Energy storage wireless BMS data transmission method, device, equipment and storage medium

Abstract

The present invention discloses a method, apparatus, device, and storage medium for transmitting data in an energy storage wireless BMS. The method comprises: receiving a transmission request initiated by a decryption party; verifying the public key certificate of the decryption party using a pre-set certificate; and, after verification, compressing and encrypting the original data to be transmitted using a chaotic mapping rule to obtain an encrypted data stream; inputting the encrypted data stream into a wireless signal encryption model, generating a carrier image in the wireless signal encryption model through adversarial training optimization of an encoder, embedding the carrier image into an environmental image, and generating a transmission image; and sending the transmission image to the decryption party. The present invention utilizes a dual security mechanism of chaotic mapping rules and wireless signal encryption models to achieve secure data transmission from battery cells to a monitoring system, thereby eliminating the risk of data interception in the energy storage wireless BMS communication system.

Description

Technical Field

[0001] The present application belongs to the field of battery management system security communication technology, and in particular relates to a method, device, equipment and storage medium for energy storage wireless BMS data transmission. Background Art

[0002] With the continuous advancement of energy storage technology, wireless BMSs in grid-scale energy storage power plants can be exploited. By monitoring wireless signals (such as Zigbee / LoRa communications) over a long period of time and analyzing characteristics such as packet length, transmission period, and signal strength, attackers can establish a mapping between battery state of charge (SOC) / state of health (SOH) and wireless communication patterns. By inferring battery SOC / SOH, attackers can predict the energy storage power plant's scheduling strategy, enabling malicious bidding and potentially disrupting grid stability. Therefore, the security of data transmission in energy storage wireless BMSs faces severe challenges.

[0003] However, in the existing technology, encryption algorithms such as AES are usually used to protect only data content. Not only can they not hide the characteristics of communication behavior, but the fixed key update cycle is easily cracked by statistical attacks, and cannot effectively defend against destructive behaviors targeting battery status and power grids. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a method, apparatus, device and storage medium for energy storage wireless BMS data transmission, which realizes the secure transmission of data from battery cells to the monitoring system through the dual security mechanism of chaotic mapping rules and wireless signal encryption model, thereby solving the risk of data interception in the energy storage wireless BMS communication system.

[0005] A first aspect of an embodiment of the present application provides a method for transmitting energy storage wireless BMS data, including:

[0006] receiving a transmission request initiated by a decryption party, wherein the transmission request carries the public key certificate of the decryption party;

[0007] The public key certificate of the decryption party is verified by a pre-set certificate. After the verification is passed, the original data to be transmitted is compressed and encrypted using a chaotic mapping rule to obtain an encrypted data stream;

[0008] Inputting the encrypted data stream into a pre-trained wireless signal encryption model, generating a carrier image in the wireless signal encryption model, and embedding the carrier image into the environment image through an adversarial training optimized encoder to generate a transmission image;

[0009] The transmission image is sent to the decryption party, so that the decryption party extracts the encrypted data stream through the jointly trained wireless signal decryption model and decrypts the encrypted data stream based on the encrypted authentication message.

[0010] In one embodiment, the transmission request further carries a random number; and the compressing and encrypting the original data to be transmitted using a chaotic mapping rule includes:

[0011] Convert the original data into a binary byte stream, and count the occurrence probability of each byte value in the byte stream;

[0012] Initializing mapping parameters of the chaotic mapping rule based on the random number, adjusting the mapping parameters according to the occurrence probability of each byte value, and generating encrypted bytes;

[0013] The original data is encrypted based on the encryption bytes to obtain an encrypted data stream.

[0014] In one embodiment, inputting the encrypted data stream into a pre-trained wireless signal encryption model to generate a carrier image includes:

[0015] The encrypted data stream is input into a pre-trained wireless signal encryption model, in which the dynamic time series features of the encrypted data stream are captured; the dynamic time series features are gradually reduced in dimension, and the features after the gradual dimensionality reduction are encoded and decoded to generate the carrier image.

[0016] In one embodiment, capturing the dynamic timing characteristics of the encrypted data stream includes:

[0017] Performing segmented time-series processing on the encrypted data stream to obtain a time sequence;

[0018] The network parameters of the wireless signal encryption model are configured based on the timing sequence, and the dynamic timing features are extracted based on the configured wireless signal encryption model.

