Methods, devices, equipment and storage media for enhancing communication in transmission line ad hoc networks

Abstract

This invention provides a method, apparatus, device, and storage medium for enhancing communication in a transmission line ad hoc network, relating to the field of communication technology. The method includes: constructing a hybrid noise model; constructing a wireless ad hoc network channel model; and enhancing communication in the wireless ad hoc network using a distributed waveforming beamforming method based on the hybrid noise model and the wireless ad hoc network channel model. Through this approach, the impact of complex noise in the transmission line scenario on communication and the characteristics of wireless ad hoc network channel transmission are fully considered during the communication enhancement process. This ensures that the enhanced ad hoc network is more adaptable to real transmission line scenarios, optimizes its performance in real transmission line scenarios, improves communication quality, and enhances the reliability of ad hoc network communication.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method, apparatus, equipment, and storage medium for enhancing communication in a power transmission line self-organizing network. Background Technology

[0002] In dense power transmission channels in remote areas, there are large areas that are not covered by public networks and power fiber optic networks, making it difficult to support the collection, transmission, storage and application of full data during maintenance. The lack of communication means has become a key bottleneck restricting the stable operation of dense power transmission channels.

[0003] Wireless ad hoc networks (WANs), as a flexible communication solution, can rapidly transmit service data from power poles and lines. By expanding network coverage through multi-hop interconnection, they overcome the limitations of single devices, adapt to different environments and needs, significantly reduce infrastructure costs, and improve communication reliability. Simultaneously, WANs demonstrate strong adaptability in complex environments, becoming an important means of ensuring the safe and stable operation of dense power transmission channels. However, because the communication paths between ad hoc network devices such as drones, ground terminals, and vehicle-mounted terminals need to traverse areas densely populated with high-voltage transmission lines, they inevitably face strong electromagnetic interference generated by these lines. Furthermore, co-channel interference between different communication links and signal attenuation caused by complex channel environments also negatively impact high-quality communication transmission.

[0004] Beamforming is a technique that controls the direction and coverage of a signal by adjusting the transmit power and phase of each antenna in an antenna array. It can effectively enhance signal strength in the target direction while suppressing interference from other directions, thereby improving communication quality and system capacity. Distributed beamforming extends this concept to multiple nodes located in different positions, which cooperate to optimize signal transmission and reception. Unlike traditional centralized beamforming, distributed beamforming can be flexibly adjusted among different nodes to adapt to environmental changes and user needs, improving system robustness and flexibility. In complex communication environments, especially in the presence of interference and multipath propagation, distributed beamforming can effectively enhance signal reliability and reduce the impact of interference, thus achieving more efficient data transmission.

[0005] To address the issue of various interferences affecting communication quality in wireless ad hoc networks under dense power transmission line scenarios, some solutions have been proposed in existing technologies. For example, beamforming adjustment models can be used to enhance the signal coverage of wireless ad hoc networks, or beamforming technology can be used to reduce the impact of single-source interference on the communication of each node in the wireless ad hoc network.

[0006] However, existing communication enhancement methods perform poorly in real-world scenarios, making it difficult to guarantee the communication quality of wireless ad hoc networks. Summary of the Invention

[0007] This invention provides a method, apparatus, device, and storage medium for enhancing communication in power transmission line ad hoc networks, in order to address the shortcomings of existing communication enhancement methods that perform poorly in real-world scenarios and make it difficult to guarantee the communication quality of wireless ad hoc networks.

[0008] This invention provides a method for enhancing communication in a transmission line ad hoc network, comprising: constructing a hybrid noise model; constructing a wireless ad hoc network channel model; and enhancing communication in the wireless ad hoc network by employing a distributed waveforming beamforming method based on the hybrid noise model and the wireless ad hoc network channel model.

[0009] According to the communication enhancement method for self-organizing networks of transmission lines provided by the present invention, the hybrid noise model is a mathematical model constructed based on background noise, impulse noise, and modulated Gaussian impulse noise. The background noise follows a zero-mean Gaussian distribution, the impulse noise follows a non-zero-mean Gaussian distribution, and the modulated Gaussian impulse noise follows a Poisson distribution. The expression of the hybrid noise model is as follows:

[0010] ;

[0011] ;

[0012] in, This represents the probability of background noise occurring. This represents the probability of impulse noise occurring. To modulate the probability of Gaussian impulse noise occurring; This represents the mean value of the impulse noise. The mean of the modulated Gaussian impulse noise; The variance of the background noise; The variance of the impulse noise; Noise intensity; Indicates noise intensity as The probability of.

