates the device In time Control strategies adopted.

[0081] It should be noted that the first term of the reward function encourages low energy consumption solutions. The second and third terms ensure that the temperature and light are close to the optimal value. The fourth term penalizes frequent adjustment of control parameters to improve the stability of the strategy.

[0082] The Q-value function of reinforcement learning is used to evaluate the long-term benefits of different control strategies: ; in, Indicates in status Take Action long-term benefits. Represents the discount factor, which controls the long-term reward weight, and its value range is between 0 and 1.

[0083] The Q value is iteratively updated through the Bellman equation to continuously optimize the strategy.

[0084] To avoid local optimality, a greedy strategy is used to balance exploration and utilization. During the training process, the convergence of the Q value is continuously monitored. When the strategy converges, that is, the Q value change is lower than the set threshold, the training is terminated.

[0085] The optimal control strategy is selected from the training results and applied to the energy-saving control of building equipment to ensure the lowest energy consumption of the building while maintaining user comfort. The optimal control strategy is expressed as: ; in, represents the optimal control strategy, including the optimal control strategy for the HVAC system, It should be noted that traditional optimization methods often aim to minimize energy consumption while ignoring the user's comfort experience. Control methods based on short-term optimization are prone to fall into local optimality, while reinforcement learning can evaluate long-term benefits.

[0086] Furthermore, compared to fixed rule control, reinforcement learning can continuously optimize strategies based on historical data and real-time feedback to improve adaptability. Through the reward mechanism, it can ensure energy saving while not affecting user comfort.

[0087] In step S4, the optimized strategy is input into the deep reinforcement learning model for strategy iteration. Compared with the traditional energy-saving control method based on static rules, reinforcement learning can continuously optimize the control strategy under different environmental conditions to ensure that the strategy always has the best energy-saving effect. Traditional energy-saving methods often only focus on minimizing energy consumption, while reinforcement learning can maintain user comfort while saving energy through a reward mechanism, ensuring that intelligent control does not affect user experience. Since reinforcement learning can continuously adjust the strategy based on environmental feedback, this method can adapt to different building types and environmental conditions, improving the versatility of the control system.

[0088] The above embodiments also include an intelligent energy-saving control system for green building equipment based on artificial intelligence, specifically: The preprocessing module collects building environment data and performs preprocessing.

[0089] The prediction module uses the digital twin model to simulate the energy consumption of building equipment, train the baseline neural network model, and obtain the initial control strategy.

[0090] The optimization module uses genetic algorithm to optimize the hyperparameters of the baseline model and generate multiple candidate energy-saving control strategies.

[0091] The screening module inputs the optimized strategy into the deep reinforcement learning model to perform strategy iteration. After each iteration, the energy-saving efficiency and comfort score are calculated, and the optimal strategy is screened through the reward mechanism.

[0092] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of the power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an intelligent energy-saving control method for green building equipment based on artificial intelligence is implemented.

[0093] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0094] Example 2 is an embodiment of the present invention, which provides an intelligent energy-saving control method and system for green building equipment based on artificial intelligence. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0095] This embodiment aims to verify the actual effect of the intelligent energy-saving control method and system of green building equipment based on artificial intelligence in optimizing building energy consumption and improving energy-saving efficiency. The experiment selected a smart office building as the research object, which includes an HVAC (heating, ventilation and air conditioning) system, an intelligent lighting system and an elevator dispatching system. During the experiment, the building environment data, including indoor and outdoor temperature and humidity, light intensity, carbon dioxide concentration, etc., were first collected through sensors, and the data was preprocessed to eliminate outliers and perform normalization.

[0096] Subsequently, the digital twin model was used to simulate the energy consumption of building equipment and train the baseline neural network model to generate a preliminary energy-saving control strategy. The neural network input is environmental data and equipment status data, and the output is the energy consumption prediction value. In order to optimize the hyperparameters of the model, the experiment used a genetic algorithm to search for hyperparameters, including the number of neural network layers, learning rate, regularization parameters, etc., to ensure the generation of the optimal energy consumption control strategy. Finally, the optimized strategy was input into the deep reinforcement learning model, and the energy-saving strategy was continuously iterated through reinforcement learning. After each iteration, the energy-saving efficiency and comfort score were calculated, and the optimal strategy was selected through the reward mechanism.

