Public building air conditioner load decomposition analysis method and device based on two-stage attention mechanism fused convolutional neural network and long short-term memory network, and electronic equipment
By fusing convolutional neural networks and long short-term memory networks through a two-stage attention mechanism, and combining feature and temporal attention mechanisms, the accuracy problem of air conditioning load monitoring and analysis in public buildings is solved, enabling precise assessment and potential analysis of air conditioning energy consumption.
Patent Information
- Application Number
- CN202411126371.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-15
AI Technical Summary
In existing technologies, the monitoring, analysis, and interactive control of air conditioning load in public buildings lack comprehensive building air conditioning monitoring data, and the air conditioning load estimation methods are crude, resulting in inaccurate assessment of air conditioning energy consumption by the power grid, and a lack of real-time performance and accuracy.
A method based on a two-stage attention mechanism that integrates convolutional neural networks and long short-term memory networks is adopted. Clustering algorithms are used to distinguish between air conditioning operating days and non-operating days. A non-air conditioning load prediction model is established by combining a CNN-LSTM network. Feature and time attention mechanisms are introduced on the input and output sides to dynamically adjust feature and time weights. Finally, the air conditioning load is decomposed by dynamic difference method.
It improves the accuracy of air conditioning load forecasting, provides precise air conditioning energy consumption analysis tools, and helps to study the energy consumption and adjustable potential of air conditioning in public buildings.
Smart Images

Figure CN119026291A_ABST
Abstract
Description
Technical Field
[0001] The invention discloses a method for decomposing and analyzing the air conditioning load of a public building based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, and relates to a method, a device and an electronic device for decomposing the air conditioning load of a public building. Background Art
[0002] Air conditioning, as a device that can regulate indoor temperature, has been widely used. However, as the type of energy consumption with the highest proportion in the whole society, the energy consumption of building air conditioning accounts for about 15% of the total energy consumption of the whole society, and the air conditioning load in summer accounts for more than 30%. In addition, due to the relatively weak awareness of air conditioning energy conservation, there is a serious problem of air conditioning energy waste, and there is huge room for energy conservation.
[0003] At present, the monitoring, analysis and interactive control of air conditioning loads are lacking comprehensive building air conditioning monitoring data, the air conditioning load estimation method is relatively rough, and there is a lack of air conditioning energy consumption benchmarking evaluation methods. In particular, the current power grid can only estimate the user's air conditioning load by subtracting the real-time threshold load from the typical daily baseline load for public buildings without air conditioning sub-item measurement data. This method has poor real-time performance and accuracy. Therefore, building a neural network model to decompose the user's air conditioning load in real time is of great practical significance for the power grid to accurately evaluate the user's energy consumption level and provide corresponding energy-saving strategies. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a decomposition and analysis method for the air-conditioning load of public buildings based on a two-stage attention mechanism fused with a convolutional neural network and a long short-term memory (dual attention mechanism-convolutional neural network-longshort-term memory, DA-CNN-LSTM) network, establish a public building air-conditioning load decomposition method based on a CNN-LSTM network, and improve the accuracy of the model by establishing a dual attention mechanism (DA), which provides a powerful analysis tool for studying the energy consumption and adjustable potential of air-conditioning in public buildings.
[0005] The present invention provides a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, comprising the following steps:
[0006] Based on the clustering algorithm, a model for distinguishing air-conditioning operation days from non-operation days was established. The air-conditioning non-operation days after distinction were used as the training set of the neural network prediction model, and the air-conditioning operation days were used as the test set of the model.
[0007] The non-air conditioning load prediction model is established by using CNN convolutional neural network combined with LSTM long short-term memory network;
[0008] A feature attention mechanism is established on the input side of the non-air-conditioning load forecasting model to quantify the correlation between input feature variables, thereby dynamically adjusting the input feature weights and enhancing the guidance of strongly correlated feature variables;
[0009] A temporal attention mechanism is established on the output side of the non-air-conditioning load forecasting model to capture the dependencies of temporal information, dynamically adjust the output of hidden states, and enhance the information expression of key time steps.
[0010] Based on the results of distinguishing between air-conditioning operation days and non-operation days in public buildings, a public building air-conditioning load decomposition method based on dynamic subtraction method is established, that is, the air-conditioning load of public buildings is obtained by dynamically subtracting the threshold load curve of air-conditioning operation days from the non-air-conditioning load curve obtained by the non-air-conditioning load prediction model.
[0011] Furthermore, the method for establishing a model for distinguishing air conditioner operation days from non-operation days based on a clustering algorithm is as follows:
[0012] Based on the clustering algorithm, a clustering method for the threshold load curve of public building users is established to distinguish between the days when the user's air conditioner is turned on and the days when it is not in operation. The user's daily threshold load curve is input into the clustering algorithm and clustered into 2 clusters.
[0013] Select a clustering algorithm and use the actual sample that is most similar to other samples in each cluster as the cluster center to improve the clustering algorithm's sensitivity to noise and outliers and its tendency to fall into local optimality;
[0014] The clustering algorithm outputs the dates corresponding to the two different curves after classification, representing the air conditioner operation days and non-operation days respectively. This method is more accurate than distinguishing the air conditioner on and off days based on seasonal temperature changes and other experience.
[0015] Furthermore, the method of selecting the clustering algorithm is:
[0016] First, for a given cluster number of 2, two representative objects are randomly selected as the initial cluster centers, the distance between each remaining object and the representative object is calculated and assigned to the nearest cluster, and the corresponding clustering results are generated;
[0017] Then, the iterative process begins, and for each iteration, a randomly selected non-central point replaces one of the original central points and the clustering results are recalculated;
[0018] If the clustering effect is improved, keep the replacement, otherwise restore the original center point. When the replacement no longer improves the clustering effect, the iteration stops;
[0019] The cost function is used to measure the quality of the clustering results. This function is used to measure the average dissimilarity between the object and the center point. The specific definition is as follows:
[0020]
[0021] Among them, p is a point in space, that is, a given object; o i Cluster C i The center point of the dataset; E is the sum of squared deviations of all objects in the dataset.
[0022] Furthermore, the method of establishing a non-air conditioning load prediction model by using a CNN convolutional neural network combined with an LSTM long short-term memory network is as follows:
[0023] Establish the factors affecting the load of public buildings, including historical load, meteorological information and date type;
[0024] The historical load includes the historical load of the past day, the load at the same time in the past week, and the load at the same time on the same characteristic day in the past month.
