Indoor intelligent energy-saving method and system based on Internet of Things and AI

Abstract

The invention provides an indoor intelligent energy-saving method based on the Internet of Things and AI, and belongs to the technical field of intelligent energy-saving control, and the method comprises the steps: 1, collecting indoor environment data through an Internet of Things device in a layered manner, including basic environment data and dynamic behavior data; 2, generating an environment state matrix based on the basic environment data; 3, generating a behavior-energy consumption association map based on the dynamic behavior data and the environment state matrix; 4, generating a dynamic energy-saving strategy based on the behavior-energy consumption association map and preset energy-saving target and comfort constraint; and 5, executing the dynamic energy-saving strategy through the Internet of Things equipment, monitoring the execution effect in real time, and optimizing the environment state matrix and the behavior-energy consumption association map based on the execution effect. According to the invention, the intelligent and autonomous level of the energy-saving effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent energy-saving control technology, and in particular to an indoor intelligent energy-saving method and system based on the Internet of Things and AI. Background Art

[0002] With global energy shortages and increasingly severe environmental pollution, smart buildings and energy-saving technologies have become important research areas in energy management. Existing smart energy-saving systems rely primarily on simple timers and temperature control devices to regulate indoor environments. While these systems can achieve certain energy savings, they lack the ability to dynamically and accurately adjust energy usage strategies based on the environment and user behavior in real time.

[0003] Currently, some IoT-based smart home energy-saving systems utilize devices such as temperature and humidity sensors and light sensors to monitor the indoor environment and optimize device operation through pre-set algorithms. However, these systems often overlook the impact of user behavior patterns on energy consumption, lack dynamic energy-saving strategies based on the integration of environmental and behavioral data, and fail to improve energy-saving results through continuous optimization mechanisms.

[0004] Therefore, the present invention provides an indoor intelligent energy-saving method and system based on the Internet of Things and AI. Summary of the Invention

[0005] The present invention provides an indoor smart energy-saving method and system based on the Internet of Things and AI, which is used to achieve intelligent energy-saving control of the indoor environment by combining Internet of Things devices with AI technology. First, environmental data is collected in layers through the Internet of Things to establish a comprehensive environmental state matrix and behavior-energy consumption correlation map. Based on this data, dynamic energy-saving strategies can be generated to effectively adjust the balance between energy consumption and comfort. Through real-time monitoring and feedback adjustment, not only the energy-saving effect is improved, but also the environmental comfort is ensured, and the negative impact of excessive energy saving on the living experience is avoided. In addition, the combination of environmental status and behavior data makes the energy-saving strategy more accurate and personalized, and improves the intelligence and autonomy of the energy-saving effect.

[0006] The present invention provides an indoor intelligent energy-saving method based on the Internet of Things and AI, including:

[0007] Step 1: Collect indoor environmental data in layers through IoT devices. The environmental data includes basic environmental data and dynamic behavior data.

[0008] Step 2: Generate an environmental state matrix based on basic environmental data;

[0009] Step 3: Generate a behavior-energy consumption correlation map based on dynamic behavior data and the environmental state matrix;

[0010] Step 4: Generate a dynamic energy-saving strategy based on the behavior-energy consumption correlation map and the preset energy-saving goals and comfort constraints;

[0011] Step 5: Execute dynamic energy-saving strategies through IoT devices and monitor the execution results in real time. Optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution results.

[0012] Preferably, generating an environmental state matrix based on basic environmental data and an environmental state deduction model includes:

[0013] Clean and normalize basic environmental data;

[0014] A spatiotemporal convolutional neural network is used as the environmental state deduction model, and the processed basic environmental data is used as the model input to output the environmental state matrix.

[0015] Preferably, generating a behavior-energy consumption correlation map based on dynamic behavior data and an environmental state matrix includes:

[0016] Extract features from dynamic behavior data to obtain personnel behavior features and equipment power consumption features;

[0017] Analyze all environmental parameters in the environmental state matrix to obtain the state characteristics of several spatial regions;

[0018] A behavior-energy consumption correlation map is generated based on personnel behavior characteristics, equipment power consumption characteristics, and spatial area status characteristics.

[0019] Preferably, generating a behavior-energy consumption correlation map based on personnel behavior characteristics, equipment power consumption characteristics, and spatial area state characteristics includes:

[0020] Quantify and classify personnel behavior characteristics as personnel behavior nodes in the behavior-energy consumption correlation map;

[0021] Define equipment power consumption nodes based on equipment power consumption characteristics;

[0022] The state characteristics of the spatial region are used as the environment-related nodes of the behavior-energy consumption association map;

[0023] Get the correlation strength coefficient between all nodes;

[0024] Generate a behavior-energy consumption correlation graph based on the correlation strength coefficients between all nodes.