[0019] In one embodiment, the step of gradually reducing the dimension of the dynamic time series features, encoding and decoding the features after the gradual dimension reduction, and generating the carrier image includes:

[0020] Compressing the dynamic temporal features based on a fully connected layer, and downsampling the compressed features based on a multi-layer convolutional encoder;

[0021] Based on the multi-layer deconvolution decoder, the pooled features of the last layer of the multi-layer convolution encoder are upsampled, and during the upsampling process, the output features of each layer are spliced ​​with the output features of the corresponding layer of the multi-layer convolution encoder as the upsampled features of the corresponding layer, until the last layer of the multi-layer deconvolution decoder outputs the carrier image.

[0022] In one embodiment, the carrier image includes an image whose encrypted signal features are not recognizable to the human eye; and embedding the carrier image into the environment image through adversarial training to optimize the encoder to generate the transmission image includes:

[0023] Selecting an environment image from a monitoring image library of a battery monitoring system, and adjusting the size of the environment image to be consistent with the carrier image;

[0024] The carrier image and the environment image are input into the encoder for adversarial training, and the loss function of the encoder is continuously optimized until the encoder cannot recognize the environment image and the carrier image, and the carrier image is embedded into the environment image to generate the transmission image.

[0025] In one embodiment, the environment image includes normal battery status parameters, and the carrier image includes hidden battery status parameters; the loss function includes an adversarial loss function, a reconstruction loss function, and a classification loss function;

[0026] The step of inputting the carrier image and the environment image into an encoder for adversarial training and continuously optimizing the loss function of the encoder until the encoder is unable to recognize the environment image and the carrier image, and then embedding the carrier image into the environment image to generate the transmission image includes:

[0027] The carrier image and the environment image are spliced ​​and input into the encoder. In the encoder, residual connection and attention mechanism are used to determine the target area in the environment image for embedding the carrier image and to perform hierarchical protection on the battery status parameters in the environment image. A spatial adaptive strategy is used to embed the carrier image in the target area. At the same time, the adversarial loss function, reconstruction loss function and classification loss function are continuously optimized until the adversarial loss function, reconstruction loss function and classification loss function all meet the preset conditions, thereby completing the embedding of the carrier image into the environment image and generating a transmission image.

[0028] A second aspect of the present application provides an energy storage wireless BMS data transmission device, including:

[0029] A receiving module, configured to receive a transmission request initiated by a decryption party, wherein the transmission request carries the public key certificate of the decryption party;

[0030] The encryption module is used to verify the public key certificate of the decryption party through the pre-set certificate, and after the verification is passed, the chaotic mapping rule is used to compress and encrypt the original data to be transmitted to obtain an encrypted data stream;

[0031] a generation module, configured to input the encrypted data stream into a pre-trained wireless signal encryption model, generate a carrier image in the wireless signal encryption model, and embed the carrier image into an environment image through an adversarial training optimized encoder to generate a transmission image;

[0032] A sending module is used to send the transmission image to the decryption party, so that the decryption party extracts the encrypted data stream through the jointly trained wireless signal decryption model and decrypts the encrypted data stream based on the encrypted authentication message.

[0033] In one embodiment, the transmission request further carries a random number; the encryption module includes:

[0034] a statistical unit, configured to convert the raw data into a binary byte stream and to count the occurrence probability of each byte value in the byte stream;

[0035] An adjusting unit, configured to initialize a mapping parameter of a chaotic mapping rule based on the random number, adjust the mapping parameter according to the occurrence probability of each byte value, and generate an encrypted byte;

[0036] The encryption unit is used to encrypt the original data based on the encryption bytes to obtain an encrypted data stream.

[0037] In one embodiment, the generating module is specifically configured to:

[0038] The encrypted data stream is input into a pre-trained wireless signal encryption model, in which the dynamic time series features of the encrypted data stream are captured; the dynamic time series features are gradually reduced in dimension, and the features after the gradual dimensionality reduction are encoded and decoded to generate the carrier image.

[0039] In one embodiment, the generating module is specifically configured to:

[0040] Performing segmented time-series processing on the encrypted data stream to obtain a time sequence;

[0041] The network parameters of the wireless signal encryption model are configured based on the timing sequence, and the dynamic timing features are extracted based on the configured wireless signal encryption model.

