Air conditioner load parameter credible aggregation method based on cloud-edge encryption

Abstract

The invention relates to the technical field of air conditioner loads, and particularly discloses an air conditioner load parameter credible aggregation method based on cloud-edge encryption, which is based on a cloud-edge collaborative architecture, uses a public cloud server as a cloud platform, and uses edge computing equipment as a user side intelligent terminal. A data transmission mode based on a file transfer protocol is adopted to carry out cloud side communication, the cloud-side collaborative architecture comprises three cloud servers, the cloud server 3 is responsible for distributing encryption keys to users and distributing decryption keys to the cloud server 1, the cloud server 2 is responsible for clustering user parameters, and the cloud server 3 is responsible for distributing encryption keys to the users and distributing decryption keys to the cloud server 2. And the cloud server 1 is responsible for decrypting the clustered parameters and solving a demand response load reduction optimization problem to determine an optimal strategy. In this way, it is ensured that each cloud server can only master local information of all users, the security of data circulation is enhanced, and the user data privacy is protected and the solving scale of the load reduction optimization problem in the demand response is reduced by encrypting and clustering the user parameters at the cloud.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioning loads, and more specifically, to a trusted aggregation method of air conditioning load parameters based on cloud-edge encryption. Background Art

[0002] Air conditioning load is an important type of adjustable load that can be used to achieve load reduction in the power system, that is, demand response. There is an obvious master-slave relationship between the demand response implementer (usually the load aggregation subject) and the air conditioning load. The load aggregation subject is the "master" and is responsible for formulating the demand response plan; the air conditioning user is the "slave" and adjusts his or her electricity consumption behavior according to the plan. In this scenario, a two-level optimization problem of demand response load reduction is formed, which maximizes the profit of the load aggregation subject and minimizes the comprehensive cost of the user's air conditioning. For solving the optimal demand response strategy in the two-level optimization model, in the existing method, the load reduction executor obtains the parameters of the air conditioning user, converts the user's optimization problem into the Karush–Kuhn–Tucker equivalent condition, and integrates it into the constraint conditions of the load reducer's profit maximization problem, forming an optimization problem with equilibrium constraints (Mathematical Programs with Equilibrium Constraints, MPEC) problem, and performs linearization to obtain a mixed integer linear programming problem (Mixed-Integer Linear Program, MILP), and finally solves the optimal load reduction strategy.

[0003] However, this approach has some obvious limitations. Specifically, private data such as the air conditioning electricity consumption preferences of users participating in demand response will be directly exposed to the database of the load reduction executor, so the security of users' personal data cannot be fully guaranteed. In addition, the seasonal characteristics of air conditioning load are obvious. Dedicated servers only run during a few periods of the year and are idle during other periods, which will cause a waste of computing resources. At the same time, the participation of a large number of users brings about a variable surge problem in the demand response load reduction optimization problem MPEC or MILP, which makes it difficult to solve the optimal strategy.

[0004] Therefore, a trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption is expected. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a trusted aggregation method of air conditioning load parameters based on cloud-edge encryption, which is based on a cloud-edge collaborative architecture, uses a public cloud server as a cloud platform, and the edge computing device is a user-side intelligent terminal. It adopts a data transmission method based on a file transfer protocol for cloud-edge communication, wherein the cloud-edge collaborative architecture includes three cloud servers, cloud server 3 is responsible for distributing encryption keys to users and decryption keys to cloud server 1, cloud server 2 is responsible for clustering user parameters, and cloud server 1 is responsible for decrypting the clustered parameters and solving the demand response load reduction optimization problem to determine the optimal strategy. In this way, it is ensured that each cloud server can only grasp the local information of all users, and the security of data flow is enhanced. By encrypting and clustering user parameters in the cloud, the scale of solving the load reduction optimization problem in demand response is reduced while protecting user data privacy.

[0006] According to one aspect of the present application, a trusted aggregation method for air conditioning load parameters based on cloud-edge encryption is provided, which includes:

[0007] The third cloud server generates an encryption key and a decoding key, and stores the encryption key and the decoding key in the first FTP folder;

[0008] The edge side obtains the encryption key from the first FTP folder, uses the encryption key to encrypt the air conditioning load parameter to obtain the encrypted air conditioning load parameter, and transmits the encrypted air conditioning load parameter to the second FTP folder, wherein the air conditioning load parameter includes the air conditioning temperature preference coefficient and the most comfortable temperature setting;

[0009] The second cloud server extracts the encrypted air conditioning load parameter from the second FTP folder and performs cluster analysis on the encrypted air conditioning load parameter to obtain a clustering result, and then writes the clustering result into a third FTP folder;

[0010] The first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates an optimal demand response strategy based on the clustering result.

[0011] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates the optimal demand response strategy based on the clustering result, including: using MPEC or MILP method to process the clustering result to obtain the optimal demand response strategy, and the optimal demand response strategy is the recommended air-conditioning temperature setting.