[0025] Preferably, obtaining the correlation strength coefficients between all nodes includes:

[0026] Perform feature dimension analysis on all nodes to determine the feature dimensions corresponding to each node and the feature values corresponding to each feature dimension;

[0027] The correlation strength coefficient between every two nodes is determined based on several feature dimensions corresponding to each node and the feature value corresponding to each feature dimension: ;

[0028] in, is the correlation strength coefficient between node i and node j, and Respectively represent the values after normalizing the feature values of node i and node j on the kth feature dimension, is the preset weight of the kth feature dimension, and , and Respectively represent the rate of change of the eigenvalues of node i and node j in the kth feature dimension over time, The number of feature dimensions determined when determining the correlation strength coefficient between node i and node j, The maximum value symbol.

[0029] Preferably, a dynamic energy-saving strategy is generated based on the behavior-energy consumption association map and the preset energy-saving target and comfort constraints, including:

[0030] Determine the operating parameters of each indoor device based on the preset energy-saving target and comfort constraints, and encode the operating parameters of each indoor device to form a multidimensional vector;

[0031] A solution space is constructed based on all multidimensional vectors, where each multidimensional vector corresponds to a particle in the solution space;

[0032] Obtain historical energy consumption data of indoor equipment, build an energy consumption estimation model based on the behavior-energy consumption correlation map, and obtain the total energy consumption;

[0033] Determine the degree of energy consumption deviation based on the preset energy saving target and total energy consumption;

[0034] Obtain several comfort indicators based on the behavior-energy consumption correlation map;

[0035] The comfort deviation degree is obtained based on the preset comfort constraint and the comfort index;

[0036] The energy consumption deviation and comfort deviation are combined according to the preset weights to obtain the fitness value of each particle;

[0037] Monitor the fitness value of each particle in real time and determine the corresponding termination condition based on the fitness value of each particle;

[0038] Based on the rules of the MOPSO algorithm, each particle updates its speed and position according to its own historical optimal position and the global optimal position of the particle swarm corresponding to each particle in the solution space until the termination condition is reached and the update stops;

[0039] The position of each particle in the solution space that stops updating is obtained, and then the operating parameters of each device are determined to generate a dynamic energy-saving strategy.

[0040] Preferably, the corresponding termination condition is determined based on the fitness value of each particle, including:

[0041] The corresponding termination iteration coefficient is determined based on the fitness value of each particle: ;

[0042] in, is the termination iteration coefficient corresponding to the fitness value of each particle, is the fitness value of each particle at the g-th iteration, is the fitness value of each particle at the g+1th iteration, is the weight coefficient corresponding to the g-th iteration and g+1-th iteration of each particle, is the second-order differential impact factor, with a value range of (0, 1). is the number of iterations, is the adjustment factor, and its value range is (0, 0.5);

[0043] The corresponding termination condition is determined based on the termination iteration coefficient of each particle.

[0044] Preferably, the dynamic energy-saving strategy is executed by IoT devices and the execution effect is monitored in real time, and the environmental state matrix and behavior-energy consumption correlation map are optimized based on the execution effect, including:

[0045] Based on the control interface of the IoT device, the dynamic energy-saving strategy is sent to the corresponding device execution end. At the same time, the device's operating status data and real-time changes in the indoor environment are collected in real time through the sensors on the device.

[0046] The operating status data of the equipment and the real-time change data of the environment are compared and analyzed with the expected effects of the dynamic energy-saving strategy. If the deviation exceeds the preset range, the gradient descent-based algorithm is used to adjust and optimize the parameters of the environmental state deduction model and the behavior-energy consumption correlation map according to the actual execution results.

[0047] The indoor smart energy-saving system based on IoT and AI includes:

[0048] Data collection module: collects indoor environmental data in layers through IoT devices. The environmental data includes basic environmental data and dynamic behavior data.

[0049] Matrix generation module: generates environmental state matrix based on basic environmental data;

[0050] Graph generation module: Generates behavior-energy consumption correlation graph based on dynamic behavior data and environmental state matrix;

[0051] Strategy generation module: Generates dynamic energy-saving strategies based on the behavior-energy consumption correlation map and preset energy-saving goals and comfort constraints;

[0052] Result optimization module: Execute dynamic energy-saving strategies through IoT devices and monitor the execution effects in real time, and optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution effects.

[0053] Compared with the prior art, the present invention has the following advantages:

[0054] By combining IoT devices with AI technology, intelligent energy-saving control of the indoor environment is achieved. First, through the layered collection of environmental data through the IoT, a comprehensive environmental status matrix and behavior-energy consumption correlation map are established. Based on this data, dynamic energy-saving strategies can be generated to effectively adjust the balance between energy consumption and comfort. Through real-time monitoring and feedback adjustments, not only energy savings are improved, but also environmental comfort is ensured, avoiding the negative impact of excessive energy conservation on the living experience. Furthermore, the combination of environmental status and behavioral data makes energy-saving strategies more precise and personalized, enhancing the intelligence and autonomy of energy-saving effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 This is a flow chart of an indoor intelligent energy-saving method based on the Internet of Things and AI provided by an embodiment of the present invention.