[0025] Meteorological information includes temperature, humidity, wind speed and weather;
[0026] Date types include time variables, weekday and rest day variables, and holiday variables.
[0027] The load influencing factors of public building users are taken as the input features of the training set and input into the CNN-LSTM network model in the form of a sliding window. The non-air-conditioning load of public building users in the non-air-conditioning season is taken as the target feature of the training set to train the CNN-LSTM network.
[0028] Establish CNN-LSTM network model training samples;
[0029] Among them, in the CNN convolutional neural network, the input layer, convolution layer, pooling layer, convolution layer, pooling layer, fully connected layer and output layer are connected in sequence.
[0030] Using the trained model, the load influencing factors at the corresponding time of the air-conditioning season and the non-air-conditioning load on typical days in the non-air-conditioning season are input from the input layer in the form of a sliding window. The trained model parameters are obtained through the CNN layer and the three-layer LSTM layer. The predicted non-air-conditioning load values at each time of each day in the air-conditioning season are output through the output layer.
[0031] Furthermore, the method for establishing a CNN-LSTM network model training sample is:
[0032] In the convolutional layer operation, the CNN network greatly reduces the number of parameters in the training process through local neuron connections and convolution kernel weight sharing, improves the model training speed, and enables the model to more effectively extract feature information from the original data;
[0033] In the pooling layer, the original data is abstracted and understood to reduce the feature dimension, which effectively reduces the number of training parameters while reducing the degree of model overfitting and improving the efficiency of feature data extraction;
[0034] LSTM long short-term memory network evolved from RNN recurrent neural network. LSTM has LSTM memory block. Based on the structure of input layer, hidden layer and output layer of traditional RNN network, the structure of hidden layer is improved. The gate mechanism is introduced to control the path of information transmission, and the information passing through the network is selectively memorized or deleted through the gate, so as to selectively memorize effective information and delete invalid redundant information in long-term prediction.
[0035] The state of the LSTM memory block in the corresponding time period is the cell state, which is the old cell state, the current cell state, and the updated cell state in chronological order;
[0036] Each memory block has three "gating" structures, including input gate, output gate and forget gate, through which the cell state is protected and controlled, that is, the time information is stored and transmitted;
[0037] The forget gate is responsible for deciding how much of the cell state from the previous moment to retain in the cell state at the current moment, that is, deciding what information to discard from the cell state. The formula is:
[0038] f t =σ(W f *[h t-1 ,x t ]+b f )
[0039] In the formula, h t-1 and h t are the hidden layer states at time t-1 and t, respectively, x t-1 and x t are the input values at time t-1 and t respectively, W f is the weight matrix, b f is the deviation, σ is the sigmoid function;
[0040] The input gate is responsible for deciding how much of the current input to the current cell state to retain. The formula is:
[0041] i t =σ(W i *[h t-1 ,x t ]+b i )
[0042]
[0043] In the formula, i tis the input value of the input gate at time t, Create a new cell state value vector for the tanh layer at time t, W i and W C is the weight coefficient matrix, b i and b C is the bias term;
[0044] Update the old cell state, the formula is:
[0045]
[0046] In the formula, C t-1 and C t are the cell states at time t-1 and time t respectively;
[0047] The output gate is responsible for determining how many outputs the current cell state has. The formula is:
[0048] o t =σ(W o *[h t-1 ,x t ]+b o )
[0049] h t =o t *tanh(C t )
[0050] In the formula, o t is the output value of the output gate at time t, W o is the weight coefficient matrix, b o is the bias term.
[0051] Furthermore, the method of establishing a feature attention mechanism on the input side of the non-air conditioning load prediction model, quantifying the correlation between input feature variables, dynamically adjusting the input feature weights, and enhancing the guidance of strongly correlated feature variables is as follows;
[0052] On the input side, a feature attention mechanism is established to explore the correlation between the input features of weather, time and historical load and the non-air conditioning load value at the corresponding moment, dynamically allocate the attention weight of each input feature, focus on the impact of important feature variables, and reduce the information of weakly related or redundant irrelevant features;
[0053] In order to obtain the correlation between each influencing feature and the non-air conditioning load at the current moment, the feature attention mechanism is used to encode the quantized weights;
[0054] After the feature attention mechanism is established, the input of the CNN-LSTM network is no longer the original input feature value, but the weighted input feature value considering the correlation degree. Through the feature attention mechanism, the contribution rate of each input feature is adaptively extracted to improve the prediction accuracy.
[0055] Furthermore, the method of encoding quantized weights using the feature attention mechanism is:
[0056] The input features at the current moment and the hidden layer state h at the previous moment t-1 and memory information t-1 As the input of the feature attention mechanism, the attention weight of each input feature at the current moment is calculated respectively, and the weight is quantified using the calculation method of the multi-layer perceptron. The weight calculation is as follows:
[0057]
[0058] Where V e , W e and U e is the multi-layer perceptron weight matrix for calculating attention weights, b e is the bias term;
[0059] Use the Softmax function to Normalize the feature attention weights so that they sum to 1, as shown in the following formula:
[0060]
[0061] The characteristic correlation coefficient The corresponding input affects the characteristic value Multiply to get the associated features that consider the contribution rate of different inputs affecting the features
[0062]
[0063] Hidden state h t Then update as follows:
[0064]
[0065] Among them, f CNN-LSTM is the LSTM network unit.
[0066] Furthermore, the method of establishing a time attention mechanism on the output side of the non-air-conditioning load prediction model, capturing the dependency of time series information, dynamically adjusting the output of hidden states, and enhancing the information expression of key time steps is as follows;
[0067] Establish a time attention mechanism on the decoding output side to obtain the hidden state weights of the corresponding time series, obtain the influence of the time series state at the past moment on the non-air conditioning load output at the current moment, and strengthen the influence of the strongly related moment state information;
[0068] In order to obtain the correlation between the historical time series information and the current output non-air conditioning load value, the temporal attention mechanism is used to decode the quantized weights;
[0069] Building a dual attention mechanism
[0070] On the basis of the original CNN-LSTM network, the feature attention mechanism is introduced before the first LSTM layer, and the time attention mechanism is introduced after the last LSTM layer. The dual attention mechanism can adaptively mine the relationship between load and influencing factors, obtain the contribution rate of each influencing factor at different times, and improve the accuracy of single-point prediction; it can also mine the correlation between the current load and the historical key moment information, and improve the accuracy of long-term time series prediction;
[0071] That is, the threshold load and load influencing factors in the non-air-conditioning season pass through the input layer, convolution layer, pooling layer, feature attention mechanism, LSTM layer 1, LSTM layer 2, LSTM layer 3, temporal attention mechanism, fully connected layer and output layer in sequence to obtain the non-air-conditioning load in the air-conditioning season; LSTM layer 1, LSTM layer 2 and LSTM layer 3 are LSTM layers, and the convolution layer, pooling layer and fully connected layer are CNN layers.