[0097] The experiment set up a comparative test, using the most common rule-based energy-saving method in the current industry as the reference group. The rule-based control method sets the equipment operation strategy according to fixed environmental parameters, such as the temperature of the HVAC system is set to a constant 22°C, and the lighting system maintains 80% brightness during the day. The method of the present invention is based on dynamic data optimization control strategy, so that energy-related parameters such as HVAC temperature, lighting brightness, and elevator scheduling can be adjusted in real time to adapt to different environmental requirements.

[0098] The experiment lasted for 30 days, and the building energy consumption data was recorded 24 hours a day, and the comfort feedback of the building occupants was counted. During the experiment, the recorded environmental parameters, equipment operating status and optimized control strategy are shown in Table 1.

[0099] Table 1 Our invention experimental data table

[0100] In order to verify the advantages of the method of the present invention, the energy-saving effect of the rule-based control method is compared, as shown in Table 2. The comfort calculation method is as follows: Temperature score: According to the human body's comfortable temperature range (usually 20℃~26℃), an optimal temperature range is set. If the room temperature is within this range, the highest score is given; when the temperature deviates from this range, the score gradually decreases, and the greater the deviation, the lower the score.

[0101] Humidity score: The relative humidity suitable for the human body is usually between 40% and 60%. Too high or too low humidity will affect comfort, so the score is adjusted according to the degree of humidity deviation.

[0102] Lighting score: Considering daily office or life scenes, set the optimal lighting range (for example, 300~500 lux is recommended for office areas). If the actual light intensity is within this range, the score will be the highest. Too bright or too dark will reduce the score.

[0103] Carbon dioxide concentration score: Too high CO2 concentration will lead to a decline in air quality, affecting people's concentration and comfort. Generally speaking, CO2 concentration is more suitable in the range of 400~800ppm, and exceeding 1000ppm will have a significant impact on comfort. Therefore, the score is dynamically adjusted based on concentration changes.

[0104] Equipment noise score: The operating noise of building equipment such as HVAC systems and elevators also affects comfort. If the noise level is maintained within a reasonable range (for example, office areas usually do not exceed 50 dB), the score will be high; if the equipment is frequently started and stopped, generating loud noise, the score will be reduced accordingly.

[0105] The scores of the above factors are weighted and calculated according to the self-set weights to obtain the final comprehensive comfort score. The weight setting can be adjusted according to the actual needs of the experimental environment. In this experiment, the weight design is 35% for indoor temperature, 20% for humidity, 20% for CO2 concentration, 15% for light intensity, and 10% for equipment noise.

[0106] Finally, all scores are weighted and summed to obtain a comprehensive comfort score, which is normalized to the range of 0 to 10 to intuitively compare the comfort performance under different control strategies.

[0107] Table 2. Comparative experimental data of existing technologies

[0108] The experimental data analysis shows that the method of the present invention is superior to the existing technology in terms of energy saving effect and comfort. First, in terms of HVAC energy consumption, after adopting intelligent optimization control based on artificial intelligence, energy consumption dropped from 15.2kWh to 11.8kWh, and the energy saving rate reached 22.4%. This is mainly attributed to the fact that the optimized control strategy can adaptively adjust the temperature set point according to environmental changes, avoiding energy waste caused by fixed rule control.

[0109] In terms of lighting energy consumption, the optimization strategy can dynamically adjust the lighting brightness according to the light intensity, reducing energy consumption from 4.5kWh to 3.2kWh, with an energy saving rate of 28.9%. In addition, the elevator scheduling optimization strategy reduces the number of unnecessary elevator starts and stops from 22 times to 15 times, which not only reduces energy consumption but also increases the life of equipment.

[0110] The improvement in the comfort score (from 7.5 to 8.9) shows that the optimization strategy can ensure energy saving while avoiding the degradation of user experience. Traditional energy-saving methods often aim to minimize energy consumption while ignoring the comfort of the indoor environment. The method of the present invention uses a reinforcement learning model to balance energy consumption and comfort, so that the final control strategy is more in line with user needs.