[0057] Figure 2 This is a structural diagram of an indoor intelligent energy-saving system based on the Internet of Things and AI provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0059] Example 1:

[0060] The embodiment of the present invention provides an indoor intelligent energy-saving method based on the Internet of Things and AI, such as Figure 1 Shown, including:

[0061] Step 1: Collect indoor environmental data in layers through IoT devices. The environmental data includes basic environmental data and dynamic behavior data.

[0062] Step 2: Generate an environmental state matrix based on basic environmental data;

[0063] Step 3: Generate a behavior-energy consumption correlation map based on dynamic behavior data and the environmental state matrix;

[0064] Step 4: Generate a dynamic energy-saving strategy based on the behavior-energy consumption correlation map and the preset energy-saving goals and comfort constraints;

[0065] Step 5: Execute dynamic energy-saving strategies through IoT devices and monitor the execution results in real time. Optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution results.

[0066] In this embodiment, basic environmental data includes temperature, humidity, and light intensity, and dynamic behavior data includes personnel activity trajectories and equipment usage patterns.

[0067] In this embodiment, the environmental state matrix includes the spatiotemporal evolution characteristics of temperature distribution, humidity distribution, and light distribution. Temperature distribution: the temperature change trend of different indoor areas; humidity distribution: the humidity change trend of different indoor areas; light distribution: the light intensity change trend of different indoor areas; the matrix is stored in the form of a time series and can predict the environmental state in the future.

[0068] In this embodiment, the dynamic energy-saving strategy includes a device control solution, an environment adjustment solution, and a behavior guidance solution.

[0069] The beneficial effects of this technical solution include: By combining IoT devices with AI technology, intelligent energy-saving control of the indoor environment is achieved. First, through the layered collection of environmental data through the IoT, a comprehensive environmental state matrix and behavior-energy consumption correlation map are established. Based on this data, dynamic energy-saving strategies are generated to effectively adjust the balance between energy consumption and comfort. Through real-time monitoring and feedback adjustments, not only energy savings are improved, but also environmental comfort is ensured, avoiding the negative impact of excessive energy conservation on the living experience.

[0070] Example 2:

[0071] The embodiment of the present invention provides an indoor smart energy-saving method based on the Internet of Things and AI, which generates an environmental state matrix based on basic environmental data and an environmental state deduction model, including:

[0072] Clean and normalize basic environmental data;

[0073] A spatiotemporal convolutional neural network is used as the environmental state deduction model, and the processed basic environmental data is used as the model input to output the environmental state matrix.

[0074] In this embodiment, a spatiotemporal convolutional neural network is used as an environmental state deduction model, and basic environmental data is used as model input to obtain an environmental state matrix, including: converting the basic environmental data into a spatiotemporal data format, i.e., a three-dimensional tensor (time × space × feature), wherein: the time dimension represents the time series of the data; the spatial dimension represents the spatial distribution of the sensor indoors; and the feature dimension represents temperature, humidity, and light intensity. The input data is a three-dimensional tensor (time × space × feature), which represents the spatiotemporal distribution of the basic environmental data. The model structure is as follows: spatiotemporal convolution layer: a three-dimensional convolution kernel (time × space × feature) is used to capture the spatiotemporal features of the data; the convolution kernel size is, for example, 3 × 3 × 3 (time × space × feature); the output of the convolution layer is a feature map after extracting spatiotemporal features. Pooling layer: a three-dimensional maximum pooling layer (MaxPooling) is used to reduce the dimension of the feature map; the pooling kernel size is, for example, 2 × 2 × 2 (time × space × feature). Fully connected layer: the feature map output by the pooling layer is flattened into a one-dimensional vector; the feature vector is mapped to the dimension of the environmental state matrix through the fully connected layer. Output layer:

[0075] The output is an environmental state matrix, including the spatiotemporal evolution characteristics of temperature, humidity, and light distribution. Model training: Historical basic environmental data is used as the training set, and the environmental state matrix is used as the label. The loss function is the mean squared error (MSE), which measures the difference between the model prediction and the true value. The optimization algorithm is the Adam optimizer, which is used to update the model parameters. The training process is to minimize the loss function through the backpropagation algorithm until the model converges. Model prediction: The preprocessed basic environmental data is input into the trained ST-CNN model. The model output is an environmental state matrix, including the spatiotemporal evolution characteristics of temperature, humidity, and light distribution.

[0076] In this embodiment, the environmental state matrix structure is a three-dimensional tensor (time × space × feature), where the time dimension represents environmental state changes over a period of time; the space dimension represents the environmental states of different indoor areas; and the feature dimension represents temperature, humidity, and light intensity. Matrix storage and application: The environmental state matrix is stored as a time series for subsequent steps (such as multi-source data fusion and dynamic weight allocation).