[0072] Furthermore, the method of decoding quantized weights of the temporal attention mechanism is:
[0073] The hidden layer state h containing the time series information at each historical moment τ (τ=1,2,…,t,…,T) and the hidden layer state h at the previous moment of historical moment t t and memory information t As the input of the temporal attention mechanism, the attention weights of the historical moment t and each historical moment are calculated respectively, and quantized using the calculation method of the multi-layer perceptron. The weight calculation is as follows:
[0074]
[0075] In the formula, V d and W d is the multi-layer perceptron weight matrix for calculating attention weights, U d is the bias term;
[0076] Use the Softmax function to Normalize the data so that the sum of the temporal attention weights is 1, as shown in the following formula:
[0077]
[0078] Quantify the importance of the state information of the τth hidden layer for the predicted output at time t, and set all the weights The weighted sum of the corresponding hidden layer state information is used to obtain the comprehensive information c related to the time series state characteristics. t , as shown below:
[0079]
[0080] The non-air conditioning load value y to be predicted at time t t Comprehensive information related to the characteristics of the temporal state c t After fusion through a single-layer feedforward network, the input of the CNN-LSTM network at each time t is obtained
[0081]
[0082] In the formula, and The weights and biases of a single-layer feed-forward network are calculated for fusion input respectively;
[0083] h t The CNN-LSTM network in the following formula iterates T times from the initial moment to the T moment:
[0084]
[0085] The hidden layer state h at the final time T T With comprehensive information T The single-layer feedforward network is used for integration, and finally the single-layer feedforward network is used for dimension transformation to obtain the predicted value of the non-air-conditioning load to be predicted. As shown below:
[0086]
[0087] Where W y and b w are the weights and biases of the single-layer feedforward network that integrates the output, V y and b y are the weights and biases of the feed-forward network for dimension transformation, respectively.
[0088] Furthermore, the modeling method for establishing a public building air conditioning load decomposition model based on the dynamic difference method based on the seasonal operation characteristics of the public building load is:
[0089] The building is divided into air-conditioning season and non-air-conditioning season according to whether the air conditioner is turned on or not, and the following constraints are established:
[0090] P 非空调季关口负荷 ≈P 非空调季非空调负荷
[0091] P 空调季关口负荷 =P 空调季非空调负荷 +P 空调季空调负荷
[0092] Establish a method to dynamically predict the non-air-conditioning load in the air-conditioning season through the threshold load in the non-air-conditioning season;
[0093] Due to the following constraints:
[0094] P 空调负荷 =P 关口负荷 -P 非空调负荷
[0095] For the air-conditioning operation days divided by clustering, a public building air-conditioning load decomposition method is established, which uses the real-time measured gateway load actual value and the non-air-conditioning load prediction value dynamically predicted by the neural network to decompose the dynamic prediction value of the air-conditioning load. Based on the non-air-conditioning load prediction result of the air-conditioning season, the air-conditioning load prediction value of the air-conditioning season is obtained by real-time subtraction.
[0096] An electronic device includes one or more processors for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors execute a decomposition and analysis method for air conditioning load for public buildings based on a DA-CNN-LSTM network.
[0097] A storage medium having a computer program stored therein, wherein the computer program is configured to execute a decomposition and analysis method of air conditioning load for public buildings using a DA-CNN-LSTM network when running.
[0098] The beneficial effects of the present invention are:
[0099] (1) A non-air conditioning load forecasting method was established based on the CNN-LSTM neural network;
[0100] (2) The accuracy of the load forecasting model is improved by introducing the dual attention mechanism (DA);
[0101] (3) Based on the seasonal characteristics of air-conditioning load in public buildings, a method was established to predict the non-air-conditioning load in the air-conditioning season by using the non-air-conditioning threshold load. The air-conditioning load of public buildings was then decomposed by differentiating the measurable real-time threshold load of the air-conditioning season with the predicted non-air-conditioning load. This method provides a powerful analytical tool for studying the energy consumption and adjustable potential of air-conditioning in public buildings.
[0102] Description of the attached figures and tables
[0103] Figure 1 It is a schematic diagram of the method flow of the present invention.
[0104] Figure 2 This is a diagram of the CNN network structure used in the present invention.
[0105] Figure 3 This is a diagram of the LSTM network structure used in the present invention.
[0106] Figure 4 This is a structural diagram of the CNN-LSTM network model used in the present invention.
[0107] Figure 5 Schematic diagram of the feature attention mechanism (FA) used in the present invention.
[0108] Figure 6 Schematic diagram of the temporal attention mechanism (TA) used in the present invention.
[0109] Figure 7 This is a structural diagram of the DA-CNN-LSTM network model used in the present invention.
[0110] Figure 8 This is a structural diagram of the public building air conditioning load decomposition method used in the present invention.
[0111] Fig. 9 This is a structural schematic diagram of the analysis device of the public building air conditioning load decomposition analysis method based on a two-stage attention mechanism fusing a convolutional neural network and a long short-term memory network in the present invention.
[0112] Fig.10 This is a schematic diagram of the structure of a computer device in some embodiments of the present invention. DETAILED DESCRIPTION
[0113] In order to more clearly illustrate the technical solution of the present invention, the present invention will be further described below; obviously, the following description is only a part of the embodiments, and for ordinary technicians in this field, without paying creative work, the technical solution of the present invention can also be applied to other similar scenarios based on these; in order to more clearly illustrate the technical solution of the present invention, the following description is combined with the attached Figure 1-10 The technical solution of the present invention is further described in detail.