[0013] According to the present invention, a method for enhancing communication in a transmission line ad hoc network is provided, wherein the wireless ad hoc network channel model is a mathematical model; the expression of the wireless ad hoc network channel model is:

[0014] ;

[0015] Where r is the actual distance between the transmitting node and the receiving node in the wireless ad hoc network; This is the reference distance between the transmitting and receiving nodes in a wireless ad hoc network. The received signal strength of the receiving node at a distance r from the transmitting node in a wireless ad hoc network; For a receiving node in a wireless ad hoc network, the distance to the transmitting node is... The received signal strength at that location; The slope of the path loss; As a reference frequency calibration standard; This is the path loss coefficient; This is the measured frequency; This is the diffraction loss component; This is the model correction factor.

[0016] According to the present invention, a communication enhancement method for a transmission line ad hoc network is provided. The ad hoc network includes multiple nodes. Based on a hybrid noise model and a channel model of the ad hoc network, a distributed beamforming method is used to enhance the communication of the ad hoc network. The method includes: constructing a beamforming optimization problem for the ad hoc network based on the hybrid noise model and the channel model of the ad hoc network; solving the beamforming optimization problem based on the communication enhancement model to obtain the transmit power and phase of each node; and enhancing the communication of the ad hoc network based on the transmit power and phase of each node. The communication enhancement model is a model constructed based on the MAPPO algorithm.

[0017] According to the communication enhancement method for ad hoc networks of transmission lines provided by the present invention, the expression for the beamforming optimization problem of wireless ad hoc networks is as follows:

[0018] ;

[0019] ;

[0020] Where max is the maximum value function; is the beamformer for node i in a wireless ad hoc network, where node i is the transmitting node; This represents the number of nodes in a wireless ad hoc network. For nodes in a wireless ad hoc network achievable rate, node For receiving nodes; Maximum transmit power for each cluster head node; It is the set of all nodes in a wireless ad hoc network.

[0021] According to the present invention, a communication enhancement method for a transmission line ad hoc network is provided. Based on a communication enhancement model, a beamforming optimization problem for the wireless ad hoc network is solved to obtain the transmit power and phase of each node. Based on the transmit power and phase of each node, communication enhancement is performed on the wireless ad hoc network. The method includes: acquiring the observation signal of each node in the wireless ad hoc network; inputting the observation signal of each node into the communication enhancement model to obtain the transmit power and phase of each node output by the communication enhancement model; the communication enhancement model aims to maximize the total channel capacity of the transmitting and receiving nodes when there is co-channel interference among multiple nodes, and solves the beamforming optimization problem for the wireless ad hoc network; and adjusting each node in the wireless ad hoc network based on the transmit power and phase of each node.

[0022] According to the present invention, a communication enhancement method for a transmission line ad hoc network is provided. The communication enhancement model includes a Critic network and multiple Actor networks. The Critic network is deployed at a central node, and each Actor network is deployed at a non-central node. The central node is a node in the wireless ad hoc network that can communicate and interconnect with all nodes.

[0023] The present invention also provides a communication enhancement device for a transmission line ad hoc network, comprising: a first construction module for constructing a hybrid noise model; a second construction module for constructing a wireless ad hoc network channel model; and a communication enhancement module for enhancing the communication of the wireless ad hoc network based on the hybrid noise model and the wireless ad hoc network channel model, using a distributed waveforming beamforming method.

[0024] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for enhancing communication in a transmission line ad hoc network.

[0025] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described transmission line ad hoc network communication enhancement methods.

[0026] The present invention provides a method, apparatus, device, and storage medium for enhancing communication in transmission line ad hoc networks. It performs noise modeling and wireless ad hoc network channel modeling for ad hoc networks in transmission line scenarios, constructing a hybrid noise model and a wireless ad hoc network channel model. Based on these models, a distributed waveforming beamforming method is used to enhance the communication of the wireless ad hoc network. During the enhancement process, the impact of complex noise in transmission line scenarios on communication and the characteristics of wireless ad hoc network channel transmission are fully considered. This ensures that the enhanced ad hoc network is more adaptable to real transmission line scenarios, optimizes its performance, improves communication quality, and enhances communication reliability. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is one of the flowcharts illustrating the method for enhancing communication in a self-organizing network of transmission lines provided by this invention.