[0042] In one embodiment, the generating module is specifically configured to:

[0043] Compressing the dynamic temporal features based on a fully connected layer, and downsampling the compressed features based on a multi-layer convolutional encoder;

[0044] Based on the multi-layer deconvolution decoder, the pooled features of the last layer of the multi-layer convolution encoder are upsampled, and during the upsampling process, the output features of each layer are spliced ​​with the output features of the corresponding layer of the multi-layer convolution encoder as the upsampled features of the corresponding layer, until the last layer of the multi-layer deconvolution decoder outputs the carrier image.

[0045] In one embodiment, the generating module includes:

[0046] an adjustment unit, configured to select an environment image from a monitoring image library of the battery monitoring system and adjust the size of the environment image to be consistent with the carrier image;

[0047] A generation unit is used to input the carrier image and the environment image into the encoder for adversarial training, and continuously optimize the loss function of the encoder until the encoder cannot recognize the environment image and the carrier image, and then complete the embedding of the carrier image into the environment image to generate the transmission image.

[0048] In one embodiment, the environment image includes normal battery status parameters, and the carrier image includes hidden battery status parameters; the loss function includes an adversarial loss function, a reconstruction loss function, and a classification loss function;

[0049] The generation module is specifically used to:

[0050] The carrier image and the environment image are spliced ​​and input into the encoder. In the encoder, residual connection and attention mechanism are used to determine the target area in the environment image for embedding the carrier image and to perform hierarchical protection on the battery status parameters in the environment image. A spatial adaptive strategy is used to embed the carrier image in the target area. At the same time, the adversarial loss function, reconstruction loss function and classification loss function are continuously optimized until the adversarial loss function, reconstruction loss function and classification loss function all meet the preset conditions, thereby completing the embedding of the carrier image into the environment image and generating a transmission image.

[0051] A third aspect of an embodiment of the present application provides an energy storage wireless BMS data transmission device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the steps of the energy storage wireless BMS data transmission method described in the first aspect above are implemented.

[0052] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the energy storage wireless BMS data transmission method as described in the first aspect above are implemented.

[0053] The beneficial effects of the embodiments of the present application are as follows: after receiving a transmission request initiated by a decryption party, the public key certificate of the decryption party is verified using a pre-set certificate. After verification, the original data to be transmitted is compressed and encrypted using chaotic mapping rules to obtain an encrypted data stream; the encrypted data stream is input into a wireless signal encryption model, and a carrier image is generated in the wireless signal encryption model through adversarial training to optimize the encoder. The carrier image is embedded into the environment image to generate a transmission image; and the transmission image is sent to the decryption party. The present invention achieves secure data transmission from battery cells to the monitoring system through the dual security mechanism of chaotic mapping rules and wireless signal encryption models, eliminating the risk of data interception in energy storage wireless BMS communication systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] Figure 1 A flowchart of a method for transmitting energy storage wireless BMS data in accordance with an embodiment of the present application is provided;

[0056] Figure 2 A schematic diagram of an energy storage wireless BMS data transmission device provided in one embodiment of the present application;

[0057] Figure 3 A schematic diagram of an energy storage wireless BMS data transmission device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0058] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0060] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0061] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0062] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0063] In the description of the embodiments of the present application, the term "multi-frame" refers to two or more (including two).

[0064] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0065] The embodiment of the present application provides a method for transmitting data of a wireless energy storage BMS. Through the dual security mechanism of chaotic mapping rules and wireless signal encryption model, the method realizes the secure transmission of data from battery cells to the monitoring system, thereby eliminating the risk of data interception in the communication system of the wireless energy storage BMS.

[0066] See also Figure 1 As shown, Figure 1This is a flow chart of a method for transmitting data to a wireless BMS for energy storage provided in one embodiment of the present application. The method for transmitting data to a wireless BMS for energy storage provided in this embodiment of the present application is implemented by exchanging data between battery cells in the wireless BMS system and the monitoring system. This is illustrated by way of example using battery cells as the data transmission party and the monitoring system as the data decryption party. Details are as follows:

[0067] S101: Receive a transmission request initiated by a decryption party, where the transmission request carries the public key certificate of the decryption party.

[0068] In this embodiment, the decryption party is the monitoring system in the energy storage wireless BMS system, which initiates a transmission request to the data transmission party (battery cell). The transmission request carries the public key certificate of the decryption party for identity authentication and data encryption.