[0114] Embodiment 1:
[0115] like Figure 1-8 As shown, a decomposition and analysis method for air conditioning load in public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network includes the following steps:
[0116] The present invention provides a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, comprising the following steps:
[0117] Based on the clustering algorithm (K-Medoids), a model for distinguishing air-conditioning operation days from non-operation days was established. The air-conditioning non-operation days after distinction were used as the training set of the neural network prediction model, and the air-conditioning operation days were used as the test set of the model.
[0118] The non-air conditioning load prediction model is established by using CNN convolutional neural network combined with LSTM long short-term memory network;
[0119] A feature attention mechanism (FA) is established on the input side of the non-air-conditioning load forecasting model to quantify the correlation between input feature variables, thereby dynamically adjusting the input feature weights and enhancing the guidance of strongly correlated feature variables;
[0120] A temporal attention mechanism (TA) is established on the output side of the non-air-conditioning load forecasting model to capture the dependencies of temporal information, dynamically adjust the output of hidden states, and enhance the information expression of key time steps;
[0121] Based on the results of distinguishing between air-conditioning operation days and non-operation days in public buildings, a public building air-conditioning load decomposition method based on dynamic subtraction method is established, that is, the air-conditioning load of public buildings is obtained by dynamically subtracting the threshold load curve of air-conditioning operation days from the non-air-conditioning load curve obtained by the non-air-conditioning load prediction model.
[0122] Embodiment 2:
[0123] The present invention provides a modeling method for establishing a model for distinguishing between air-conditioning operation days and non-operation days, and the modeling method is:
[0124] Based on the clustering algorithm (K-Medoids), a clustering method for the threshold load curves of public building users is established to distinguish between the days when the user's air conditioner is turned on and the days when the air conditioner is not turned on. The user's daily threshold load curve is input into the clustering algorithm and set to be clustered into 2 clusters.
[0125] A clustering algorithm (K-Medoids) is selected, and the actual sample that is most similar to other samples in each cluster is used as the cluster center to improve the defects of the K-Means clustering algorithm, which is sensitive to noise and outliers and prone to falling into local optimality.
[0126] The specific steps of the clustering algorithm are:
[0127] First, for a given cluster number of 2, two representative objects are randomly selected as the initial cluster centers, the distance between each remaining object and the representative object is calculated and assigned to the nearest cluster, and the corresponding clustering results are generated;
[0128] Then, the iterative process begins, and for each iteration, a randomly selected non-central point replaces one of the original central points and the clustering results are recalculated;
[0129] If the clustering effect is improved, keep the replacement, otherwise restore the original center point. When the replacement no longer improves the clustering effect, the iteration stops.
[0130] The cost function is used to measure the quality of the clustering results. This function is used to measure the average dissimilarity between the object and the center point. The specific definition is as follows:
[0131]
[0132] Among them, p is a point in space, that is, a given object; o i Cluster C i The center point of the dataset; E is the sum of squared deviations of all objects in the dataset.
[0133] The clustering algorithm (K-Medoids) is used to output the dates corresponding to the two different curves after classification, which represent the air conditioner operation days and non-operation days respectively. This method is more accurate than distinguishing the air conditioner switch days based on seasonal temperature changes and other experience.
[0134] Embodiment 3:
[0135] The method for establishing the non-air conditioning load prediction model in the present invention is:
[0136] Establish the factors affecting the load of public buildings, including historical load, meteorological information and date type;
[0137] The historical load includes the historical load of the past day, the load at the same time in the past week, and the load at the same time on the same characteristic day in the past month.
[0138] Meteorological information includes temperature, humidity, wind speed and weather;
[0139] Date types include time variables, weekday and rest day variables, and holiday variables.
[0140] The load influencing factors of public building users are taken as the input features of the training set and input into the CNN-LSTM network model in the form of a sliding window. The non-air-conditioning load of public building users in the non-air-conditioning season is taken as the target feature of the training set to train the CNN-LSTM network.
[0141] Establish CNN-LSTM network model training samples;
[0142] See attached Figure 2In the CNN convolutional neural network, the input layer, convolution layer, pooling layer, convolution layer, pooling layer, fully connected layer and output layer are connected in sequence.
[0143] In the convolutional layer operation, the CNN network greatly reduces the number of parameters in the training process through local connections of neurons and sharing of convolution kernel weights, improves the model training speed, and enables the model to more effectively extract feature information from the original data.
[0144] In the pooling layer, the original data is abstracted and understood to reduce the feature dimension, which effectively reduces the number of training parameters while reducing the degree of model overfitting and improving the efficiency of feature data extraction.
[0145] The LSTM long short-term memory network evolved from the RNN recurrent neural network. LSTM has an LSTM memory block. Based on the structure of the traditional RNN network input layer, hidden layer and output layer, the structure of the hidden layer is improved. The gate mechanism is introduced to control the path of information transmission, and the information passing through the network is selectively memorized or deleted through the gate, so as to selectively memorize valid information and delete invalid redundant information in long-term prediction.
[0146] like Figure 3 The LSTM memory block shown, the state of the LSTM memory block in the corresponding time period is the cell state, which is the old cell state, the current cell state, and the updated cell state in chronological order;
[0147] Each memory block has three "gating" structures, including input gate, output gate and forget gate, which are used to protect and control the cell state, that is, to store and transmit time information.
[0148] The forget gate is responsible for deciding how much of the cell state from the previous moment to retain in the cell state at the current moment, that is, deciding what information to discard from the cell state. The formula is:
[0149] f t =σ(W f *[h t-1 ,x t ]+b f )
[0150] In the formula, h t-1 and h t are the hidden layer states at time t-1 and t, respectively, x t-1 and x t are the input values at time t-1 and t respectively, W f is the weight matrix, b f is the deviation, σ is the sigmoid function;
[0151] The input gate is responsible for deciding how much of the current input to the current cell state to retain. The formula is:
[0152] i t =σ(W i *[h t-1 ,x t ]+b i )
[0153]
[0154] In the formula, i t is the input value of the input gate at time t, Create a new cell state value vector for the tanh layer at time t, W i and W C is the weight coefficient matrix, b i and b C is the bias term;
[0155] Update the old cell state, the formula is:
[0156]
[0157] In the formula, C t-1 and C t are the cell states at time t-1 and time t respectively;
[0158] The output gate is responsible for determining how many outputs the current cell state has. The formula is:
[0159] o t =σ(W o *[h t-1 ,x t ]+b o )
[0160] h t =o t *tanh(C t )
[0161] In the formula, o t is the output value of the output gate at time t, W o is the weight coefficient matrix, b o is the bias term.