[0029] Figure 2 This is a schematic diagram of the self-organizing network communication architecture in the scenario of dense power transmission lines provided by the present invention.

[0030] Figure 3 This is the second flowchart of the transmission line self-organizing network communication enhancement method provided by the present invention.

[0031] Figure 4 This is a schematic diagram of the structure of the power transmission line self-organizing network communication enhancement device provided by the present invention.

[0032] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0034] Please see Figure 1 , Figure 1This is one of the flowcharts illustrating the communication enhancement method for ad hoc networks of transmission lines provided by the present invention. In this embodiment, the communication enhancement method for ad hoc networks of transmission lines is applied to ad hoc networks in dense transmission line scenarios. The communication enhancement method for ad hoc networks of transmission lines includes steps S110 to S130, each step of which is detailed below:

[0035] S110: Construct a mixed noise model.

[0036] Please see Figure 2 , Figure 2 This is a schematic diagram of the self-organizing network communication architecture in the scenario of dense power transmission lines provided by the present invention.

[0037] like Figure 2 As shown in this embodiment, a wireless ad hoc network can be deployed in dense power transmission line scenarios to serve as a signal connection in areas without a public network, thereby improving communication coverage. During communication, the wireless ad hoc network is inevitably subject to electromagnetic interference from power transmission lines and co-channel interference from other devices (i.e., nodes) within the network.

[0038] Co-channel interference refers to the situation in which multiple nodes in a wireless ad hoc network share the same spectrum resources. In complex environments or when nodes are densely packed, signal transmission is affected by interference from other nodes. This interference can not only cause signal fading but also lead to data packet loss and delay, seriously affecting the reliability and efficiency of communication.

[0039] Electromagnetic interference (EMI) refers to the phenomenon where energy from electromagnetic waves couples into radio receiving equipment or systems, causing a decrease in the equipment's ability to receive signals. This leads to negative impacts such as deterioration of wireless communication signal quality and increased information errors. Power frequency electric and magnetic fields are widely present around power transmission lines. Especially with the promotion of ultra-high voltage AC technology, the voltage of charged bodies will increase significantly, directly leading to further complexity of the electromagnetic environment. EMI from transmission lines mainly comes from two sources: active interference and passive interference. Active interference is mainly caused by corona discharge on the conductor surface, spark discharge generated by high potential gradients in insulators, and spark discharge caused by poor contact. The resulting high-frequency electromagnetic pulse signals are strong enough to interfere with normal radio broadcasting communications. Passive interference is mainly caused by the reflection and shielding of useful signals by large metal structures such as transmission lines and towers.

[0040] Please see Figure 3 , Figure 3 This is the second flowchart of the transmission line self-organizing network communication enhancement method provided by the present invention.

[0041] like Figure 3As shown, to address the aforementioned co-channel interference and electromagnetic interference from power transmission lines, this embodiment proposes a communication enhancement method based on distributed beamforming: First, to accurately assess the propagation characteristics of wireless signals in a complex interference environment, it is necessary to model the environmental noise and wireless ad hoc network channel in a dense power transmission line scenario. For example, a hybrid noise model can be established to describe the intensity change of background noise in the time domain, and a wireless ad hoc network channel model can be constructed using a Lee model-based method to analyze the intensity fading of signals during propagation caused by path loss, shadowing fading, and electromagnetic interference. Then, combining the above modeling results, distributed beamforming technology is applied to dynamically adjust the transmit power and phase of each node in the wireless ad hoc network, and the beamforming problem is solved based on the MAPPO algorithm to optimize the overall network capacity.

[0042] Specifically, noise modeling is first performed on wireless ad hoc networks in dense power transmission line scenarios to obtain a hybrid noise model.

[0043] S120: Construct a wireless ad hoc network channel model.

[0044] Furthermore, wireless ad hoc network channel modeling is performed for wireless ad hoc networks in dense power transmission line scenarios to obtain a wireless ad hoc network channel model.

[0045] S130: Based on the hybrid noise model and the wireless ad hoc network channel model, a distributed waveforming beamforming method is used to enhance the communication of the wireless ad hoc network.