[0012] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates the optimal demand response strategy based on the clustering result, including: using the decoding key to decrypt the clustering result to obtain the decrypted clustering result; using the class embedding matrix to embed code each cluster center in the decrypted clustering result to obtain a set of embedded coding vectors of air-conditioning parameter cluster centers; performing feature dynamic aggregation on the set of embedded coding vectors of air-conditioning parameter cluster centers to obtain a global significant integration representation vector of air-conditioning parameters; and generating the optimal demand response strategy based on the global significant integration representation vector of air-conditioning parameters.

[0013] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the set of embedded coding vectors of the air-conditioning parameter cluster centers is dynamically aggregated to obtain a global significant integration representation vector of the air-conditioning parameters, including: determining the global clustering initial center vector of the air-conditioning parameters based on the feature distribution field of the set of embedded coding vectors of the air-conditioning parameter cluster centers; based on the spatial span of the embedded coding vectors of each air-conditioning parameter cluster center in the set of embedded coding vectors of the air-conditioning parameter cluster centers relative to the global clustering initial center vector of the air-conditioning parameters, performing significance modulation dynamic aggregation on the set of embedded coding vectors of the air-conditioning parameter cluster centers to obtain the global significant integration representation vector of the air-conditioning parameters.

[0014] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the initial center vector of the global clustering of air-conditioning parameters is determined based on the characteristic distribution field of the set of embedded coding vectors of the air-conditioning parameter cluster centers, including: calculating the static energy factors of each air-conditioning parameter cluster center embedded coding vector in the set of embedded coding vectors of the air-conditioning parameter cluster centers to obtain a set of static energy factors of air-conditioning parameters; selecting the air-conditioning parameter cluster center embedded coding vector corresponding to the maximum value in the set of static energy factors of the air-conditioning parameters as the initial center vector of the global clustering of the air-conditioning parameters.

[0015] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the static energy factor of each air-conditioning parameter cluster center embedded coding vector in the set of air-conditioning parameter cluster center embedded coding vectors is calculated to obtain a set of air-conditioning parameter static energy factors, including: calculating the kurtosis of the air-conditioning parameter cluster center embedded coding vector, and inputting the kurtosis into the sigmoid activation function to obtain the air-conditioning parameter static energy factor.

[0016] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, based on the spatial span of each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors relative to the initial center vector of the global clustering of the air-conditioning parameters, the set of air-conditioning parameter cluster center embedding coding vectors is subjected to significance modulation dynamic aggregation to obtain the global significant integration representation vector of the air-conditioning parameters, including: based on the spatial span between each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors and the initial center vector of the global clustering of the air-conditioning parameters, and the set of air-conditioning parameter static energy factors, the dynamic aggregation energy factor of each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors is calculated to obtain a set of air-conditioning parameter dynamic aggregation energy factors; the set of air-conditioning parameter dynamic aggregation energy factors is input into a gated mask unit to obtain a set of air-conditioning parameter dynamic aggregation weight factors; and the weighted sum of the set of air-conditioning parameter cluster center embedding coding vectors is calculated based on the set of air-conditioning parameter dynamic aggregation weight factors to obtain the global significant integration representation vector of the air-conditioning parameters.

[0017] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the dynamic aggregation energy factor of each air-conditioning parameter clustering center embedded coding vector in the set of air-conditioning parameter clustering center embedded coding vectors is calculated to obtain a set of air-conditioning parameter dynamic aggregation energy factors, including: taking the square value of the number of eigenvectors between the air-conditioning parameter clustering center embedded coding vector and the air-conditioning parameter global clustering initial center vector as the spatial span coefficient, and calculating the weighted ratio between the product of the static energy factor of the air-conditioning parameter clustering center embedded coding vector and the static energy factor of the air-conditioning parameter global clustering initial center vector and the spatial span coefficient to obtain the air-conditioning parameter dynamic aggregation energy factor.

[0018] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, the optimal demand response strategy is generated based on the global significant integration representation vector of the air-conditioning parameters, including: inputting the global significant integration representation vector of the air-conditioning parameters into the decoder-based optimal demand response strategy generator to obtain the optimal demand response strategy.

[0019] Compared with the prior art, the trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption provided by the present application is based on a cloud-edge collaborative architecture, uses a public cloud server as a cloud platform, and the edge computing device is a user-side intelligent terminal. It adopts a data transmission method based on the file transfer protocol for cloud-edge communication, wherein the cloud-edge collaborative architecture includes three cloud servers, cloud server 3 is responsible for distributing encryption keys to users and decryption keys to cloud server 1, cloud server 2 is responsible for clustering user parameters, and cloud server 1 is responsible for decrypting the clustered parameters and solving the demand response load reduction optimization problem to determine the optimal strategy. In this way, it is ensured that each cloud server can only grasp the local information of all users, and the security of data flow is enhanced. By encrypting and clustering user parameters in the cloud, the scale of solving the load reduction optimization problem in demand response is reduced while protecting user data privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0021] Figure 1 This is a flowchart of cloud-edge encrypted clustering of user personal data in a trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application.