[0069] S102: The public key certificate of the decryption party is verified by the preset certificate. After the verification is passed, the original data to be transmitted is compressed and encrypted using the chaotic mapping rule to obtain an encrypted data stream.

[0070] Specifically, the transmitting party pre-sets a trusted certificate library to verify the legitimacy of the decrypting party's public key certificate. For example, by checking whether the certificate signature is issued by a trusted authority and verifying whether the certificate's validity period and purpose match.

[0071] The transmission request also carries a random number, which is used to initialize the subsequent chaotic mapping parameters and enhance the randomness of the encryption.

[0072] Specifically, a chaotic mapping rule is used to compress and encrypt the original data to be transmitted. This includes: converting the original data (e.g., voltage 3.7V, current 2.1A, temperature 25°C, etc.) into a binary byte stream, such as 0x3A, 0x21 / 0x19, and calculating the probability of occurrence of each byte value in the byte stream (e.g., 0x3A has a 15% probability of occurrence, 0x21 has a 10% probability of occurrence, etc.); and initializing the chaotic mapping rule based on a random number in the transmission request (e.g., 0x3A7F...D9E2). In this embodiment, Logstic is used as the chaotic mapping. Initializing the chaotic mapping rule includes initializing the initial conditions and control parameters. For example, the initial condition after initialization is x_{n+1} = μx_n(1-x_n), where the initial control parameter μ = 3.9 (specifically, μ is randomly selected from the interval [3.7, 4.0] after hashing the random number 0x3A7F...D9E2). Based on the probability of occurrence of each byte value, the mapping parameters of the chaotic mapping are adjusted so that high-frequency bytes correspond to stronger chaotic perturbations. This chaotic mapping is then iteratively generated into a pseudo-random sequence, which serves as the encryption byte. The original data is then encrypted based on the encryption byte. Specifically, the pseudo-random sequence can be XORed with the original byte stream to produce an encrypted data stream. Specifically, during the mapping process, the chaotic effect is enhanced for high-frequency bytes by increasing the control parameter μ. For example, for the high-frequency byte 0x3A, μ is increased to 3.95 to enhance the chaotic effect. After completing the chaotic mapping for each byte value, the pseudo-random sequence is generated, which is then XORed with the original data to produce the encrypted data stream.

[0073] Since the chaotic map is sensitive to initial conditions, slight changes can lead to completely different encryption results, ensuring data unpredictability.

[0074] S103: Input the encrypted data stream into a pre-trained wireless signal encryption model, generate a carrier image in the wireless signal encryption model, and embed the carrier image into the environment image through adversarial training optimization encoder to generate a transmission image.

[0075] While chaotic encryption can protect data content, the encrypted data stream still exhibits distinct communication patterns (e.g., fixed packet lengths and timed transmissions), allowing attackers to identify BMS communication nodes. Furthermore, the encrypted data stream is a pseudo-random sequence, and directly embedding it into an image can lead to statistical anomalies (e.g., unnatural pixel value distribution). In this application, by extracting temporal correlations, the random data stream is converted into a carrier image with spatial regularity (e.g., generating a textured noise pattern), thus preventing detection by steganalysis tools.

[0076] Exemplarily, the carrier image is generated in a pre-trained wireless signal encryption model by inputting the encrypted data stream into the pre-trained wireless signal encryption model. Specifically, this includes: inputting the encrypted data stream into the pre-trained wireless signal encryption model, capturing the dynamic time series features of the encrypted data stream in the wireless signal encryption model; performing step-by-step dimensionality reduction on the dynamic time series features, and encoding and decoding the reduced features to generate the carrier image.

[0077] Capturing the dynamic timing characteristics of the encrypted data stream includes: segmenting the encrypted data stream into time series to obtain a time series; configuring network parameters of a wireless signal encryption model based on the time series; and extracting dynamic timing characteristics based on the configured wireless signal encryption model. Specifically, pre-trained wireless signal encryption models include, but are not limited to, LSTM networks or Transfrom networks.

[0078] For example, using a pre-trained wireless signal encryption model as an LSTM network, the encrypted data stream 0x64 0x08... is input into the LSTM network and divided into multiple time windows. For example, each time window is 10ms, and each time window contains 16 bytes (a 16-dimensional vector). For example, time window 1 is represented as: 0x64 0x08..., and time window 2 is represented as: 0x3F 0x12.... The LSTM network has 128 hidden units and outputs the time series features (128-dimensional vectors) for each time window. The resulting time series feature matrix (shape N × 126, where N is the number of windows) serves as the dynamic time series features.

