Distributed radio map sensing method for privacy protection in wireless network

Abstract

The invention discloses a distributed radio map sensing method for privacy protection under a wireless network, which comprises the following steps: S1, distributing an independent local sub-model for each user, extracting local data features by the users by using respective local sub-models, and finally generating a deep local feature to be uploaded to a server; s2, a decision sub-model is configured for a server, the server receives local features from all users and takes the local features as input of the decision sub-model, and the decision sub-model visualizes transmitter information and forms a two-channel picture with the static geographical environment image; and S3, inputting the two-channel picture into a pre-trained U-Net model to generate a radio map, and finally obtaining a radio map estimation result. According to the method, high-precision real-time radio map estimation is realized on the premise of protecting user privacy, and the method has application universality; and importance is allocated to features from different users, so that the estimation accuracy is improved and the model complexity is reduced.

Description

Technical Field

[0001] The present invention relates to the field of radio map perception, and in particular to a distributed radio map perception method with privacy protection in a wireless network. Background Art

[0002] Radio map is a tool that can effectively depict the key features of the surrounding radio environment, such as the received signal strength (RSS) at any location in the area, path gain, interference strength, etc. Therefore, accurate and efficient radio map estimation (RME) has been a research hotspot in recent years. Traditional radio map estimation techniques such as interpolation algorithms, matrix completion algorithms, and ray tracing methods are difficult to achieve real-time and accurate radio map estimation. However, the deep learning (DNN)-based methods that have emerged in recent years can achieve real-time and high-precision radio map estimation due to their high-quality data sets and low-complexity DNN structures.

[0003] However, current deep learning methods can only be applied to cases where data is processed in a centralized manner. Since the received signal strength information of the user end in a wireless network is distributed on the user end, considering the issue of data privacy protection, such information is often difficult to upload to the server end in a centralized manner. Therefore, how to deal with real-time high-precision radio map perception in distributed scenarios is still one of the key challenges facing current research. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a privacy-preserving distributed radio map perception method in a wireless network, which can achieve high-precision real-time radio map estimation while protecting user privacy (i.e., without uploading local original data), and has more universal application; and assign importance to features from different users to improve estimation accuracy and reduce model complexity.

[0005] The object of the present invention is achieved through the following technical solution: a distributed radio map perception method for privacy protection in a wireless network, comprising the following steps: S1. Each user is assigned an independent local sub-model. The user uses their own local sub-model to extract local data features, and finally generates a deep local feature and uploads it to the server; S2. Configure a decision sub-model for the server. The server receives local features from all users as inputs to the decision sub-model. The decision sub-model first uses the attention mechanism in the model input layer to assign importance to data from different users, and then obtains transmitter information through subsequent neural network layer reasoning. Finally, the transmitter information is visualized to obtain a picture representing the signal strength of the transmitter location, and forms a two-channel picture with the static geographic environment image. S3. Input the two-channel image into the pre-trained U-Net model to generate a radio map, and finally obtain the radio map estimation result.

[0006] The beneficial effects of the present invention are: 1. The present invention proposes a two-stage radio map estimation framework from distributed estimation of transmitter information to radio map estimation. First, a distributed transmitter information online estimation scheme based on user-side received signal strength information is designed, which can obtain high-precision transmitter position and strength estimation; after obtaining accurate transmitter information estimation, combined with a UNet-based deep learning method, the final radio map is inferred using an offline trained deep model. This method can adapt to scenarios where the number of transmitters and users changes dynamically, and is suitable for a wide range of scenarios.

[0007] 2. In the transmitter information estimation stage, the vertical federated learning (VFL) architecture is used for model training and reasoning. Under this architecture, sub-neural networks are deployed on both the user side and the server side. The user sub-network is used to extract local data (i.e., the signal strength information received by the user side) features, and the server sub-network is used for judgment. All sub-networks work together for training and reasoning. When using this architecture for training and reasoning, users do not need to upload the original data (i.e., the signal strength information received by the user side), but only upload the local data features extracted by the sub-network, thereby protecting user privacy.