[0046] The transmission line ad hoc network communication enhancement method provided in this embodiment performs noise modeling and wireless ad hoc network channel modeling for ad hoc networks in transmission line scenarios. It constructs a hybrid noise model and a wireless ad hoc network channel model, and based on these models, employs a distributed waveforming beamforming method to enhance the wireless ad hoc network's communication. During the communication enhancement process, the impact of complex noise in the transmission line scenario on communication and the characteristics of wireless ad hoc network channel transmission are fully considered. This ensures that the enhanced ad hoc network is more adaptable to real transmission line scenarios, optimizes its performance in such scenarios, improves communication quality, and enhances communication reliability.

[0047] In some embodiments, the mixed noise model is a mathematical model constructed based on background noise, impulse noise, and modulated Gaussian impulse noise. The background noise follows a zero-mean Gaussian distribution, the impulse noise follows a non-zero-mean Gaussian distribution, and the modulated Gaussian impulse noise follows a Poisson distribution. The expression for the mixed noise model is:

[0048] ;

[0049] ;

[0050] in, This represents the probability of background noise occurring. This represents the probability of impulse noise occurring. To modulate the probability of Gaussian impulse noise occurring; This represents the mean value of the impulse noise. The mean of the modulated Gaussian impulse noise; The variance of the background noise; The variance of the impulse noise; Noise intensity; Indicates noise intensity as The probability of.

[0051] It should be noted that the wireless signal transmission environment in dense power transmission line scenarios is different from the transmission environment of other traditional communication channels. Due to the complex and varied topology of the power line network and the various loads connected to the power lines, which are randomly connected to or disconnected from the power grid, the noise in the power line channel is not simply Gaussian white noise, but is composed of a combination of many different noises, and the noise exhibits characteristics such as randomness, periodicity and continuity.

[0052] Based on this, this embodiment classifies high-amplitude, long-duration noise as modulated Gaussian impulse noise, low-amplitude, short-duration noise as impulse noise, and other noise as background white Gaussian noise (i.e., background noise). It then proposes a hybrid noise model based on background noise, impulse noise, and modulated Gaussian impulse noise. The hybrid noise model considers background noise that follows a zero-mean Gaussian distribution, impulse noise with a non-zero mean, and modulated Gaussian impulse noise that follows a Poisson distribution. The three types of noise are constructed into three systems, and the state transition matrix of the Markov chain is calculated according to their occurrence probability.

[0053] The expression for the mixed noise model is as follows:

[0054] ;

[0055] ;

[0056] in, This represents the probability of background noise occurring. This represents the probability of impulse noise occurring. To modulate the probability of Gaussian impulse noise occurring; This represents the mean value of the impulse noise. The mean of the modulated Gaussian impulse noise; The variance of the background noise; The variance of the impulse noise; Noise intensity; Indicates noise intensity as The probability of.

[0057] The state transition matrices for the three states are as follows:

[0058]

[0059] The matching pursuit algorithm is a greedy algorithm in sparse decomposition. It selects the atom that best matches the original signal from the atom library in each iteration, thus forming a gradual approximation process and finally completing the sparse representation of the signal.

[0060] Optionally, during the noise modeling process, the matched pursuit algorithm is used to statistically analyze the pulse width and pulse amplitude of the modulated Gaussian pulses generated by the sampled noise samples to determine the parameters of the mixed noise model.

[0061] In some embodiments, the wireless ad hoc network channel model is a mathematical model; the expression for the wireless ad hoc network channel model is:

[0062] ;

[0063] Where r is the actual distance between the transmitting node and the receiving node in the wireless ad hoc network; This is the reference distance between the transmitting and receiving nodes in a wireless ad hoc network. The received signal strength of the receiving node at a distance r from the transmitting node in a wireless ad hoc network; For a receiving node in a wireless ad hoc network, the distance to the transmitting node is... The received signal strength at that location; The slope of the path loss; As a reference frequency calibration standard; This is the path loss coefficient; This is the measured frequency; This is the diffraction loss component; This is the model correction factor.

[0064] Choosing a beamforming scheme first requires understanding the propagation characteristics of wireless ad hoc network signals, thus necessitating the modeling of wireless channels in dense power transmission line scenarios. Since signal transmission in wireless ad hoc networks is affected by various factors such as scattering and diffraction caused by terrain and power transmission facilities, as well as electromagnetic interference, traditional wireless communication channel models struggle to guarantee stability and reliability in complex environments. Therefore, this embodiment constructs a wireless ad hoc network channel model based on the Lee model, taking into account the effects of path loss, shadowing fading, and electromagnetic loss.