[0162] Use a trained model such as Figure 4 As shown in the figure, the load influencing factors at the corresponding time of the air-conditioning season and the non-air-conditioning load on typical days in the non-air-conditioning season are input from the input layer in the form of a sliding window. The trained model parameters are obtained through the CNN layer and the three-layer LSTM layer. The predicted non-air-conditioning load values at each time of each day in the air-conditioning season are output through the output layer.
[0163] Specifically, the threshold load and load influencing factors in the non-air-conditioning season pass through the input layer, convolution layer, pooling layer, LSTM layer 1, LSTM layer 2, LSTM layer 3, fully connected layer and output layer in sequence to obtain the non-air-conditioning load in the air-conditioning season; LSTM layer 1, LSTM layer 2 and LSTM layer 3 are LSTM layers, and the convolution layer, pooling layer and fully connected layer are CNN layers.
[0164] Embodiment 4:
[0165] The method of establishing a time attention mechanism on the output side of the non-air conditioning load prediction model of the present invention is:
[0166] On the input side, a feature attention mechanism (FA) is established to explore the correlation between the input features of weather, time and historical load and the non-air-conditioning load value at the corresponding moment, dynamically allocate the attention weight of each input feature, focus on the influence of important feature variables, and reduce the information of weakly related or redundant irrelevant features.
[0167] In order to obtain the correlation between each influencing feature and the non-air-conditioning load at the current moment, the feature attention mechanism is used to encode the quantized weights.
[0168] See attached Figure 5 , the input features at the current moment and the hidden layer state h at the previous moment t-1 and memory information t-1 As the input of the feature attention mechanism, the attention weight of each input feature at the current moment is calculated respectively, and the weight is quantified using the calculation method of the multi-layer perceptron. The weight calculation is as follows:
[0169]
[0170] Where V e , W e and U e is the multi-layer perceptron weight matrix for calculating attention weights, b e is the bias term.
[0171] Use the Softmax function to Normalize the feature attention weights so that they sum to 1, as shown in the following formula:
[0172]
[0173] The characteristic correlation coefficient The corresponding input affects the characteristic value Multiply to get the associated features that consider the contribution rate of different inputs affecting the features
[0174]
[0175] Hidden state h t Then update as follows:
[0176]
[0177] Among them, f CNN-LSTM is the LSTM network unit.
[0178] After the feature attention mechanism (FA) is established, the input of the CNN-LSTM network is no longer the original input feature value, but the weighted input feature value considering the magnitude of the correlation. Through the feature attention mechanism, the contribution rate of each input feature is adaptively extracted to improve the prediction accuracy.
[0179] Embodiment 5:
[0180] The method of establishing a time attention mechanism on the output side of the non-air conditioning load prediction model of the present invention is:
[0181] A temporal attention mechanism (TA) is established on the decoding output side to obtain the hidden state weights of the corresponding time series, and the influence of the time series state at the past moment on the non-air-conditioning load output at the current moment is obtained, thereby strengthening the influence of the strongly correlated moment state information.
[0182] In order to obtain the correlation between the historical time series information and the output non-air-conditioning load value at the current moment, the temporal attention mechanism is used to decode the quantization weights.
[0183] See attached Figure 6 , the hidden layer state h containing the time series information at each historical moment τ (τ=1,2,…,t,…,T) and the hidden layer state h at the previous moment of historical moment t t and memory information t As the input of the temporal attention mechanism, the attention weights of the historical moment t and each historical moment are calculated respectively, and quantized using the calculation method of the multi-layer perceptron. The weight calculation is as follows:
[0184]
[0185] In the formula, V d and W d is the multi-layer perceptron weight matrix for calculating attention weights, U d is the bias term.
[0186] Use the Softmax function to Normalize the data so that the sum of the temporal attention weights is 1, as shown in the following formula:
[0187]
[0188] Quantify the importance of the state information of the τth hidden layer for the predicted output at time t, and set all the weights The weighted sum of the corresponding hidden layer state information is used to obtain the comprehensive information c related to the time series state characteristics. t , as shown below:
[0189]
[0190] The non-air conditioning load value y to be predicted at time t t Comprehensive information related to the characteristics of the time series state c t After fusion through a single-layer feedforward network, the input of the CNN-LSTM network at each time t is obtained
[0191]
[0192] In the formula, and They are respectively used to calculate the weights and biases of a single-layer feed-forward network that fused the input.
[0193] h t The CNN-LSTM network in the following formula iterates T times from the initial moment to the T moment:
[0194]
[0195] The hidden layer state h at the final time T T With comprehensive information T The single-layer feedforward network is used for integration, and finally the single-layer feedforward network is used for dimension transformation to obtain the predicted value of the non-air-conditioning load to be predicted. As shown below:
[0196]
[0197] Where W y and b w are the weights and biases of the single-layer feedforward network that integrates the output, V y and b y are the weights and biases of the feed-forward network for dimension transformation, respectively.
[0198] Building a Dual Attention Mechanism (DA)
[0199] See attached Figure 7On the basis of the original CNN-LSTM network, the feature attention mechanism (FA) is introduced before the first LSTM layer, and the time attention mechanism (TA) is introduced after the last LSTM layer. The dual attention mechanism (DA) can not only adaptively mine the relationship between load and influencing factors, obtain the contribution rate of each influencing factor at different times, and improve the accuracy of single-point prediction; it can also mine the correlation between the current load and the historical key moment information, and improve the accuracy of long-term time series prediction.
[0200] That is, the threshold load and load influencing factors in the non-air-conditioning season pass through the input layer, convolution layer, pooling layer, feature attention mechanism, LSTM layer 1, LSTM layer 2, LSTM layer 3, temporal attention mechanism, fully connected layer and output layer in sequence to obtain the non-air-conditioning load in the air-conditioning season; LSTM layer 1, LSTM layer 2 and LSTM layer 3 are LSTM layers, and the convolution layer, pooling layer and fully connected layer are CNN layers.