[0111] Overall, the method of the present invention not only has obvious advantages in energy consumption optimization, but also achieves a significant improvement in user experience. The method can adapt to different building environments and has better versatility. Compared with traditional rule-based control methods, this method can dynamically optimize energy-saving strategies to ensure the lowest building energy consumption while maintaining user comfort, making it widely popularized in practical applications.

[0112] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent energy-saving control method for green building equipment based on artificial intelligence, characterized in that: include: Collect building environment data and pre-process it; Use the digital twin model to simulate the energy consumption of building equipment, train the baseline neural network model, and obtain the initial control strategy; Genetic algorithm is used to optimize the hyperparameters of the baseline model and generate multiple candidate energy-saving control strategies; The optimized strategy is input into the deep reinforcement learning model for strategy iteration. The energy-saving efficiency and comfort scores are calculated after each iteration, and the optimal strategy is selected through the reward mechanism.

2. The green building equipment intelligent energy-saving control method based on artificial intelligence according to claim 1, characterized in that: The collecting of building environment data and preprocessing includes: Deploy sensors in buildings to collect building environment data and equipment operating status data; Environmental data include indoor and outdoor temperature, humidity, light intensity, and carbon dioxide concentration; Equipment operation data includes HVAC system energy consumption, elevator start and stop frequency, and intelligent lighting brightness settings; Preprocessing includes data cleaning, feature extraction and data normalization.

3. The green building equipment intelligent energy-saving control method based on artificial intelligence as claimed in claim 2, characterized in that: The simulation of building equipment energy consumption using a digital twin model includes: The digital twin model builds a dynamic virtual map of building equipment, integrates environmental data and equipment operating status data, and performs real-time simulation analysis of energy consumption, including: The impact of environmental factors is modeled as follows: ； in, Indicates the comprehensive impact of environmental factors on energy consumption, represents the weight of each environmental factor, Represents the influence function of each environmental variable, represents the time variable; The energy consumption change of the equipment is modeled as: ； in, express The total energy consumption at the time, express The total energy consumption at the time, Indicates the energy consumption impact of the operating status of building equipment, Represents a time variable.

4. The green building equipment intelligent energy-saving control method based on artificial intelligence as claimed in claim 3 is characterized by: The training baseline neural network model to obtain the initial control strategy includes: Based on the preprocessed data and the data obtained by digital twin model simulation, the baseline neural network is trained to learn the characteristics of building equipment energy consumption and predict the energy consumption value, which is expressed as: ； in, represents the predicted total energy consumption of building equipment, represents the baseline neural network, Indicates the environmental data input, Indicates the device status input, represents the baseline neural network weights; According to the loss function, the prediction error of the neural network model is minimized, and the optimal control strategy for the future is predicted through the trained baseline neural network. The strategy goal is to minimize energy consumption while ensuring user comfort, which is expressed as: ； in, represents the optimal control strategy, including HVAC regulation, lighting optimization, and elevator scheduling; represents the set of control strategies for building equipment, represents the indoor temperature inside the building, represents the comfort constraint weight, represents the optimal temperature set point, Indicates the optimal indoor temperature set based on user comfort and energy saving requirements. represents the comfort constraint weight, Indicates the optimal illumination setting value, It represents the optimal light intensity set based on human visual comfort and lighting energy saving requirements. represents the decision time step.

5. The green building equipment intelligent energy-saving control method based on artificial intelligence as claimed in claim 4, characterized in that: The use of a genetic algorithm to optimize the hyperparameters of the baseline model includes: Define optimization goals, including minimizing energy consumption, maximizing comfort, and optimizing control stability: ； in, represents the fitness function, represents the set of hyperparameters of the genetic algorithm, Represents hyperparameters The corresponding fitness value, the larger the value, the better the hyperparameter combination; Indicates The predicted energy consumption for each time step is represents the indoor temperature setpoint under the current control decision, represents the lighting setting value under the current control decision, represents the number of time steps in the time window considered during the optimization process, represents the volatility of the control strategy and is defined as: ； in, Indicates the device In time The control strategy value of is used to measure the stability of the control strategy; Indicates the device In time The control strategy value of Indicates the total number of smart devices controlled inside the building, Indicates Smart devices, Represents the balance factor.