[0077] The beneficial effects of this technical solution include: By employing a spatiotemporal convolutional neural network as the environmental state deduction model, it can fully exploit the spatiotemporal correlations in the data and improve the prediction accuracy of the environmental state matrix. Compared with existing technologies, this optimizes the environmental state deduction process, enhances the intelligence and adaptability of the system, makes energy-saving strategies more precise and efficient, and improves the intelligent level of indoor energy management.

[0078] Example 3:

[0079] The embodiment of the present invention provides an indoor smart energy-saving method based on the Internet of Things and AI, which generates a behavior-energy consumption correlation map based on dynamic behavior data and an environmental state matrix, including:

[0080] Extract features from dynamic behavior data to obtain personnel behavior features and equipment power consumption features;

[0081] Analyze all environmental parameters in the environmental state matrix to obtain the state characteristics of several spatial regions;

[0082] A behavior-energy consumption correlation map is generated based on personnel behavior characteristics, equipment power consumption characteristics, and spatial area status characteristics.

[0083] In this embodiment, AI technology is employed to extract features from dynamic behavior data to derive behavioral characteristics of individuals and device power usage. For example, computer vision and machine learning algorithms (such as convolutional neural networks and support vector machines) are used to analyze video data captured by smart cameras to identify behavioral characteristics such as patterns of activity (e.g., walking, standing, sitting down for work, or discussing in meetings), movement trajectories, and activity areas. For device power usage data, deep learning models (such as long short-term memory (LSTM) networks) are employed to analyze device power usage patterns, power trends, and other power usage characteristics for fault diagnosis.

[0084] In this embodiment, all environmental parameters in the environmental state matrix are analyzed to obtain state characteristics of several spatial regions, including: using a clustering algorithm, such as K-Means clustering, to analyze the data in the environmental state matrix and divide the indoor space into different areas. For example, based on the similarity of temperature and humidity, the office is divided into window areas, middle areas, and wall areas. Each area has relatively consistent environmental state characteristics. State index calculation: For each spatial area, a series of state indicators are determined. For example, the average temperature, humidity standard deviation, and light intensity change rate in the area are calculated. These indicators can reflect the environmental stability and change trend of the area. At the same time, combined with personnel behavior data and equipment power consumption data, the correlation between personnel activity density, equipment utilization rate and environmental status in different areas is analyzed.

[0085] The beneficial effects of this technical solution include: through feature extraction and data analysis, it accurately captures the characteristics of human behavior, equipment power consumption, and spatial area status, effectively constructing a behavior-energy consumption correlation map. Compared with existing technologies, this can more accurately identify and correlate the relationship between behavior and energy consumption, providing more precise data support for the optimization of dynamic energy-saving strategies, and improving the intelligence and refinement of indoor energy efficiency management.

[0086] Example 4:

[0087] The present invention provides an indoor smart energy-saving method based on the Internet of Things and AI. The method generates a behavior-energy consumption correlation map based on the behavioral characteristics of personnel, the power consumption characteristics of equipment, and the state characteristics of spatial areas, including:

[0088] Quantify and classify personnel behavior characteristics as personnel behavior nodes in the behavior-energy consumption correlation map;

[0089] Define equipment power consumption nodes based on equipment power consumption characteristics;

[0090] The state characteristics of the spatial region are used as the environment-related nodes of the behavior-energy consumption association map;

[0091] Get the correlation strength coefficient between all nodes;

[0092] Generate a behavior-energy consumption correlation graph based on the correlation strength coefficients between all nodes.

[0093] In this embodiment, human behavior characteristics are quantified and categorized as human behavior nodes in the behavior-energy consumption correlation graph. For example, characteristics such as activity type (standing, walking, working), activity area, and activity time are defined as separate nodes. Activity areas can be divided according to indoor space, with each area set as a node. Activity time can be divided according to different time periods (e.g., weekday mornings, afternoons, weekends, etc.). These nodes comprehensively reflect the different aspects of human behavior.

[0094] In this embodiment, device power consumption nodes are defined based on device power usage characteristics. The device type (lighting fixture, air conditioner, office equipment, etc.), power characteristics under different power usage modes, and harmonic characteristics are used as nodes. For example, for lighting fixtures, power consumption at different brightness levels is set as a node; for air conditioners, power consumption corresponding to different temperature settings in cooling and heating modes is set as a node. This accurately describes the device's power usage behavior.

[0095] In this embodiment, the spatial area state characteristics are used as environment-related nodes in the association map. For example, the temperature state (high temperature, medium temperature, low temperature) and humidity state (high humidity, medium humidity, low humidity) of different indoor areas are used as nodes, which are combined with the personnel behavior nodes and equipment power consumption nodes to construct a node system that comprehensively reflects the relationship between the indoor environment, personnel behavior and equipment power consumption.

[0096] In this embodiment, all nodes include: personnel behavior nodes, equipment power consumption nodes, and environment-related nodes.