[0201] Embodiment 6:
[0202] The method of establishing the public building air conditioning load decomposition method based on the dynamic difference method is as follows:
[0203] The building is divided into air-conditioning season and non-air-conditioning season according to whether the air conditioner is turned on or not, and the following constraints are established:
[0204] P 非空调季关口负荷 ≈P 非空调季非空调负荷
[0205] P 空调季关口负荷 =P 空调季非空调负荷 +P 空调季空调负荷
[0206] A method for dynamically predicting the non-air-conditioning load in the air-conditioning season through the threshold load in the non-air-conditioning season is established.
[0207] Due to the following constraints:
[0208] P 空调负荷 =P 关口负荷 -P 非空调负荷
[0209] For the air-conditioning operation days separated by clustering, a public building air-conditioning load decomposition method is established to obtain the dynamic prediction value of air-conditioning load by real-time differential analysis of the real value of the gateway load measured in real time and the non-air-conditioning load prediction value dynamically predicted by the neural network. The complete process is as follows: Figure 8 As shown, based on the prediction results of non-air-conditioning load in air-conditioning season, the prediction value of air-conditioning load in air-conditioning season is obtained by real-time difference.
[0210] Embodiment 7:
[0211] According to an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors execute the aforementioned decomposition and analysis method for air conditioning load for public buildings based on the DA-CNN-LSTM network.
[0212] Embodiment 8:
[0213] According to an embodiment of the present invention, a storage medium is further provided, in which a computer program is stored, wherein the computer program is configured to execute the aforementioned decomposition and analysis method of air conditioning load for public buildings based on the DA-CNN-LSTM network when running.
Claims
1. A decomposition and analysis method for air conditioning load in public buildings based on a two-stage attention mechanism fused with convolutional neural network and long short-term memory DA-CNN-LSTM network, It is characterized in that The steps include: Based on the clustering algorithm, a model for distinguishing air-conditioning operation days from non-operation days was established. The air-conditioning non-operation days after distinction were used as the training set of the neural network prediction model, and the air-conditioning operation days were used as the test set of the model. The non-air conditioning load prediction model is established by using CNN convolutional neural network combined with LSTM long short-term memory network; A feature attention mechanism is established on the input side of the non-air-conditioning load forecasting model to quantify the correlation between input feature variables, thereby dynamically adjusting the input feature weights and enhancing the guidance of strongly correlated feature variables; A temporal attention mechanism is established on the output side of the non-air-conditioning load forecasting model to capture the dependencies of temporal information, dynamically adjust the output of hidden states, and enhance the information expression of key time steps; Based on the results of distinguishing between air-conditioning operation days and non-operation days in public buildings, a public building air-conditioning load decomposition method based on dynamic subtraction method is established, that is, the air-conditioning load of public buildings is obtained by dynamically subtracting the threshold load curve of air-conditioning operation days from the non-air-conditioning load curve obtained by the non-air-conditioning load prediction model.
2. According to claim 1, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method for establishing a model for distinguishing air conditioner operation days from non-operation days based on a clustering algorithm is as follows: Based on the clustering algorithm, a clustering method for the threshold load curve of public building users is established to distinguish between the days when the user's air conditioner is turned on and the days when it is not in operation. The user's daily threshold load curve is input into the clustering algorithm and clustered into 2 clusters. Select a clustering algorithm and use the actual sample that is most similar to other samples in each cluster as the cluster center to improve the clustering algorithm's sensitivity to noise and outliers and the defect of being easily trapped in local optimality; Through the clustering algorithm, the dates corresponding to the two different types of curves after classification are output, representing the air-conditioning operation days and non-operation days respectively; this method of distinguishing between air-conditioning operation days and non-operation days is more accurate than distinguishing between air-conditioning switch days based on experience such as seasonal temperature changes.
3. According to claim 2, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method for selecting the clustering algorithm is: First, for a given cluster number of 2, two representative objects are randomly selected as the initial cluster centers, the distance between each remaining object and the representative object is calculated and assigned to the nearest cluster, and the corresponding clustering results are generated; Then, the iterative process begins, and for each iteration, a randomly selected non-central point replaces one of the original central points and the clustering results are recalculated; If the clustering effect is improved, keep the replacement, otherwise restore the original center point. When the replacement no longer improves the clustering effect, the iteration stops; The cost function is used to measure the quality of the clustering results. This function is used to measure the average dissimilarity between the object and the center point. The specific definition is as follows: Among them, p is a point in space, that is, a given object; o i Cluster C i The center point of the dataset; E is the sum of squared deviations of all objects in the dataset.
4. According to claim 1, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method of using CNN convolutional neural network combined with LSTM long short-term memory network to establish a non-air conditioning load prediction model is as follows: Establish the factors affecting the load of public buildings, including historical load, meteorological information and date type; The historical load includes the historical load of the past day, the load at the same time in the past week, and the load at the same time on the same characteristic day in the past month. Meteorological information includes temperature, humidity, wind speed and weather; Date types include time variables, weekday and rest day variables, and holiday variables. The load influencing factors of public building users are taken as the input features of the training set and input into the CNN-LSTM network model in the form of a sliding window. The non-air-conditioning load of public building users in the non-air-conditioning season is taken as the target feature of the training set to train the CNN-LSTM network. Establish CNN-LSTM network model training samples; Among them, in the CNN convolutional neural network, the input layer, convolution layer, pooling layer, convolution layer, pooling layer, fully connected layer and output layer are connected in sequence. Using the trained model, the load influencing factors at the corresponding time of the air-conditioning season and the non-air-conditioning load on typical days in the non-air-conditioning season are input from the input layer in the form of a sliding window. The trained model parameters are obtained through the CNN layer and the three-layer LSTM layer. The predicted non-air-conditioning load values at each time of each day in the air-conditioning season are output through the output layer.