6. The green building equipment intelligent energy-saving control method based on artificial intelligence as claimed in claim 5, characterized in that: The use of a genetic algorithm to optimize the hyperparameters of the baseline model also includes: The initial population consists of multiple randomly generated hyperparameter combinations Composition, each individual Including the number of neural network layers , learning rate , regularization parameter , batch size , activation function parameters ; The population size is set to , the initialization method is expressed as: ； in, Indicates The initial individual, represents a uniform random distribution, represents the minimum value of hyperparameter search, Indicates the maximum value of hyperparameter search; According to the fitness function Perform roulette selection to select individuals with high fitness to enter the next generation: ； in, Represents an individual The probability of being selected, represents the number of individuals in the current genetic algorithm population, Indicates the number of Individual.

7. The green building equipment intelligent energy-saving control method based on artificial intelligence according to claim 6, characterized in that: Generating a plurality of candidate energy-saving control strategies comprises: Energy consumption weighted adaptive crossover is introduced, and the crossover weight is allocated according to the energy consumption trend. Low energy consumption individuals give priority to contributing hyperparameters: ； in, Represents a new individual, Indicates an incidental individual; Perform dynamic compilation and use exponential decay mutation rate to prevent premature convergence, expressed as: ； in, represents the dynamic mutation rate, represents the initial mutation rate, Indicates the current genetic generation; The optimized hyperparameters are used to train multiple candidate neural networks, and the objective function is expressed as: ； in, It represents the energy-saving control strategy set finally generated by the baseline neural network after genetic algorithm optimization; represents the building energy consumption predicted by the baseline neural network after optimizing the hyperparameters, represents the HVAC temperature setpoint output by the neural network according to the optimization strategy, represents the lighting setting value output by the neural network according to the optimization strategy, Represents the weights for controlling temperature and lighting optimization.

8. The green building equipment intelligent energy-saving control method based on artificial intelligence as claimed in claim 7, characterized in that: Inputting the optimized strategy into the deep reinforcement learning model and performing strategy iteration includes: Build a deep reinforcement learning model to define the state, action, and reward mechanism so that the system can learn to optimize the control strategy; The status includes indoor temperature and humidity, light intensity, carbon dioxide concentration, HVAC power, lighting power and elevator power, and the actions include HVAC temperature setting, lighting brightness adjustment and elevator dispatch; The reward function is calculated based on energy consumption, comfort deviation and control strategy stability.

9. The green building equipment intelligent energy-saving control method based on artificial intelligence as claimed in claim 8, characterized in that: After each iteration, the energy-saving efficiency and comfort scores are calculated, and the optimal strategy is selected through the reward mechanism, including: The Q-value function of reinforcement learning is used to evaluate the long-term benefits of different control strategies, and the Q-value is iteratively updated through the Bellman equation to continuously optimize the strategy. To avoid local optimality, a greedy strategy is used to balance exploration and utilization. During the training process, the convergence of the Q-value is continuously monitored. When the strategy converges, that is, the Q-value change is lower than the set threshold, the training is terminated. The optimal control strategy is selected from the training results and applied to the energy-saving control of building equipment to ensure the lowest energy consumption of the building while maintaining user comfort.

10. An artificial intelligence-based green building equipment intelligent energy-saving control system using the method according to any one of claims 1 to 9, characterized in that: Preprocessing module, collects building environment data and performs preprocessing; The prediction module uses the digital twin model to simulate the energy consumption of building equipment, train the baseline neural network model, and obtain the initial control strategy; The optimization module uses genetic algorithms to optimize the hyperparameters of the baseline model and generate multiple candidate energy-saving control strategies; The screening module inputs the optimized strategy into the deep reinforcement learning model to perform strategy iteration. After each iteration, the energy-saving efficiency and comfort score are calculated, and the optimal strategy is screened through the reward mechanism.

Images