[0097] In this embodiment, a behavior-energy consumption correlation graph is generated based on the correlation strength coefficients between all nodes. This includes: creating an empty graph framework containing a set of human behavior nodes P, a set of device power consumption nodes E, and a set of environment-related nodes A. The nodes in each set are initialized according to the previously quantified and classified definitions. For example, the human behavior node set includes nodes for different activity types, activity areas, and activity times; the device power consumption node set includes nodes for different device types, power characteristics, and harmonic characteristics; and the environment-related node set includes nodes for state characteristics such as temperature, humidity, and light intensity in different spatial regions. Node connections are established: All node pairs are traversed. For each pair of nodes (i, j), where i belongs to node set X (X can be P, E, or A) and j belongs to node set Y (Y can be P, E, or A, and X and Y can be the same), the calculated correlation strength coefficient is used to determine whether to establish a connection edge. If the coefficient is greater than a preset threshold (e.g., 0.3, which can be adjusted based on actual conditions), an edge is established between nodes i and j, indicating a certain degree of correlation between the two nodes. Set the edge weight: For the node pair (i, j) that has established a connection edge, set the association strength coefficient The weight of the edge is used as the edge's weight. The weight reflects the closeness of the association between two nodes; the larger the weight, the stronger the association. For example, if the correlation strength coefficient between the "person stays in a certain area for more than 30 minutes node" and the "lighting in that area is turned on node" is 0.8, then the weight of the edge connecting these two nodes in the graph is set to 0.8. Visualization: Use graph visualization tools (such as Graphviz and NetworkX) to visualize the constructed behavior-energy consumption association graph. In the visualization interface, different types of nodes can be distinguished by different shapes and colors. For example, human behavior nodes are represented by circles, equipment power consumption nodes are represented by squares, and environment-related nodes are represented by triangles.

[0098] The beneficial effects of this technical solution include: by quantifying and classifying human behavior characteristics and defining the status characteristics of equipment power nodes and spatial regions, a more comprehensive and detailed behavior-energy consumption correlation map is constructed. Compared with existing technologies, this approach optimizes the implementation of energy-saving strategies by accurately capturing the correlation strength between nodes, and improves the intelligence, accuracy, and real-time nature of energy consumption management.

[0099] Example 5:

[0100] The embodiment of the present invention provides an indoor intelligent energy-saving method based on the Internet of Things and AI, which obtains the correlation strength coefficient between all nodes, including:

[0101] Perform feature dimension analysis on all nodes to determine the feature dimensions corresponding to each node and the feature values corresponding to each feature dimension;

[0102] The correlation strength coefficient between every two nodes is determined based on several feature dimensions corresponding to each node and the feature value corresponding to each feature dimension: ;

[0103] in, is the correlation strength coefficient between node i and node j, and Respectively represent the values after normalizing the feature values of node i and node j on the kth feature dimension, is the preset weight of the kth feature dimension, and , and Respectively represent the rate of change of the eigenvalues of node i and node j in the kth feature dimension over time, The number of feature dimensions determined when determining the correlation strength coefficient between node i and node j, The maximum value symbol.

[0104] In this embodiment, the preset weights are determined based on the degree of influence of each feature dimension on the node association strength in the actual scenario. For example, in an indoor smart energy-saving scenario, if temperature has a greater impact on device energy consumption, the weight of the feature dimension related to temperature can be set relatively high; while the weight of some feature dimensions that have a smaller impact on the overall association can be reduced accordingly. By introducing weights, the importance of different feature dimensions in calculating the association strength can be more accurately reflected;

[0105] In this embodiment, the rate of change over time: for personnel behavior nodes, such as the rate of change of activity time, the rate of change of power of equipment power nodes, the rate of change of temperature of environment-related nodes, etc., are all calculated according to the corresponding time series data.

[0106] In this embodiment, for node types with fewer dimensions than the original, virtual dimensions can be added under specific conditions. The data values for these virtual dimensions can be set to constants (e.g., 0) or generated using an algorithm based on existing dimensional data. This allows the two node types to have the same number of dimensions when calculating the correlation strength coefficient, allowing k to have the same value range.

[0107] The beneficial effects of the above technical solution are: by analyzing the characteristic dimensions of nodes and accurately calculating the correlation strength coefficient between nodes, the accuracy and reliability of the behavior-energy consumption correlation map are improved. By introducing weight factors through standardization and time change rate, a more refined analysis of the correlation between nodes is ensured, thereby optimizing energy-saving decisions and strategies, and improving energy-saving efficiency and intelligence level.