5. According to claim 4, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method for establishing the CNN-LSTM network model training sample is: In the convolutional layer operation, the CNN network greatly reduces the number of parameters in the training process through local neuron connections and convolution kernel weight sharing, improves the model training speed, and enables the model to more effectively extract feature information from the original data; In the pooling layer, the original data is abstracted and understood to reduce the feature dimension, which effectively reduces the number of training parameters while reducing the degree of model overfitting and improving the efficiency of feature data extraction; LSTM long short-term memory network evolved from RNN recurrent neural network. LSTM has LSTM memory block. Based on the structure of input layer, hidden layer and output layer of traditional RNN network, the structure of hidden layer is improved. The gate mechanism is introduced to control the path of information transmission, and the information passing through the network is selectively memorized or deleted through the gate, so as to selectively memorize effective information and delete invalid redundant information in long-term prediction. The state of the LSTM memory block in the corresponding time period is the cell state, which is the old cell state, the current cell state, and the updated cell state in chronological order; Each memory block has three "gating" structures, including input gate, output gate and forget gate, through which the cell state is protected and controlled, that is, time information is stored and transmitted; The forget gate is responsible for deciding how much of the cell state at the previous moment to retain in the cell state at the current moment, that is, deciding what information to discard from the cell state. The formula is: f t =σ(W f *[h t-1 ,x t ]+b f ) In the formula, h t-1 and h t are the hidden layer states at time t-1 and time t, respectively, x t-1 and x t are the input values at time t-1 and t respectively, W f is the weight matrix, b f is the deviation, σ is the sigmoid function; The input gate is responsible for deciding how much of the current input to the current cell state to retain. The formula is: i t =σ(W i *[h t-1 ,x t ]+b i ) In the formula, i t is the input value of the input gate at time t, Create a new cell state value vector for the tanh layer at time t, W i and W C is the weight coefficient matrix, b i and b C is the bias term; Update the old cell state, the formula is: In the formula, C t-1 and C t are the cell states at time t-1 and time t respectively; The output gate is responsible for determining how many outputs the current cell state has. The formula is: the t =σ(W o *[h t-1 ,x t ]+b o ) h t =o t *tanh(C t ) In the formula, o t is the output value of the output gate at time t, W o is the weight coefficient matrix, b o is the bias term.
6. According to claim 1, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method of establishing a feature attention mechanism on the input side of the non-air conditioning load prediction model, quantifying the correlation between input feature variables, dynamically adjusting the input feature weights, and enhancing the guidance of strongly correlated feature variables is as follows; On the input side, a feature attention mechanism is established to explore the correlation between the input features of weather, time and historical load and the non-air conditioning load value at the corresponding moment, dynamically allocate the attention weight of each input feature, focus on the impact of important feature variables, and reduce the information of weakly related or redundant irrelevant features; In order to obtain the correlation between each influencing feature and the non-air conditioning load at the current moment, the feature attention mechanism is used to encode the quantized weights; After the feature attention mechanism is established, the input of the CNN-LSTM network is no longer the original input feature value, but the weighted input feature value considering the correlation degree. Through the feature attention mechanism, the contribution rate of each input feature is adaptively extracted to improve the prediction accuracy.
7. According to claim 6, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method of encoding quantized weights using the feature attention mechanism is: The input features at the current moment and the hidden layer state h at the previous moment t-1 and memory information t-1 As the input of the feature attention mechanism, the attention weight of each input feature at the current moment is calculated respectively, and the weight is quantified using the calculation method of the multi-layer perceptron. The weight calculation is as follows: Where V e , W e and U e is the multi-layer perceptron weight matrix for calculating attention weights, b e is the bias term; Use the Softmax function to Normalize the feature attention weights so that they sum to 1, as shown in the following formula: The characteristic correlation coefficient The corresponding input affects the characteristic value Multiply to get the associated features that consider the contribution rate of different inputs affecting the features Hidden state h t Then update as follows: Among them, f CNN-LSTM is the LSTM network unit.
8. According to claim 1, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method of establishing a time attention mechanism on the output side of the non-air conditioning load prediction model, capturing the dependency of time series information, dynamically adjusting the output of hidden states, and enhancing the information expression of key time steps is as follows; Establish a time attention mechanism on the decoding output side to obtain the hidden state weights of the corresponding time series, obtain the influence of the time series state at the past moment on the non-air conditioning load output at the current moment, and strengthen the influence of the strongly related moment state information; In order to obtain the correlation between the historical time series information and the current output non-air conditioning load value, the temporal attention mechanism is used to decode the quantized weights; Building a dual attention mechanism On the basis of the original CNN-LSTM network, the feature attention mechanism is introduced before the first LSTM layer, and the time attention mechanism is introduced after the last LSTM layer. The dual attention mechanism can adaptively mine the relationship between load and influencing factors, obtain the contribution rate of each influencing factor at different times, and improve the accuracy of single-point prediction; it can also mine the correlation between the current load and the historical key moment information, and improve the accuracy of long-term time series prediction; That is, the threshold load and load influencing factors in the non-air-conditioning season pass through the input layer, convolution layer, pooling layer, feature attention mechanism, LSTM layer 1, LSTM layer 2, LSTM layer 3, temporal attention mechanism, fully connected layer and output layer in sequence to obtain the non-air-conditioning load in the air-conditioning season; LSTM layer 1, LSTM layer 2 and LSTM layer 3 are LSTM layers, and the convolution layer, pooling layer and fully connected layer are CNN layers.
9. According to claim 8, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The method of decoding quantized weights by the temporal attention mechanism is: The hidden layer state h containing the time series information at each historical moment τ (τ=1,2,…,t,…,T) and the hidden layer state h at the previous moment of historical moment t t and memory information t As the input of the temporal attention mechanism, the attention weights of the historical moment t and each historical moment are calculated respectively, and quantized using the calculation method of the multi-layer perceptron. The weight calculation is as follows: In the formula, V d and W d is the multi-layer perceptron weight matrix for calculating attention weights, U d is the bias term; Use the Softmax function to Normalize the weights so that the sum of the temporal attention weights is 1, as shown in the following formula: Quantify the importance of the state information of the τth hidden layer for the predicted output at time t, and set all the weights The weighted sum of the corresponding hidden layer state information is used to obtain the comprehensive information c related to the time series state characteristics. t , as shown below: The non-air conditioning load value y to be predicted at time t t Comprehensive information related to the characteristics of the temporal state c t After fusion through a single-layer feedforward network, the input of the CNN-LSTM network at each time t is obtained In the formula, and The weights and biases of a single-layer feed-forward network are calculated for fusion input respectively; h t The CNN-LSTM network in the following formula iterates T times from the initial moment to the T moment: The hidden layer state h at the final time T T With comprehensive information T The single-layer feedforward network is used for integration, and finally the single-layer feedforward network is used for dimension transformation to obtain the predicted value of the non-air-conditioning load to be predicted. As shown below: Where W y and b w are the weights and biases of the single-layer feedforward network that integrates the output, V y and b y are the weights and biases of the feed-forward network for dimension transformation, respectively.