[0022] Figure 2 This is a flowchart of a method for clustering user parameters using Euclidean distance in a trusted aggregation method for air-conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application.

[0023] Figure 3 This is a flowchart of sub-step S4 of the trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application.

[0024] Figure 4 This is a data flow diagram of sub-step S4 of the trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application.

[0025] Figure 5 This is a flowchart of sub-step S43 of the trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0027] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0028] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0029] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0030] In response to the above technical problems, this application proposes an optimized trusted aggregation method of air conditioning load parameters based on cloud-edge encryption, which is based on a cloud-edge collaborative architecture, uses a public cloud server as a cloud platform, and the edge computing device is a user-side intelligent terminal. It adopts a data transmission method based on the file transfer protocol for cloud-edge communication, wherein the cloud-edge collaborative architecture includes three cloud servers, cloud server 3 is responsible for distributing encryption keys to users and decryption keys to cloud server 1, cloud server 2 is responsible for clustering user parameters, and cloud server 1 is responsible for decrypting the clustered parameters and solving the demand response load reduction optimization problem to determine the optimal strategy. In this way, it is ensured that each cloud server can only grasp the local information of all users, and the security of data flow is enhanced. By encrypting and clustering user parameters in the cloud, the scale of solving the load reduction optimization problem in demand response is reduced while protecting user data privacy.

[0031] Figure 1 Flow chart of cloud-edge encrypted clustering of user personal data in a trusted aggregation method of air conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application. Figure 1As shown, the trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption includes the following steps: S1, a third cloud server generates an encryption key and a decoding key, and stores the encryption key and the decoding key in a first FTP folder; S2, the edge side obtains the encryption key from the first FTP folder, uses the encryption key to encrypt the air-conditioning load parameters to obtain the encrypted air-conditioning load parameters, and transmits the encrypted air-conditioning load parameters to a second FTP folder, wherein the air-conditioning load parameters include an air-conditioning temperature preference coefficient and a most comfortable temperature setting; S3, the second cloud server extracts the encrypted air-conditioning load parameters from the second FTP folder and performs cluster analysis on the encrypted air-conditioning load parameters to obtain clustering results, and then writes the clustering results into a third FTP folder; S4, the first cloud server extracts the decoding key from the first FTP folder and the clustering results from the third FTP folder, and calculates the optimal demand response strategy based on the clustering results.

[0032] In the above-mentioned trusted aggregation method of air conditioning load parameters based on cloud-edge encryption, in step S1, the third cloud server generates an encryption key and a decoding key, and stores the encryption key and the decoding key in the first FTP folder. Cloud server 3 generates a key and writes the encryption key X and the decryption key X′ into the FTP1 folder. In order to retain the characteristics of the user's original data to the maximum extent, both encryption and decryption use a linear method, that is, the encrypted data is multiplied by a constant, and the decrypted data is divided by the same constant.

[0033] In the above-mentioned trusted aggregation method of air conditioning load parameters based on cloud-edge encryption, in step S2, the edge side obtains the encryption key from the first FTP folder, uses the encryption key to encrypt the air conditioning load parameters to obtain the encrypted air conditioning load parameters, and transmits the encrypted air conditioning load parameters to the second FTP folder, wherein the air conditioning load parameters include the air conditioning temperature preference coefficient and the most comfortable temperature setting. It should be understood that the key for users in demand response is to minimize their own comprehensive costs, of which the core is the temperature discomfort cost, which is a quadratic form, indicating that the farther the air conditioning setting temperature deviates from the ideal temperature, the higher the user's discomfort cost:

[0034] C discomfort,m =ω m Δi(T set,m -T ideal,m ) 2

[0035] Among them, ω m is the temperature preference coefficient of user m, T set,m is the air conditioning temperature setting of user m, T ideal,mIt is the most comfortable temperature value for user m.

[0036] Based on this, this application focuses on the air conditioning temperature preference coefficient ω m And the most comfortable temperature setting T ideal,m Execute clustering. The user reads the encryption key X from the FTP1 folder, encrypts his own temperature preference coefficient and the most comfortable temperature setting parameters, and writes them into the FTP2 folder. The encryption formula is:

[0037] ω′ m =X(ω m )=τω m

[0038] T′ ideal,m =X(T ideal,m )=τT ideal,m

[0039] Among them, ω′ m represents the key-encrypted temperature preference coefficient, T′ ideal,m represents the most comfortable temperature setting after key encryption, τ represents the constant used for user parameter encryption, and the total number of users is M.

[0040] In the above-mentioned trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption, in step S3, the second cloud server extracts the encrypted air-conditioning load parameters from the second FTP folder and performs cluster analysis on the encrypted air-conditioning load parameters to obtain clustering results, and then writes the clustering results into the third FTP folder. After cloud server 2 reads the encrypted air-conditioning parameters from the FTP2 folder, it performs clustering on them using the K-means algorithm based on Euclidean Distance, thereby avoiding the influence of data encryption operations on clustering results. Then, the clustered user parameters are written into the FTP3 folder. The detailed steps of data clustering are as follows: Figure 2 As shown. Among them:

[0041] Step 3.1: Initialize K cluster centers.