[0108] Example 6:

[0109] This embodiment of the present invention provides an indoor smart energy-saving method based on the Internet of Things and AI. It generates a dynamic energy-saving strategy based on a behavior-energy consumption correlation map and preset energy-saving goals and comfort constraints, including:

[0110] Determine the operating parameters of each indoor device based on the preset energy-saving target and comfort constraints, and encode the operating parameters of each indoor device to form a multidimensional vector;

[0111] A solution space is constructed based on all multidimensional vectors, where each multidimensional vector corresponds to a particle in the solution space;

[0112] Obtain historical energy consumption data of indoor equipment, build an energy consumption estimation model based on the behavior-energy consumption correlation map, and obtain the total energy consumption;

[0113] Determine the degree of energy consumption deviation based on the preset energy saving target and total energy consumption;

[0114] Obtain several comfort indicators based on the behavior-energy consumption correlation map;

[0115] The comfort deviation degree is obtained based on the preset comfort constraint and the comfort index;

[0116] The energy consumption deviation and comfort deviation are combined according to the preset weights to obtain the fitness value of each particle;

[0117] Monitor the fitness value of each particle in real time and determine the corresponding termination condition based on the fitness value of each particle;

[0118] Based on the rules of the MOPSO algorithm, each particle updates its speed and position according to its own historical optimal position and the global optimal position of the particle swarm corresponding to each particle in the solution space until the termination condition is reached and the update stops;

[0119] The position of each particle in the solution space that stops updating is obtained, and then the operating parameters of each device are determined to generate a dynamic energy-saving strategy.

[0120] In this embodiment, the operating parameters of each indoor device are encoded. For example, for an indoor environment containing air conditioning, lighting, and ventilation, the solution vector can be represented as [air conditioning set temperature, air conditioning fan speed level, air conditioning cooling / heating mode, lighting brightness, lighting on / off mode, ventilation speed level, ventilation on / off time]. Through this encoding method, each point in the solution space accurately corresponds to a specific combination of device operating parameters.

[0121] In this embodiment, an energy consumption estimation model is constructed. For example, for air conditioning equipment, energy consumption data for different set temperatures, wind speed levels, and cooling / heating modes is analyzed to establish a mathematical model linking energy consumption and these parameters. When calculating the energy consumption for the device operating parameter combinations represented by the particles, the parameters of each device are substituted into the corresponding energy consumption model, and the total energy consumption is accumulated. This total energy consumption is then compared with a preset target of reducing total energy consumption by at least 30%, and the degree to which the energy consumption deviates from the target is calculated.

[0122] In this embodiment, several comfort indicators are derived based on a behavior-energy consumption correlation graph. While the graph itself does not directly present comfort indicators, they can be inferred through the relationships between nodes and edges in the graph. The association between human behavior nodes and environmental status nodes can provide clues. For example, when a person is active in a certain area, the corresponding environmental status indicators such as temperature and humidity can serve as basic data for comfort assessment. From the perspective of equipment power consumption nodes, the operating status of air conditioners, for example, is closely correlated with temperature nodes, which can reflect whether the indoor temperature adjustment is within the comfortable range. Based on these correlations, a comfort index calculation model can be constructed. For example, if the temperature comfort range is set to 24°C - 26°C, the corresponding regional temperature node is found in the graph to determine whether it is within this range, thereby deriving the temperature comfort index. Similarly, for humidity, 40% - 60% is set as the comfortable range and the data from the humidity nodes in the graph are combined for evaluation.

[0123] In this embodiment, the comfort index includes comfort indexes such as temperature, humidity and light intensity.

[0124] The beneficial effects of this technical solution include: By combining energy-saving goals with comfort constraints, the MOPSO algorithm optimizes equipment operating parameters and generates a dynamic energy-saving strategy. Compared with existing technologies, this method accurately balances energy conservation and comfort, achieving efficient energy management and intelligent regulation through the particle swarm optimization algorithm, improving the accuracy and adaptability of energy conservation and user experience.

[0125] Example 7:

[0126] The embodiment of the present invention provides an indoor intelligent energy-saving method based on the Internet of Things and AI, which determines the corresponding termination condition based on the fitness value of each particle, including:

[0127] The corresponding termination iteration coefficient is determined based on the fitness value of each particle: ;

[0128] in, is the termination iteration coefficient corresponding to the fitness value of each particle, is the fitness value of each particle at the g-th iteration, is the fitness value of each particle at the g+1th iteration, is the weight coefficient corresponding to the g-th iteration and g+1-th iteration of each particle, is the second-order differential impact factor, with a value range of (0, 1). is the number of iterations, is the adjustment factor, and its value range is (0, 0.5);

[0129] The corresponding termination condition is determined based on the termination iteration coefficient of each particle.

[0130] In this embodiment, The relative ratio of the second-order difference to the first-order difference of the fitness value change can reflect the change in the fitness value trend. For example, if the fitness value originally showed a stable downward trend, the second-order difference would be close to 0; if a sudden change occurs, the absolute value of the second-order difference will increase.

[0131] In this embodiment, It represents the cumulative sum of the relative proportions of the second-order differences to the first-order differences in all iterative steps, and is used to further adjust the denominator so that the calculation results can more accurately reflect the convergence state of the algorithm.

[0132] In this embodiment, the weight coefficients corresponding to the g-th iteration and the g+1-th iteration of each particle can be set according to the actual situation. For example, as the number of iterations increases, the later iteration steps may be more critical and can be gradually increased. For example, in the early iteration (i≤N / 2), The value range is 0.005-0.01; in later iterations (i>N / 2), the value range is 0.01-0.02.