10. According to claim 8, a method for decomposing and analyzing air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network, It is characterized in that The modeling method for establishing a public building air conditioning load decomposition model based on the dynamic difference method based on the seasonal operation characteristics of the public building load is as follows: The building is divided into air-conditioning season and non-air-conditioning season according to whether the air conditioner is turned on or not, and the following constraints are established: P 非空调季关口负荷 ≈P 非空调季非空调负荷 P 空调季关口负荷 =P 空调季非空调负荷 +P 空调季空调负荷 Establish a method to dynamically predict the non-air-conditioning load in the air-conditioning season through the threshold load in the non-air-conditioning season; Due to the following constraints: P 空调负荷 =P 关口负荷 -P 非空调负荷 For the air-conditioning operation days divided by clustering, a public building air-conditioning load decomposition method is established, which uses the real-time measured gateway load actual value and the non-air-conditioning load prediction value dynamically predicted by the neural network to decompose the dynamic prediction value of the air-conditioning load. Based on the non-air-conditioning load prediction result of the air-conditioning season, the air-conditioning load prediction value of the air-conditioning season is obtained by real-time subtraction.
11. An analysis device for a decomposition and analysis method of air conditioning load for public buildings based on a two-stage attention mechanism integrating a convolutional neural network and a long short-term memory network. It is characterized in that The analysis device comprises: Clustering algorithm module, to establish a model module for distinguishing air-conditioning operation day module from non-operation day module; The air conditioning non-operation day module is used as the training set for the neural network prediction model; The air-conditioning operation day module is used as the test set of the model; a method for obtaining the air-conditioning load of public buildings by dynamically subtracting the threshold load curve of the air-conditioning operation day module from the non-air-conditioning load curve obtained by the non-air-conditioning load prediction model; The non-air-conditioning load prediction model module establishes a feature attention mechanism module on the input side of the module; quantifies the correlation between input feature variables, thereby dynamically adjusting the input feature weights and enhancing the guidance of strongly correlated feature variables; Non-air-conditioning load prediction model module, on the output side of which a temporal attention mechanism module is established to capture the dependency of timing information, dynamically adjust the output of hidden states, and enhance the information expression of key time steps; Based on the distinction between the air-conditioning operation day module and the air-conditioning non-operation day module, a public building air-conditioning load decomposition module based on the dynamic difference method is established.
12. The analysis device of the method for decomposing and analyzing the air conditioning load for public buildings based on the two-stage attention mechanism fused with convolutional neural network and long short-term memory network according to claim 11, It is characterized in that Through the clustering algorithm module, the method for establishing the air conditioning non-operating day module and the air conditioning operating day module is as follows: Based on the clustering algorithm, a clustering method for the threshold load curve of public building users is established to distinguish between the days when the user's air conditioner is turned on and the days when it is not in operation. The user's daily threshold load curve is input into the clustering algorithm and set to be clustered into 2 clusters. Select a clustering algorithm and use the actual sample that is most similar to other samples in each cluster as the cluster center to improve the clustering algorithm's sensitivity to noise and outliers and the defect of being easily trapped in local optimality; The clustering algorithm outputs the dates corresponding to the two different curves after classification, representing the air conditioner operation days and non-operation days respectively. This method is more accurate than distinguishing the air conditioner on and off days based on experience such as seasonal temperature changes.
13. The analysis device of the method for decomposing and analyzing the air conditioning load for public buildings based on the two-stage attention mechanism fused with convolutional neural network and long short-term memory network according to claim 11, It is characterized in that The method of establishing the non-air conditioning load prediction model module is: Establish the factors affecting the load of public buildings, including historical load, meteorological information and date type; The historical load includes the historical load of the past day, the load at the same time in the past week, and the load at the same time on the same characteristic day in the past month. Meteorological information includes temperature, humidity, wind speed and weather; Date types include time variables, weekday and rest day variables, and holiday variables. The load influencing factors of public building users are taken as the input features of the training set and input into the CNN-LSTM network model in the form of a sliding window. The non-air-conditioning load of public building users in the non-air-conditioning season is taken as the target feature of the training set to train the CNN-LSTM network. Establish CNN-LSTM network model training samples; Among them, in the CNN convolutional neural network, the input layer, convolution layer, pooling layer, convolution layer, pooling layer, fully connected layer and output layer are connected in sequence. Using the trained model, the load influencing factors at the corresponding time of the air-conditioning season and the non-air-conditioning load on typical days in the non-air-conditioning season are input from the input layer in the form of a sliding window. The trained model parameters are obtained through the CNN layer and the three-layer LSTM layer. The predicted non-air-conditioning load values at each time of each day in the air-conditioning season are output through the output layer.
14. The analysis device of the method for decomposing and analyzing the air conditioning load for public buildings based on the two-stage attention mechanism fused with convolutional neural network and long short-term memory network according to claim 11, It is characterized in that The public building air conditioning load decomposition module is a method for obtaining the public building air conditioning load by dynamically subtracting the air conditioning operation day threshold load curve from the non-air conditioning load prediction model.
15. An electronic device, Features: It includes one or more processors for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors execute any one of claims 1-10, a method for decomposing and analyzing the air conditioning load for public buildings based on a DA-CNN-LSTM network.
16. A storage medium having a computer program stored therein, Features: in, The computer program is configured to execute, when running, any one of claims 1 to 10, a method for decomposing and analyzing air conditioning load for public buildings based on a DA-CNN-LSTM network.
Citation Information
Patent Citations
Public building load identification method and device and computer readable storage medium
CN115018052A
Public building cold load prediction method and device, equipment and storage medium
CN116384773A
CNN-LSTM-based central air conditioner demand response test method and system
CN117273077A
Calculation method for schedulable potential of active loads, terminal, and storage medium
WO2024060521A1
Cited By
Power log anomaly detection method based on attention mechanism multi-feature fusion
CN119961791A
SO2 concentration prediction method based on double-stage attention and double-flow memory adjustment GRU
CN120126601A
SO2 concentration prediction method based on two-stage attention and double-flow memory regulation GRU
CN120126601B
Intelligent control method and system for commercial energy storage
CN120357522A
Transformer dynamic load capacity prediction method considering salt lake chemical load flexibility
CN122451399A