[0079] The dynamic time series features are gradually reduced in dimension, and the features after the gradual dimensionality reduction are encoded and decoded to generate a carrier image, including: compressing the dynamic time series features based on the fully connected layer, and down-sampling the compressed features based on the multi-layer convolution encoder; up-sampling the pooled features of the last layer of the multi-layer convolution encoder based on the multi-layer deconvolution decoder, and in the upsampling process, splicing the output features of each layer with the output features of the corresponding layer of the multi-layer convolution encoder as the up-sampled features of the corresponding layer, until the last layer of the multi-layer deconvolution decoder outputs the carrier image.

[0080] For example, in this embodiment, the fully connected layer compresses 128-dimensional features to 64-dimensional features (reducing redundancy). The multi-layer convolutional encoder is a three-layer convolutional encoder, and the multi-layer deconvolutional encoder is also a three-layer deconvolutional encoder. Downsampling the compressed features based on the multi-layer convolutional encoder can be exemplarily expressed as:

[0081] Layer 1: Conv2D(64, kernel=3x3, stride=2) → output 32x32x64.

[0082] Layer 2: Conv2D(128, kernel=3x3, stride=2) → output 16x16x128.

[0083] Layer 3: Conv2D(256, kernel=3x3, stride=2) → Output 8x8x256 (low-dimensional features).

[0084] The upsampling of the pooled features of the last layer of the multi-layer convolution encoder based on the multi-layer deconvolution decoder can be exemplarily expressed as:

[0085] Layer 1: Deconvolution 8x8x256 + concatenation 16x16x128 → output 16x16x128.

[0086] Layer 2: Deconvolution 16x16x128 + concatenation 32x32x64 → output 32x32x64.

[0087] Layer 3: Deconvolution 32x32x64 → Output 64x64x1 (single-channel grayscale carrier image).

[0088] From the above analysis, we can see that the carrier image is a 64×64 unrecognizable noise pattern (containing encrypted data features).

[0089] The carrier image includes an image that is unrecognizable to the human eye with encrypted signal features; the carrier image is embedded into the environmental image through adversarial training to optimize the encoder to generate a transmission image, including: selecting an environmental image from a monitoring image library of a battery monitoring system, and adjusting the size of the environmental image to be consistent with the carrier image; inputting the carrier image and the environmental image into the encoder for adversarial training, and continuously optimizing the encoder's loss function until the encoder can no longer recognize the environmental image and the carrier image, thereby completing the embedding of the carrier image into the environmental image to generate a transmission image.

[0090] The environmental image includes normal battery status parameters, and the carrier image includes hidden battery status parameters; the loss function includes an adversarial loss function, a reconstruction loss function, and a classification loss function. The carrier image and the environmental image are input into the encoder for adversarial training, and the encoder's loss function is continuously optimized until the encoder is unable to recognize the environmental image and the carrier image. The carrier image is then embedded into the environmental image to generate a transmission image, including: splicing the carrier image and the environmental image and inputting them into the encoder. The encoder uses a residual connection and an attention mechanism to determine the target area in the environmental image for embedding the carrier image and hierarchically protects the battery status parameters in the environmental image. A spatial adaptive strategy is used to embed the carrier image in the target area. At the same time, the adversarial loss function, the reconstruction loss function, and the classification loss function are continuously optimized until the adversarial loss function, the reconstruction loss function, and the classification loss function all meet the preset conditions. The carrier image is then embedded into the environmental image to generate a transmission image.

[0091] For example, in this embodiment, the ambient image is assumed to include a battery temperature distribution map (a 64×64 RGB image). The carrier image and the ambient image are concatenated and fed into the encoder. The encoder's residual connections, such as ResNet, prevent vanishing gradients. The encoder's attention mechanism includes channel attention, which weights important feature channels such as high-frequency regions (as target regions for embedding into the carrier image); spatial attention, which locates low-texture regions such as the edges of the temperature map; and an attention mask, which assigns higher embedding weights to key parameters such as overvoltage data (implementing layered protection). Within the target regions located by the attention mechanism, the carrier image pixels are weightedly overlaid onto the ambient image based on the weighted results of the attention mask. During this process, the discriminator attempts to distinguish between the transmitted image and the ambient image. This requires continuous optimization of the encoder based on an adversarial loss function to improve the encoder's ability to deceive the discriminator. The classification loss function is continuously optimized to ensure that the discriminator maintains the correct classification of the original parameters in the ambient image. The reconstruction loss function is also continuously optimized to ensure that the wireless signal decryption model jointly trained by the decryption parties can recover the carrier image from the transmitted image.