[0008] 3. For the server-side network, an attention layer is introduced, and the attention mechanism is used to intelligently allocate the importance of different users, thereby improving the accuracy of transmitter information estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a flow chart of the method of the present invention; Figure 2 This is a schematic diagram of vertical federated learning; Figure 3 This is a schematic diagram of the model collaborative training effect under the vertical federated learning framework; Figure 4 Schematic diagram of the difference in estimation accuracy under different numbers of users. DETAILED DESCRIPTION

[0010] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0011] The present invention aims at distributed radio map perception with privacy protection in wireless networks. The overall reasoning framework consists of three parts: user feature extraction, transmitter information estimation, and radio map generation. User feature extraction and transmitter information estimation are implemented on a vertical federated learning model, which consists of multiple local sub-models located at the user end and a decision sub-model located at the server. Figure 2 As shown; actual historical data can be collected to form a data set for training. The format of a single data sample in the data set is: the received signal strength at the user end location, the transmitter location and the transmitted signal strength; the radio map generation part is implemented on a U-Net model. The model can be pre-trained based on the existing data set RadioMapSeer (this part directly uses the existing method to generate a radio map using transmitter and geographic environment information), as shown Figure 1 As shown, the method of the present invention comprises: User feature extraction: This solution assigns an independent local sub-model to each user. Each user uses their own local sub-model to extract local data (i.e., the signal strength information received by the user end) features, and finally generates a deep local feature and uploads it to the server; Transmitter information estimation: The server receives local features from all users and uses them as input to the decision sub-model. The decision sub-model first uses the attention mechanism in the model input layer to assign importance to data from different users, and then obtains transmitter information through subsequent neural network layer inference. Finally, the transmitter information is visualized and combined with the static geographic environment image to form a two-channel image; Radio map generation: The two-channel image is input into the pre-trained U-Net model to generate the radio map, and finally the radio map estimation result is obtained.

[0012] Specifically in the application scenario, assuming that there are K users in each time period in the same L1*L2 area, the vertical federated learning model requires K+1 sub-models, including K user local sub-models located on the user side and 1 decision sub-model located on the server side. The received signal strength at the user's location is determined by large-scale fading (including path loss and shadow fading), transmitter power, and additive noise. The specific implementation process of the solution in this scenario is as follows: Each user uses the user location and received signal strength as the input of the local sub-model to calculate the local features. Each user's local sub-model is a fully connected neural network, but the parameters are independent and not shared; The user uploads local features to the server; The server receives local features from all K users as input to the decision sub-model, which consists of an attention layer at the input layer and a subsequent fully connected neural network.

[0013] The attention mechanism of the input layer of the decision sub-model performs adaptive importance detection and weight allocation on user features; FCNN (fully connected neural network) processes user features with importance weights to derive transmitter information including transmitter location and transmission signal strength; The transmitter information is visualized as a grayscale image of size L1*L2, that is, a picture representing the signal strength of the transmitter location, where the grayscale value corresponding to the coordinates of the transmitter is 255, and the other coordinates are 0, and a two-channel picture is formed with a geographic grayscale image of the building environment image of size L1*L2 corresponding to the area where the transmitter is located; Input the two channels into the U-Net network to generate a radio map; Outputs transmitter information and radio maps.

[0014] The local sub-model and the decision sub-model are trained by vertical federated learning. The training process includes: A1. For data sample n, each user k uses the local sub-model to extract deep data features and uploads them to the server; the server receives the deep data features from all users as input to the decision sub-model and obtains the predicted value of the transmitter information; A2. Calculate the mean square error between the predicted value of the transmitter information and the true label at the server as the training loss; A3. After traversing all data samples and calculating the training loss, the gradient of the decision sub-model is calculated based on the training loss through back propagation. A4. For each user k, calculate the partial derivative of the training loss with respect to the deep data features output by user k (traverse the data samples and sum them) and send it back to the user; A5. Based on the partial derivatives transmitted above, each user k calculates the gradient of the local sub-model using the back-propagation method. A6. Update all local sub-model and decision sub-model parameters; A7. Loop A1-A6 until the set training round is reached.

[0015] The sample set used in the vertical federated learning includes multiple samples; The label of each sample is stored in the server, which is the transmitter location and strength; The sample features of each sample include: local features located at each user, namely the user position and the corresponding received signal strength; Each sample is obtained by the server collecting the transmitter position and strength at different historical moments, and each user terminal collecting its own position and the corresponding received signal strength.