[0042] The K samples selected by cloud server 2 are used as the initial cluster centers o=o1,...,o k ,...,o K :

[0043] o k =(T′ ideal,k ,ω′ k )

[0044] Step 3.2: Divide the data into K categories.

[0045] For each sample i in the data set, cloud server 2 calculates its Euclidean distance to the k cluster centers and divides it into the cluster corresponding to the cluster center with the smallest distance. k middle:

[0046]

[0047] Step 3.3: Recalculate the cluster centers of K-class data.

[0048] Cloud Server 2 recalculates the cluster centers (the centroids of all samples belonging to the class) for all data in each class:

[0049]

[0050] Among them, x k Yes k The number of sample data contained in the collection.

[0051] Step 3.4: Determine whether the iteration is completed.

[0052] Cloud server 2 repeats operations 3.2 and 3.3 until a suitable centroid is selected: in each cluster, the distance d from the sample to the centroid cri As small as possible to ensure that the samples in each cluster have high similarity:

[0053]

[0054] The K groups of data after clustering are as follows:

[0055] {(T′ ideal,1 ,ω′1),...,(T′ ideal,k ,ω′ k ),...,(T′ ideal,K ,ω′ K )}

[0056] In the above-mentioned trusted aggregation method of air conditioning load parameters based on cloud-edge encryption, in step S4, the first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates the optimal demand response strategy based on the clustering result. Cloud server 1 reads the decryption key in the FTP1 folder, reads the clustered user parameters in the FTP3 folder, and then performs the data decryption operation:

[0057]

[0058] At this point, the user's air conditioning temperature setting preference coefficient and the most comfortable temperature setting will be reduced from M categories to K categories, and the variables of the MPEC or MILP problem will also be reduced to K / M times of the original. Cloud server 1 solves the demand response load reduction optimization problem (MPEC or MILP problem) containing K groups of variables based on the clustered user parameters to obtain the optimal demand response strategy.

[0059] In particular, the present application takes into account the actual situation and constraints of the problem when constructing the MPEC and MILP problem models. However, in practical applications, there are often various complexities and uncertainties, which may cause the constructed MILP model to be unable to fully adapt to the actual situation. For example, when certain parameters or constraints in the problem change, it may be necessary to redefine the model structure or adjust the parameters and solve them, which further limits the flexibility and adaptability of the model. In this regard, in another embodiment of the present application, an optimized optimal demand response strategy solution method is proposed, which embeds and encodes each cluster center in the decrypted clustering result by introducing a deep learning algorithm to learn the intrinsic characteristics of the air conditioning parameter cluster center, and then based on the characteristic distribution field of each air conditioning parameter cluster center, modulates and dynamically aggregates the characteristic significance, further identifies and strengthens the key user load characteristics, and based on this, realizes the intelligent decoding prediction of the optimal demand response strategy. In this way, the adaptability and flexibility of the model can be effectively improved, and the strategy can be dynamically adjusted according to real-time data to cope with the uncertainty of environmental changes and user behavior, so as to provide users and power grid operators with more accurate and personalized load reduction solutions, and achieve efficient use of energy and cost minimization.

[0060] Figure 3 This is a flowchart of sub-step S4 of the trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application. Figure 4 FIG. 4 is a data flow diagram of sub-step S4 of the trusted aggregation method for air conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application. Figure 3 and Figure 4 As shown, the step S4 includes the steps of: S41, using the decoding key to decrypt the clustering result to obtain the decrypted clustering result; S42, using the class embedding matrix to embed the various cluster centers in the decrypted clustering result to obtain a set of air-conditioning parameter cluster center embedding coding vectors; S43, performing dynamic feature aggregation on the set of air-conditioning parameter cluster center embedding coding vectors to obtain an air-conditioning parameter global significant integration representation vector; S44, generating the optimal demand response strategy based on the air-conditioning parameter global significant integration representation vector.

[0061] Specifically, in step S41, the clustering result is decrypted using the decoding key to obtain a decrypted clustering result. Here, the specific operation of decrypting the clustering result using the decoding key has been described in detail above, and therefore, its repeated description will be omitted.

[0062] Specifically, in step S42, each cluster center in the decrypted clustering result is embedded and encoded using a class embedding matrix to obtain a set of embedded encoding vectors of air conditioning parameter cluster centers. It should be understood that each cluster center in the decrypted clustering result represents the air conditioning usage preferences and comfort requirements of different user groups. In order to effectively capture the correlation and difference between the air conditioning load parameter characteristics of different user groups, so as to better formulate demand response strategies, this application uses a class embedding matrix to embed and encode each cluster center in the decrypted clustering result, so as to map each cluster center data to a unified low-dimensional continuous vector space. Through the embedded coding technology, while extracting the intrinsic characteristics of the original clustering information, the potential correlation structure between the air conditioning load parameter characteristics of different user groups is revealed based on the relative position relationship of each cluster center in the feature space, thereby providing more useful data support for the formulation of subsequent demand response strategies.