[0092] Ultimately, the appearance of the transmitted image obtained in the embodiment of the present application is consistent with the environmental image, but the encrypted data is hidden (indistinguishable to the human eye).

[0093] S104: Sending the transmission image to the decryption party, so that the decryption party extracts the encrypted data stream through the jointly trained wireless signal decryption model and decrypts the encrypted data stream based on the encrypted authentication message.

[0094] Specifically, the decryption party recovers the carrier image from the transmitted image using the jointly trained decryption model and decodes the encrypted data. The decryption party then decrypts the encrypted data based on the chaotic map parameters and the certificate system, and verifies the completeness of the decryption process to obtain the original data. This embodiment of the present application does not further elaborate on the decryption process of the transmitted image.

[0095] Through the above analysis, it can be seen that the energy storage wireless BMS data transmission method provided by the embodiment of the present application, after receiving the transmission request initiated by the decryption party, verifies the public key certificate of the decryption party through the preset certificate. After the verification is passed, the chaotic mapping rule is used to compress and encrypt the original data to be transmitted to obtain an encrypted data stream; the encrypted data stream is input into the wireless signal encryption model, and the encoder is optimized through adversarial training in the wireless signal encryption model to generate a carrier image, and the carrier image is embedded in the environmental image to generate a transmission image; and the transmission image is sent to the decryption party. The present invention realizes the secure transmission of data from battery cells to the monitoring system through the dual security mechanism of chaotic mapping rules and wireless signal encryption models, thereby solving the risk of data interception in the energy storage wireless BMS communication system.

[0096] See Figure 2 , Figure 2 Schematic diagram of an energy storage wireless BMS data transmission device provided in one embodiment of the present application. The energy storage wireless BMS data transmission device 200 includes various modules or units for executing Figure 1 Each step in the corresponding embodiment. Please refer to Figure 1 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 2 , the energy storage wireless BMS data transmission device 200, comprising:

[0097] The receiving module 210 is configured to receive a transmission request initiated by a decryption party, wherein the transmission request carries the public key certificate of the decryption party;

[0098] The encryption module 220 is used to verify the public key certificate of the decryption party through the pre-set certificate, and after the verification is passed, the chaotic mapping rule is used to compress and encrypt the original data to be transmitted to obtain an encrypted data stream;

[0099] a generation module 230 for inputting the encrypted data stream into a pre-trained wireless signal encryption model, generating a carrier image in the wireless signal encryption model, and embedding the carrier image into an environment image through an adversarial training optimized encoder to generate a transmission image;

[0100] The sending module 240 is used to send the transmission image to the decryption party, so that the decryption party extracts the encrypted data stream through the jointly trained wireless signal decryption model and decrypts the encrypted data stream based on the encrypted authentication message.

[0101] In one embodiment, the transmission request further carries a random number; the encryption module 220 includes:

[0102] a statistical unit, configured to convert the raw data into a binary byte stream and to count the occurrence probability of each byte value in the byte stream;

[0103] An adjusting unit, configured to initialize a mapping parameter of a chaotic mapping rule based on the random number, adjust the mapping parameter according to the occurrence probability of each byte value, and generate an encrypted byte;

[0104] The encryption unit is used to encrypt the original data based on the encryption bytes to obtain an encrypted data stream.

[0105] In one embodiment, the generating module 230 is specifically configured to:

[0106] The encrypted data stream is input into a pre-trained wireless signal encryption model, in which the dynamic time series features of the encrypted data stream are captured; the dynamic time series features are gradually reduced in dimension, and the features after the gradual dimensionality reduction are encoded and decoded to generate the carrier image.

[0107] In one embodiment, the generating module 230 is specifically configured to:

[0108] Performing segmented time-series processing on the encrypted data stream to obtain a time sequence;

[0109] The network parameters of the wireless signal encryption model are configured based on the timing sequence, and the dynamic timing features are extracted based on the configured wireless signal encryption model.