[0016] When the U-Net model is pre-trained, it is necessary to first construct a sample set, and the sample features are: a two-channel image, consisting of an image representing the signal strength of the transmitter location and a geographic grayscale image of the building environment image; the sample label is the radio map information; After pre-training the U-Net model with the sample set, the U-Net model can predict the radio map information based on the input two-channel image; like Figure 3 As shown in the figure, the collaborative training effect of the model under the vertical federated learning framework (the number of users is 128, and the error of transmitter position and strength estimation with and without attention is shown respectively); the error changes during the training process are recorded. The error consists of two parts: transmitter position estimation error and transmitter strength estimation error. The error of the network with attention decreases faster, which means that adding the attention mechanism can help the VFL network achieve higher estimation accuracy. Figure 4 The difference in estimation accuracy under different numbers of users, the number of users are (a): 64, (b): 128, (c): 200. (d) is the real label for comparison, showing the relationship between the number of users and the final radiomap output accuracy (the final radiomap is the final output of the VFL+UNet network in series). When the number of users is > 64, the estimated radiomap and the real radiomap label are already close. When the number of users is > 200, the estimated radiomap is basically indistinguishable from the real radiomap label, indicating that the increase in the number of users can improve the estimation accuracy of the radiomap, and when the number of users reaches more than 200, the estimated radiomap is accurate enough.

[0017] The above is a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention, and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A distributed radio map perception method with privacy protection in a wireless network, characterized by: The following steps are involved: S1. Each user is assigned an independent local sub-model. The user uses their own local sub-model to extract local data features, and finally generates a deep local feature and uploads it to the server; S2. Configure the decision sub-model for the server. The server receives local features from all users as inputs to the decision sub-model. The decision sub-model first uses the attention mechanism in the model input layer to assign importance to data from different users, and then obtains transmitter information through subsequent neural network layer reasoning. Finally, the transmitter information is visualized to obtain a picture representing the signal strength of the transmitter location, and forms a two-channel picture with the building environment picture. S3. Input the two-channel image into the pre-trained U-Net model to generate a radio map, and finally obtain the radio map estimation result.

2. According to claim 1, a distributed radio map perception method for privacy protection in a wireless network is characterized by: The local data is the signal strength information received by the user end.

3. The distributed radio map perception method for privacy protection in a wireless network according to claim 1, characterized in that: In step S1, each user uses the user position and received signal strength as inputs of a local sub-model to calculate local features; wherein each user's local sub-model is a fully connected neural network, but the parameters are independent and not shared.

4. The distributed radio map perception method for privacy protection in a wireless network according to claim 1, characterized in that: The step S2 comprises: S201. The server uses the local features received from all K users as inputs of a decision sub-model, where the decision sub-model consists of an attention layer located at the input layer and a subsequent fully connected neural network; S202. The attention mechanism of the input layer of the decision sub-model performs adaptive importance detection and weight allocation on user features; S203. Using a fully connected neural network to process user features carrying importance weights, transmitter information including transmitter location and transmission signal strength is obtained; S304. Visualize the transmitter information as a grayscale image of size L1*L2, that is, a picture representing the signal strength at the transmitter location, where the grayscale value corresponding to the coordinates of the transmitter is 255, and the other coordinates are 0, and form a two-channel picture with the geographic grayscale map of the building environment image of size L1*L2 corresponding to the area.

5. The distributed radio map perception method for privacy protection in a wireless network according to claim 1, characterized in that: The local sub-model and the decision sub-model are trained by vertical federated learning. The training process includes: A1. For data sample n, each user k uses the local sub-model to extract deep data features and uploads them to the server; the server receives the deep data features from all users as input to the decision sub-model and obtains the predicted value of the transmitter information; A2. Calculate the mean square error between the predicted value of the transmitter information and the true label at the server as the training loss; A3. After traversing all data samples and calculating the training loss, the gradient of the decision sub-model is calculated based on the training loss through back propagation. A4. For each user k, the server calculates the partial derivative of the training loss with respect to the deep data features output by user k and transmits it back to the user; A5. Based on the partial derivatives transmitted above, each user k calculates the gradient of the local sub-model using the back-propagation method. A6. Update all local sub-model and decision sub-model parameters; A7. Loop A1-A6 until the set training round is reached.

6. The distributed radio map perception method for privacy protection in a wireless network according to claim 5, characterized in that: The sample set used in the vertical federated learning includes multiple samples; The label of each sample is stored in the server, which is the transmitter location and strength; The sample features of each sample include: local features located at each user, namely the user position and the corresponding received signal strength; Each sample is obtained by the server collecting the transmitter position and strength at different historical moments, and each user terminal collecting its own position and the corresponding received signal strength.

7. The distributed radio map perception method for privacy protection in a wireless network according to claim 1, characterized in that: When the U-Net model is pre-trained, it is necessary to first construct a sample set, and the sample features are: a two-channel image, consisting of an image representing the signal strength of the transmitter location and a geographic grayscale image of the building environment image; the sample label is the radio map information; After pre-training the U-Net model with the sample set, the U-Net model can predict the radio map information based on the input two-channel image.

Images