[0063] Specifically, the step S43 performs dynamic feature aggregation on the set of embedded coding vectors of the air-conditioning parameter cluster centers to obtain a globally significant integrated representation vector of the air-conditioning parameters. It should be understood that in order to further analyze the overall characteristics of the user's air-conditioning load parameters from a global perspective, it is necessary to perform feature aggregation on the set of embedded coding vectors of the air-conditioning parameter cluster centers, so as to integrate the air-conditioning usage preferences and comfort demand information of different user groups, and achieve a global understanding of the user's air-conditioning load demand. In particular, in the feature aggregation process, in order to effectively improve the discrimination and representativeness of the aggregated features, the present application proposes a dynamic aggregation method based on the feature distribution field, which dynamically adjusts the weight of feature aggregation by analyzing the relative position relationship and feature energy distribution between each cluster center, thereby strengthening the recognition and expression of key features, and suppressing the interference of non-key features, thereby improving the efficiency and accuracy of feature aggregation. Among them, Figure 5 Flow chart of sub-step S43 of the trusted aggregation method of air conditioning load parameters based on cloud-edge encryption according to an embodiment of the present application. Figure 5As shown, the step S43 includes the steps of: S431, determining the initial center vector of the global clustering of air-conditioning parameters based on the characteristic distribution field of the set of the air-conditioning parameter cluster center embedding coding vectors; S432, performing significance modulation dynamic aggregation on the set of the air-conditioning parameter cluster center embedding coding vectors based on the spatial span of each air-conditioning parameter cluster center embedding coding vector in the set of the air-conditioning parameter cluster center embedding coding vectors relative to the initial center vector of the global clustering of air-conditioning parameters to obtain the global significant integrated representation vector of the air-conditioning parameters.

[0064] More specifically, the step S431 further includes: calculating the static energy factor of each air-conditioning parameter cluster center embedded coding vector in the set of air-conditioning parameter cluster center embedded coding vectors to obtain a set of air-conditioning parameter static energy factors; selecting the air-conditioning parameter cluster center embedded coding vector corresponding to the maximum value in the set of air-conditioning parameter static energy factors as the initial center vector of the global clustering of the air-conditioning parameters.

[0065] In a specific example of the present application, the static energy factor of each air conditioning parameter cluster center embedded coding vector in the set of the air conditioning parameter cluster center embedded coding vector is calculated to obtain a set of air conditioning parameter static energy factors, including: calculating the kurtosis of the air conditioning parameter cluster center embedded coding vector, and inputting the kurtosis into the sigmoid activation function to obtain the air conditioning parameter static energy factor. That is, the static energy factor is calculated based on the kurtosis of the embedded coding vector of each air conditioning parameter cluster center to evaluate its stability and importance in the feature space, and the air conditioning parameter cluster center embedded coding vector corresponding to the largest static energy factor is selected as the initial center vector of the global clustering of the air conditioning parameters to determine the cluster core of the feature distribution of each air conditioning parameter cluster center, thereby providing a stable reference point for subsequent feature aggregation.

[0066] More specifically, the step S432 further includes: based on the spatial span between each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors and the initial center vector of the global cluster of the air-conditioning parameters, and the set of air-conditioning parameter static energy factors, calculating the dynamic aggregation energy factor of each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors to obtain a set of air-conditioning parameter dynamic aggregation energy factors; inputting the set of air-conditioning parameter dynamic aggregation energy factors into a gated mask unit to obtain a set of air-conditioning parameter dynamic aggregation weight factors; calculating the weighted sum of the set of air-conditioning parameter cluster center embedding coding vectors based on the set of air-conditioning parameter dynamic aggregation weight factors to obtain the global significant integration representation vector of the air-conditioning parameters.

[0067] In a specific example of the present application, the dynamic aggregation energy factor of each air-conditioning parameter cluster center embedded coding vector in the set of air-conditioning parameter cluster center embedded coding vectors is calculated to obtain a set of air-conditioning parameter dynamic aggregation energy factors, including: taking the square value of the number of eigenvectors between the air-conditioning parameter cluster center embedded coding vector and the air-conditioning parameter global cluster initial center vector as the spatial span coefficient, and calculating the weighted ratio between the product of the static energy factor of the air-conditioning parameter cluster center embedded coding vector and the static energy factor of the air-conditioning parameter global cluster initial center vector and the spatial span coefficient to obtain the air-conditioning parameter dynamic aggregation energy factor.

[0068] In a specific example of the present application, the set of dynamic aggregation energy factors of the air-conditioning parameters is input into a gated mask unit, including: inputting the set of dynamic aggregation energy factors of the air-conditioning parameters into a sigmoid function for normalization processing to obtain a set of normalized dynamic aggregation energy factors of the air-conditioning parameters; based on a preset mask threshold, deactivating the set of normalized dynamic aggregation energy factors of the air-conditioning parameters to obtain a set of dynamic aggregation weight factors of the air-conditioning parameters.