[0110] In one embodiment, the generating module 230 is specifically configured to:

[0111] Compressing the dynamic temporal features based on a fully connected layer, and downsampling the compressed features based on a multi-layer convolutional encoder;

[0112] Based on the multi-layer deconvolution decoder, the pooled features of the last layer of the multi-layer convolution encoder are upsampled, and during the upsampling process, the output features of each layer are spliced ​​with the output features of the corresponding layer of the multi-layer convolution encoder as the upsampled features of the corresponding layer, until the last layer of the multi-layer deconvolution decoder outputs the carrier image.

[0113] In one embodiment, the generating module 230 includes:

[0114] an adjustment unit, configured to select an environment image from a monitoring image library of the battery monitoring system and adjust the size of the environment image to be consistent with the carrier image;

[0115] A generation unit is used to input the carrier image and the environment image into the encoder for adversarial training, and continuously optimize the loss function of the encoder until the encoder cannot recognize the environment image and the carrier image, and then complete the embedding of the carrier image into the environment image to generate the transmission image.

[0116] In one embodiment, the environment image includes normal battery status parameters, and the carrier image includes hidden battery status parameters; the loss function includes an adversarial loss function, a reconstruction loss function, and a classification loss function;

[0117] The generating module 230 is specifically configured to:

[0118] The carrier image and the environment image are spliced ​​and input into the encoder. In the encoder, residual connection and attention mechanism are used to determine the target area in the environment image for embedding the carrier image and to perform hierarchical protection on the battery status parameters in the environment image. A spatial adaptive strategy is used to embed the carrier image in the target area. At the same time, the adversarial loss function, reconstruction loss function and classification loss function are continuously optimized until the adversarial loss function, reconstruction loss function and classification loss function all meet the preset conditions, thereby completing the embedding of the carrier image into the environment image and generating a transmission image.

[0119] See Figure 3 , Figure 3 This is a schematic diagram of an energy storage wireless BMS data transmission device provided by an embodiment of the present application. Figure 3 It can be seen that the energy storage wireless BMS data transmission device 300 includes: a processor 310, a memory 320, and a computer program 330 stored in the memory 320 and executable on the processor 310; when the processor 310 executes the computer program 330, the steps in the above-mentioned embodiments of the energy storage wireless BMS data transmission method are implemented, such as Figure 1 Alternatively, when the processor 310 executes the computer program 330, the functions of the modules / units in the above-mentioned device embodiments are realized, for example Figure 2 The functions of the modules 210 to 240 are shown.

[0120] Exemplarily, computer program 330 can be divided into one or more modules / units, one or more of which are stored in memory 320 and executed by processor 310 to implement the present application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of computer program 330 in the energy storage wireless BMS data transmission device. For example, computer program 330 can be divided into a receiving module, an encryption module, a generation module, and a merging module.

[0121] The energy storage wireless BMS data transmission device provided in this embodiment may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 3 The present invention is merely an example of an energy storage wireless BMS data transmission device and does not constitute a limitation on the energy storage wireless BMS data transmission device. The present invention may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the energy storage wireless BMS data transmission device may also include input and output devices, network access devices, buses, etc.

[0122] The processor 310 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0123] Memory 320 can be an internal storage unit of the energy storage wireless BMS data transmission device, such as a hard drive or memory. Memory 320 can also be an external storage device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash memory card. Furthermore, the energy storage wireless BMS data transmission device can include both an internal storage unit and an external storage device. Memory 320 is used to store computer programs and other programs and data required by the energy storage wireless BMS data transmission device. Memory 320 can also be used to temporarily store data that has been output or is about to be output.

[0124] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0125] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0126] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0127] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0128] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0129] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0130] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0131] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0133] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for transmitting energy storage wireless BMS data, characterized in that: The method comprises: Receive a transmission request initiated by a decryption party, the transmission request carrying the public key certificate of the decryption party and a random number; Verify the public key certificate of the decryption party through the pre-set certificate, convert the original data into a binary byte stream after verification, and count the occurrence probability of each byte value in the byte stream; Initializing mapping parameters of the chaotic mapping rule based on the random number, adjusting the mapping parameters according to the occurrence probability of each byte value, and generating encrypted bytes; Encrypting the original data based on the encryption bytes to obtain an encrypted data stream; Inputting the encrypted data stream into a pre-trained wireless signal encryption model, capturing the dynamic time series features of the encrypted data stream in the wireless signal encryption model; gradually reducing the dimension of the dynamic time series features, encoding and decoding the features after the gradual dimensionality reduction to generate a carrier image, and embedding the carrier image into the environment image through adversarial training to optimize the encoder to generate a transmission image; The transmission image is sent to the decryption party, so that the decryption party extracts the encrypted data stream through the jointly trained wireless signal decryption model and decrypts the encrypted data stream based on the encrypted authentication message.