[0133] In this embodiment, the adjustment factor is used to adjust the influence of the second-order difference on the calculation result.

[0134] The beneficial effect of this technical solution is that by introducing a termination iteration coefficient, the stopping condition of the particle swarm optimization algorithm can be precisely controlled. Compared with existing technologies, this method, based on the fitness changes of particles and the second-order difference influence factor, achieves more flexible and precise termination condition setting, improving the algorithm's convergence speed and optimization accuracy, thereby enhancing the intelligence and stability of the energy-saving strategy.

[0135] Example 8:

[0136] The present invention provides an indoor smart energy-saving method based on the Internet of Things and AI. This method uses IoT devices to execute dynamic energy-saving strategies and monitor the execution results in real time. Based on the execution results, the method optimizes the environmental state matrix and behavior-energy consumption correlation map, including:

[0137] Based on the control interface of the IoT device, the dynamic energy-saving strategy is sent to the corresponding device execution end. At the same time, the device's operating status data and real-time changes in the indoor environment are collected in real time through the sensors on the device.

[0138] The operating status data of the equipment and the real-time change data of the environment are compared and analyzed with the expected effects of the dynamic energy-saving strategy. If the deviation exceeds the preset range, the gradient descent-based algorithm is used to adjust and optimize the parameters of the environmental state deduction model and the behavior-energy consumption correlation map according to the actual execution results.

[0139] In this embodiment, the device execution end is such as an intelligent lighting controller, an air conditioning intelligent gateway, a ventilation equipment driver, etc.

[0140] In this embodiment, parameters of the environmental state deduction model and the behavior-energy consumption correlation map are adjusted and optimized. For example, if it is found that the actual energy consumption reduction does not reach the expected target, analysis is performed to determine whether this is due to inaccurate estimation of certain parameters by the environmental state model or to certain correlation relationships in the behavior-energy consumption correlation map that do not accurately reflect the actual situation. The model and map are then optimized in a targeted manner to improve the accuracy and effectiveness of the dynamic energy-saving strategy.

[0141] The beneficial effects of this technical solution include: By combining IoT devices with AI technology, intelligent energy-saving control of the indoor environment is achieved. First, through the layered collection of environmental data through the IoT, a comprehensive environmental state matrix and behavior-energy consumption correlation map are established. Based on this data, dynamic energy-saving strategies are generated to effectively adjust the balance between energy consumption and comfort. Through real-time monitoring and feedback adjustments, not only energy savings are improved, but also environmental comfort is ensured, avoiding the negative impact of excessive energy conservation on the living experience.

[0142] Example 9:

[0143] The embodiment of the present invention provides an indoor intelligent energy-saving system based on the Internet of Things and AI, such as Figure 2 Shown, including:

[0144] Data collection module: collects indoor environmental data in layers through IoT devices. The environmental data includes basic environmental data and dynamic behavior data.

[0145] Matrix generation module: generates environmental state matrix based on basic environmental data;

[0146] Graph generation module: Generates behavior-energy consumption correlation graph based on dynamic behavior data and environmental state matrix;

[0147] Strategy generation module: Generates dynamic energy-saving strategies based on the behavior-energy consumption correlation map and preset energy-saving goals and comfort constraints;

[0148] Result optimization module: Execute dynamic energy-saving strategies through IoT devices and monitor the execution effects in real time, and optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution effects.

[0149] The beneficial effects of this technical solution include: by collecting indoor environmental data and generating an environmental state matrix and behavior-energy consumption correlation map, energy-saving strategies can be dynamically generated to optimize energy consumption. Through real-time monitoring and feedback on implementation results, strategies can be continuously optimized, improving energy savings while maintaining comfort. This significantly increases energy efficiency and intelligence, while reducing energy waste.

[0150] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An indoor smart energy-saving method based on the Internet of Things and AI, characterized by: include: Step 1: Collect indoor environmental data in layers through IoT devices. The environmental data includes basic environmental data and dynamic behavior data. Step 2: Generate an environmental state matrix based on basic environmental data; Step 3: Generate a behavior-energy consumption correlation map based on dynamic behavior data and the environmental state matrix; Step 4: Generate a dynamic energy-saving strategy based on the behavior-energy consumption correlation map and the preset energy-saving goals and comfort constraints; Step 5: Execute dynamic energy-saving strategies through IoT devices and monitor the execution results in real time. Optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution results.

2. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 1 is characterized in that: Generate an environmental state matrix based on basic environmental data and environmental state deduction model, including: Clean and normalize basic environmental data; A spatiotemporal convolutional neural network is used as the environmental state deduction model, and the processed basic environmental data is used as the model input to output the environmental state matrix.

3. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 1 is characterized in that: Generate behavior-energy consumption correlation maps based on dynamic behavior data and environmental state matrix, including: Extract features from dynamic behavior data to obtain personnel behavior features and equipment power consumption features; Analyze all environmental parameters in the environmental state matrix to obtain the state characteristics of several spatial regions; A behavior-energy consumption correlation map is generated based on personnel behavior characteristics, equipment power consumption characteristics, and spatial area status characteristics.

4. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 3 is characterized in that: Generate a behavior-energy consumption correlation map based on personnel behavior characteristics, equipment power consumption characteristics, and spatial area status characteristics, including: Quantify and classify personnel behavior characteristics as personnel behavior nodes in the behavior-energy consumption correlation map; Define equipment power consumption nodes based on equipment power consumption characteristics; The state characteristics of the spatial region are used as the environment-related nodes of the behavior-energy consumption association map; Get the correlation strength coefficient between all nodes; Generate a behavior-energy consumption correlation graph based on the correlation strength coefficients between all nodes.

5. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 4 is characterized in that: Get the correlation strength coefficients between all nodes, including: Perform feature dimension analysis on all nodes to determine the feature dimensions corresponding to each node and the feature values corresponding to each feature dimension; The correlation strength coefficient between every two nodes is determined based on several feature dimensions corresponding to each node and the feature value corresponding to each feature dimension: ； in, is the correlation strength coefficient between node i and node j, and Respectively represent the values after normalizing the feature values of node i and node j on the kth feature dimension, is the preset weight of the kth feature dimension, and , and Respectively represent the rate of change of the eigenvalues of node i and node j in the kth feature dimension over time, The number of feature dimensions determined when determining the correlation strength coefficient between node i and node j, The maximum value symbol.

6. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 1 is characterized in that: Generate dynamic energy-saving strategies based on the behavior-energy consumption correlation map and preset energy-saving targets and comfort constraints, including: Determine the operating parameters of each indoor device based on the preset energy-saving target and comfort constraints, and encode the operating parameters of each indoor device to form a multidimensional vector; A solution space is constructed based on all multidimensional vectors, where each multidimensional vector corresponds to a particle in the solution space; Obtain historical energy consumption data of indoor equipment, build an energy consumption estimation model based on the behavior-energy consumption correlation map, and obtain the total energy consumption; Determine the degree of energy consumption deviation based on the preset energy saving target and total energy consumption; Obtain several comfort indicators based on the behavior-energy consumption correlation map; The comfort deviation degree is obtained based on the preset comfort constraint and the comfort index; The energy consumption deviation and comfort deviation are combined according to the preset weights to obtain the fitness value of each particle; Monitor the fitness value of each particle in real time and determine the corresponding termination condition based on the fitness value of each particle; Based on the rules of the MOPSO algorithm, each particle updates its speed and position according to its own historical optimal position and the global optimal position of the particle swarm corresponding to each particle in the solution space until the termination condition is reached and the update stops; The position of each particle in the solution space that stops updating is obtained, and then the operating parameters of each device are determined to generate a dynamic energy-saving strategy.

7. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 6 is characterized in that: The corresponding termination conditions are determined based on the fitness value of each particle, including: The corresponding termination iteration coefficient is determined based on the fitness value of each particle: ； in, is the termination iteration coefficient corresponding to the fitness value of each particle, is the fitness value of each particle at the g-th iteration, is the fitness value of each particle at the g+1th iteration, is the weight coefficient corresponding to the g-th iteration and g+1-th iteration of each particle, is the second-order differential impact factor, with a value range of (0, 1). is the number of iterations, is the adjustment factor, and its value range is (0, 0.5); The corresponding termination condition is determined based on the termination iteration coefficient of each particle.

8. The indoor intelligent energy-saving method based on the Internet of Things and AI according to claim 1 is characterized in that: Execute dynamic energy-saving strategies through IoT devices and monitor the execution results in real time. Optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution results, including: Based on the control interface of the IoT device, the dynamic energy-saving strategy is sent to the corresponding device execution end. At the same time, the device's operating status data and real-time changes in the indoor environment are collected in real time through the sensors on the device. The operating status data of the equipment and the real-time change data of the environment are compared and analyzed with the expected effects of the dynamic energy-saving strategy. If the deviation exceeds the preset range, the gradient descent-based algorithm is used to adjust and optimize the parameters of the environmental state deduction model and the behavior-energy consumption correlation map according to the actual execution results.

9. An indoor smart energy-saving system based on the Internet of Things and AI, applied to the indoor smart energy-saving method based on the Internet of Things and AI according to any one of claims 1 to 8, characterized in that: include: Data collection module: collects indoor environmental data in layers through IoT devices. The environmental data includes basic environmental data and dynamic behavior data. Matrix generation module: generates environmental state matrix based on basic environmental data; Graph generation module: Generates behavior-energy consumption correlation graph based on dynamic behavior data and environmental state matrix; Strategy generation module: Generates dynamic energy-saving strategies based on the behavior-energy consumption correlation map and preset energy-saving goals and comfort constraints; Result optimization module: Execute dynamic energy-saving strategies through IoT devices and monitor the execution effects in real time, and optimize the environmental state matrix and behavior-energy consumption correlation map based on the execution effects.

Images