[0069] That is, by considering the degree of proximity of the embedded coding vectors of each air conditioning parameter cluster center to the core of the cluster distribution of the air conditioning parameter cluster center feature space and the difference in the importance of the intrinsic attributes, its contribution to the global characteristics of the user's air conditioning load parameters can be more accurately measured. Then, based on the gated mask mechanism, the obtained dynamic aggregation energy factor is nonlinearly transformed and screened to generate corresponding weights, so as to perform weighted aggregation on the set of embedded coding vectors of the air conditioning parameter cluster center, thereby enhancing the expression of important features, suppressing the influence of irrelevant or noise features, and obtaining a global significant integration representation vector of air conditioning parameters. In this way, not only the overall trends and patterns of user groups in air conditioning usage preferences and comfort requirements are captured, but also user preferences and comfort requirements information that have a greater impact on the formulation of demand response strategies can be given priority, thereby providing a solid data foundation for the formulation of efficient demand response strategies.

[0070] Accordingly, the step S43 includes: processing the set of the air-conditioning parameter cluster center embedding coding vectors using the following feature dynamic aggregation formula to obtain the air-conditioning parameter global significant integration representation vector, wherein the feature dynamic aggregation formula is:

[0071] X1={x1,x2,...,x i ,...,x n}

[0072]

[0073] xc =x m

[0074]

[0075]

[0076] w si =mask(w i )

[0077]

[0078] Where X1 represents the set of embedded coding vectors of the cluster center of the air conditioning parameters, x1, x2, x i 、x m and x n represents the first, second, i-th, m-th and n-th air conditioning parameter cluster center embedded coding vectors in the set of air conditioning parameter cluster center embedded coding vectors respectively, the value of n is the number of air conditioning parameter cluster center embedded coding vectors, x ij represents the eigenvalue of the jth position in the embedding encoding vector of the i-th air conditioning parameter cluster center, μ i and σ i 4 denote the characteristic mean and the square of the characteristic variance of the embedding coding vector of the i-th conditioning parameter cluster center, E{·} denotes the expected value of the calculation set, sigmoid denotes the sigmoid activation function, represents the static energy factor of the i-th air conditioning parameter cluster center embedded coding vector, argmax represents the index corresponding to the maximum value, m represents the index of the largest static energy factor in the set of air conditioning parameter static energy factors, x c represents the initial center vector of the global clustering of air conditioning parameters, represents the static energy factor of the initial center vector of the global clustering of the air conditioning parameters, a and b are different weight parameters, Count(x i →x m ) represents the number of feature vectors between the embedding coding vector of the i-th air conditioning parameter cluster center and the initial center vector of the global cluster of air conditioning parameters, e xi represents the dynamic aggregation energy factor of the i-th conditioning parameter cluster center embedding encoding vector, w i represents the i-th normalized air conditioning parameter dynamic aggregation energy factor, mask(·) represents mask processing, θ is the preset mask threshold, and w si represents the dynamic aggregation weight factor of the ith air-conditioning parameter, and V represents the global significant integration representation vector of the air-conditioning parameter.

[0079] Specifically, the step S44 generates the optimal demand response strategy based on the global significant integration representation vector of the air-conditioning parameters. In a specific example of the present application, the step S44 includes: inputting the global significant integration representation vector of the air-conditioning parameters into the decoder-based optimal demand response strategy generator to obtain the optimal demand response strategy. In the technical solution of the present application, the decoder is based on a multi-layer neural network architecture, and through training and optimization, it can effectively learn the user air-conditioning load information contained in the global significant integration representation vector of the air-conditioning parameters, and establish a mapping relationship between the user air-conditioning load information and the demand response strategy, thereby realizing intelligent prediction of the optimal demand response strategy.

[0080] In a preferred example of the present application, the input of the global significant integration representation vector of the air-conditioning parameters into the decoder-based optimal demand response strategy generator to obtain the optimal demand response strategy includes: determining the global significant integration association response matrix of the air-conditioning parameters and the global significant integration distance response matrix of the air-conditioning parameters based on the association value and distance value of the eigenvalue of the global significant integration representation vector of the air-conditioning parameters; matrix multiplying the global significant integration representation vector of the air-conditioning parameters with the global significant integration association response matrix of the air-conditioning parameters to obtain the global significant integration association response vector of the air-conditioning parameters; matrix multiplying the global significant integration distance response matrix of the air-conditioning parameters with the transposed vector of the global significant integration representation vector of the air-conditioning parameters to obtain Air conditioning parameters global significant integration distance response vector; after dot multiplication of the air conditioning parameters global significant integration association response matrix and the air conditioning parameters global significant integration distance response matrix, matrix multiplication with the transpose vector of the air conditioning parameters global significant integration representation vector to obtain the air conditioning parameters global significant integration logic bias vector; dot the air conditioning parameters global significant integration association response vector, the air conditioning parameters global significant integration distance response vector and the air conditioning parameters global significant integration logic bias vector to obtain an optimized air conditioning parameters global significant integration representation vector; input the optimized air conditioning parameters global significant integration representation vector into the decoder-based optimal demand response strategy generator to obtain the optimal demand response strategy.