2. The energy storage wireless BMS data transmission method according to claim 1, characterized in that: The capturing of the dynamic timing characteristics of the encrypted data stream includes: Performing segmented time-series processing on the encrypted data stream to obtain a time sequence; The network parameters of the wireless signal encryption model are configured based on the timing sequence, and the dynamic timing features are extracted based on the configured wireless signal encryption model.

3. The energy storage wireless BMS data transmission method according to claim 2, characterized in that: The step of gradually reducing the dimension of the dynamic time series features, encoding and decoding the features after the gradual dimension reduction, and generating the carrier image includes: Compressing the dynamic temporal features based on a fully connected layer, and downsampling the compressed features based on a multi-layer convolutional encoder; Based on the multi-layer deconvolution decoder, the pooled features of the last layer of the multi-layer convolution encoder are upsampled, and during the upsampling process, the output features of each layer are spliced ​​with the output features of the corresponding layer of the multi-layer convolution encoder as the upsampled features of the corresponding layer, until the last layer of the multi-layer deconvolution decoder outputs the carrier image.

4. The energy storage wireless BMS data transmission method according to claim 1, characterized in that: The carrier image includes an image that is not recognizable to the human eye and has encrypted signal features; The method of embedding the carrier image into the environment image by optimizing the encoder through adversarial training to generate a transmission image includes: Selecting an environment image from a monitoring image library of a battery monitoring system, and adjusting the size of the environment image to be consistent with the carrier image; The carrier image and the environment image are input into the encoder for adversarial training, and the loss function of the encoder is continuously optimized until the encoder cannot recognize the environment image and the carrier image, and the carrier image is embedded into the environment image to generate the transmission image.

5. The energy storage wireless BMS data transmission method according to claim 4, characterized in that: The environment image includes normal battery status parameters, and the carrier image includes hidden battery status parameters; the loss function includes an adversarial loss function, a reconstruction loss function, and a classification loss function; The step of inputting the carrier image and the environment image into an encoder for adversarial training and continuously optimizing the loss function of the encoder until the encoder is unable to recognize the environment image and the carrier image, and then embedding the carrier image into the environment image to generate the transmission image includes: The carrier image and the environment image are spliced ​​and input into the encoder. In the encoder, residual connection and attention mechanism are used to determine the target area in the environment image for embedding the carrier image and to perform hierarchical protection on the battery status parameters in the environment image. A spatial adaptive strategy is used to embed the carrier image in the target area. At the same time, the adversarial loss function, reconstruction loss function and classification loss function are continuously optimized until the adversarial loss function, reconstruction loss function and classification loss function all meet the preset conditions, thereby completing the embedding of the carrier image into the environment image and generating a transmission image.

6. A wireless BMS data transmission device for energy storage, characterized in that: include: A receiving module, configured to receive a transmission request initiated by a decryption party, wherein the transmission request carries the public key certificate of the decryption party and a random number; An encryption module is used to verify the public key certificate of the decryption party through a pre-set certificate, convert the original data into a binary byte stream after verification, and calculate the probability of occurrence of each byte value in the byte stream; Initializing mapping parameters of the chaotic mapping rule based on the random number, adjusting the mapping parameters according to the occurrence probability of each byte value, and generating encrypted bytes; Encrypting the original data based on the encryption bytes to obtain an encrypted data stream; A generation module, configured to input the encrypted data stream into a pre-trained wireless signal encryption model, and capture the dynamic timing characteristics of the encrypted data stream in the wireless signal encryption model; Stepwise dimensionality reduction is performed on the dynamic time series features, encoding and decoding the features after the stepwise dimensionality reduction to generate a carrier image, and the carrier image is embedded into the environment image through adversarial training to optimize the encoder to generate a transmission image; A sending module is used to send the transmission image to the decryption party, so that the decryption party extracts the encrypted data stream through the jointly trained wireless signal decryption model and decrypts the encrypted data stream based on the encrypted authentication message.

7. A wireless BMS data transmission device for energy storage, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images