[0081] Accordingly, the optimization process of the global significant integration representation vector of the air conditioning parameters is expressed by the following optimization formula:

[0082] M1(i,j)=v i ×v j

[0083]

[0084] v i ,v j ∈V∈R 1×L

[0085] V1∈R 1×L

[0086] V2∈R L×1

[0087]

[0088]

[0089] Wherein, M1 is the global significant integrated association response matrix of air conditioning parameters, M2 is the global significant integrated distance response matrix of air conditioning parameters, M1(i,j) is the eigenvalue of the position (i,j) in the global significant integrated association response matrix of air conditioning parameters, M2(i,j) is the eigenvalue of the position (i,j) in the global significant integrated distance response matrix of air conditioning parameters, v i and v j are the ith and jth eigenvalues ​​in the global significant integration representation vector of air conditioning parameters, respectively; V1 is the point addition vector between the global significant integration association response vector of air conditioning parameters and the global significant integration distance response vector of air conditioning parameters; V2 is the global significant integration logical bias vector of air conditioning parameters; R is a real number set; L is the length of the global significant integration representation vector of air conditioning parameters; ⊙ represents point multiplication by position; represents matrix multiplication, represents the addition by position point, V is the global significant integration representation vector of air conditioning parameters, and V' is the global significant integration representation vector of optimized air conditioning parameters.

[0090] That is, in the technical solution of the present application, when each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors respectively represents the class embedding coding features of each cluster center in the decrypted clustering result, when the feature distribution field based on the imitation force field is dynamically aggregated, the difference in the class embedding coding features of each cluster center will cause large-scale simple repetition in the dynamic aggregation of the feature distribution field, affecting the logical dependency of the field dynamic aggregation and reducing the accuracy of the decoding results based on the cluster distribution.

[0091] Therefore, by taking the autocorrelation matrix and self-distance matrix of the global significant integration representation vector of the air-conditioning parameters as the statistical reference-free distribution response framework of the global significant integration representation vector of the air-conditioning parameters, the simple repetition of feature distribution is avoided based on the retrieval-enhanced reverse response construction for the global significant integration representation vector of the air-conditioning parameters, and by ensuring the intrinsic mapping logic of the global significant integration representation vector of the air-conditioning parameters based on the retrieval-response context, the surface combinatorial mapping of the global significant integration representation vector of the air-conditioning parameters is avoided, so as to achieve the logical dependency mapping of the global significant integration representation vector of the air-conditioning parameters to the decoding target domain while maintaining the intuitive response correlation, thereby improving the accuracy of the best demand response strategy obtained by the best demand response strategy generator based on the decoder input of the global significant integration representation vector of the air-conditioning parameters.

[0092] In summary, a trusted aggregation method of air-conditioning load parameters based on cloud-edge encryption based on the embodiment of the present application is explained, which is based on a cloud-edge collaborative architecture, uses a public cloud server as a cloud platform, and the edge computing device is a user-side intelligent terminal. It adopts a data transmission method based on the file transfer protocol for cloud-edge communication, wherein the cloud-edge collaborative architecture includes three cloud servers, cloud server 3 is responsible for distributing encryption keys to users and decryption keys to cloud server 1, cloud server 2 is responsible for clustering user parameters, and cloud server 1 is responsible for decrypting the clustered parameters and solving the demand response load reduction optimization problem to determine the optimal strategy. In this way, it is ensured that each cloud server can only grasp the local information of all users, and the security of data flow is enhanced. By encrypting and clustering user parameters in the cloud, the scale of solving the load reduction optimization problem in demand response is reduced while protecting user data privacy.

[0093] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0094] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0095] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0096] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0097] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A trusted aggregation method for air conditioning load parameters based on cloud-edge encryption, characterized in that: include: The third cloud server generates an encryption key and a decoding key, and stores the encryption key and the decoding key in the first FTP folder; The edge side obtains the encryption key from the first FTP folder, uses the encryption key to encrypt the air conditioning load parameter to obtain the encrypted air conditioning load parameter, and transmits the encrypted air conditioning load parameter to the second FTP folder, wherein the air conditioning load parameter includes the air conditioning temperature preference coefficient and the most comfortable temperature setting; The second cloud server extracts the encrypted air conditioning load parameter from the second FTP folder and performs cluster analysis on the encrypted air conditioning load parameter to obtain a clustering result, and then writes the clustering result into a third FTP folder; The first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates an optimal demand response strategy based on the clustering result.

2. The air conditioning load parameter trusted aggregation method based on cloud-edge encryption according to claim 1 is characterized in that: The first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates an optimal demand response strategy based on the clustering result, including: The clustering results are processed using the MPEC or MILP method to obtain an optimal demand response strategy, where the optimal demand response strategy is a recommended air conditioning temperature setting.

3. The air conditioning load parameter trusted aggregation method based on cloud-edge encryption according to claim 1 is characterized in that: The first cloud server extracts the decoding key from the first FTP folder and the clustering result from the third FTP folder, and calculates an optimal demand response strategy based on the clustering result, including: Decrypting the clustering result using the decoding key to obtain a decrypted clustering result; Using a class embedding matrix, embedding coding is performed on each cluster center in the decrypted clustering result to obtain a set of air conditioning parameter cluster center embedding coding vectors; Performing dynamic feature aggregation on the set of embedding coding vectors of the cluster centers of the air-conditioning parameters to obtain a global significant integration representation vector of the air-conditioning parameters; The optimal demand response strategy is generated based on the global significant integration representation vector of the air-conditioning parameters.

4. The air conditioning load parameter trusted aggregation method based on cloud-edge encryption according to claim 3 is characterized in that: The set of embedding coding vectors of the cluster centers of the air conditioning parameters is dynamically aggregated to obtain a global significant integration representation vector of the air conditioning parameters, including: Determining an initial center vector of the global clustering of air conditioning parameters based on a characteristic distribution field of a set of encoding vectors embedded in the cluster centers of the air conditioning parameters; Based on the spatial span of each air-conditioning parameter cluster center embedding coding vector in the set of air-conditioning parameter cluster center embedding coding vectors relative to the initial center vector of the global cluster of air-conditioning parameters, the set of air-conditioning parameter cluster center embedding coding vectors is dynamically aggregated by significance modulation to obtain the global significant integrated representation vector of the air-conditioning parameters.

5. The method for trusted aggregation of air conditioning load parameters based on cloud-edge encryption according to claim 4 is characterized in that: Based on the characteristic distribution field of the set of the air conditioning parameter cluster center embedding coding vectors, determining the initial center vector of the global clustering of the air conditioning parameters includes: Calculating the static energy factor of each air conditioning parameter cluster center embedded coding vector in the set of air conditioning parameter cluster center embedded coding vectors to obtain a set of air conditioning parameter static energy factors; The air-conditioning parameter cluster center embedding coding vector corresponding to the maximum value in the set of the air-conditioning parameter static energy factors is selected as the initial center vector of the global clustering of the air-conditioning parameters.

6. The method for trusted aggregation of air conditioning load parameters based on cloud-edge encryption according to claim 5 is characterized in that: Calculating the static energy factor of each air conditioning parameter cluster center embedded coding vector in the set of air conditioning parameter cluster center embedded coding vectors to obtain a set of air conditioning parameter static energy factors, including: The kurtosis of the air conditioning parameter cluster center embedding coding vector is calculated, and the kurtosis is input into a sigmoid activation function to obtain the air conditioning parameter static energy factor.

7. The method for trusted aggregation of air conditioning load parameters based on cloud-edge encryption according to claim 6 is characterized in that: Based on the spatial span of each air conditioning parameter cluster center embedding coding vector in the set of air conditioning parameter cluster center embedding coding vectors relative to the initial center vector of the global cluster of the air conditioning parameter, the set of the air conditioning parameter cluster center embedding coding vectors is dynamically aggregated by saliency modulation to obtain the global saliency integrated representation vector of the air conditioning parameter, including: Based on the spatial span between each air-conditioning parameter cluster center embedding coding vector in the set of the air-conditioning parameter cluster center embedding coding vector and the initial center vector of the global clustering of the air-conditioning parameters, and the set of the air-conditioning parameter static energy factors, the dynamic aggregation energy factor of each air-conditioning parameter cluster center embedding coding vector in the set of the air-conditioning parameter cluster center embedding coding vector is calculated to obtain a set of dynamic aggregation energy factors of the air-conditioning parameters; Inputting the set of dynamic aggregation energy factors of the air conditioning parameters into a gated mask unit to obtain a set of dynamic aggregation weight factors of the air conditioning parameters; The weighted sum of the set of the air-conditioning parameter cluster center embedding coding vectors is calculated based on the set of the air-conditioning parameter dynamic aggregation weight factors to obtain the air-conditioning parameter global significant integration representation vector.

8. The method for trusted aggregation of air conditioning load parameters based on cloud-edge encryption according to claim 7 is characterized in that: Calculating the dynamic aggregation energy factor of each air conditioning parameter cluster center embedded coding vector in the set of air conditioning parameter cluster center embedded coding vectors to obtain a set of air conditioning parameter dynamic aggregation energy factors, including: Taking the square value of the number of eigenvectors between the embedded coding vector of the air-conditioning parameter clustering center and the initial center vector of the global clustering of the air-conditioning parameters as the spatial span coefficient, the weighted ratio between the product of the static energy factor of the embedded coding vector of the air-conditioning parameter clustering center and the static energy factor of the initial center vector of the global clustering of the air-conditioning parameters and the spatial span coefficient is calculated to obtain the dynamic aggregation energy factor of the air-conditioning parameters.

9. The method for trusted aggregation of air conditioning load parameters based on cloud-edge encryption according to claim 8, characterized in that: Generating the optimal demand response strategy based on the global significant integration representation vector of the air conditioning parameters includes: The global significant integration representation vector of the air-conditioning parameters is input into a decoder-based optimal demand response strategy generator to obtain the optimal demand response strategy.

Images