[0065] ;

[0066] Where r is the actual distance between the transmitting node and the receiving node in the wireless ad hoc network; This is the reference distance between the transmitting and receiving nodes in a wireless ad hoc network. The received signal strength of the receiving node at a distance r from the transmitting node in a wireless ad hoc network; For a receiving node in a wireless ad hoc network, the distance to the transmitting node is... The received signal strength at that location; The slope of the path loss; As a reference frequency calibration standard; This is the path loss coefficient; This is the measured frequency; This represents the diffraction loss component; to enable the model to adapt to complex and ever-changing real-world scenarios, a model correction factor is introduced. Fine-tuning was performed to improve the accuracy of model predictions.

[0067] In scenarios with dense power transmission lines, wireless signal transmission environments are often obstructed by various obstacles such as terrain features and transmission towers. Therefore, the radio wave propagation process can be modeled as non-line-of-sight propagation affected by multiple sharp peak obstacles. The calculation method is as follows:

[0068] ;

[0069] ;

[0070]

[0071] ;

[0072] in, This refers to the propagation clearance between the link and the obstacle; This is the distance between the obstacle and the transmitting node (i.e., the transmitting station); This is the distance between the obstacle and the receiving node (i.e., the receiving station); is the diffraction factor; n is the total number of obstacles between the transmitting node and the receiving node; The k-th obstacle between the sending node and the receiving node; The diffraction loss is the k-th obstacle between the transmitting and receiving nodes. This represents the total diffraction loss due to obstacles between the transmitting and receiving nodes. This represents the total effective loss during diffraction.

[0073] In some embodiments, the wireless ad hoc network includes multiple nodes; based on a hybrid noise model and a wireless ad hoc network channel model, a distributed beamforming method is used to enhance the communication of the wireless ad hoc network, including: constructing a wireless ad hoc network beamforming optimization problem based on the hybrid noise model and the wireless ad hoc network channel model; solving the wireless ad hoc network beamforming optimization problem based on the communication enhancement model to obtain the transmit power and phase of each node, and enhancing the communication of the wireless ad hoc network based on the transmit power and phase of each node; wherein, the communication enhancement model is a model constructed based on the MAPPO algorithm.

[0074] First, based on the hybrid noise model and the wireless ad hoc network channel model, a beamforming optimization problem for wireless ad hoc networks is constructed.

[0075] Specifically, this embodiment divides the communication process of the wireless ad hoc network into multiple time slots, assuming that the channel state and other conditions between the two communicating parties remain unchanged in each time slot. Let's assume that in the t-th time slot, node i transmits a signal to node k. Meanwhile, node k is subjected to interference from other nodes on the same frequency. Therefore, the signal received by node k is:

[0076] ;

[0077] in, i represents the transmitting node, i.e., the desired signal source; j represents the non-transmitting node, i.e., the non-desired signal source. The beamformer for node i includes the transmitted power of node i modulated by the beamformer. and the phase of transmission ; It is by Obtained through Hermitian transformation This is the direct downlink channel between node i and node k in the t-th time slot; It is by Obtained through Hermitian transformation This is the interference channel between node j and node k; For environmental noise, It can be calculated using a mixed noise model.

[0078] In the wireless ad hoc network communication scenario of this embodiment, not all nodes will experience strong co-channel interference. When the co-channel interference link channel conditions are poor, the received signal strength (RSS) is weak when the interfering signal reaches the interfered receiving node; this type of interference can be disregarded. Two dynamic control thresholds are determined. and The number of interfering nodes and the number of interfered nodes are limited respectively. For receiving node k and its sending node i, the number of all interfering nodes is limited. and the affected nodes They can be defined as follows:

[0079] ;

[0080] ;

[0081] Then, in the t-th time slot, the signal-to-noise ratio and achievable rate of receiving node k are respectively:

[0082] ;

[0083] ;

[0084] in, The transmit power of node i after beamforming ; The transmit power of node j after modulation by the beamformer; The environmental noise power can be obtained from the above environmental noise modeling. .

[0085] In the beamforming problem of wireless ad hoc networks, the objective can be set as maximizing the total channel capacity of the transmitting and receiving nodes when there is co-channel interference among multiple nodes. Therefore, in time slot t, the expression for the optimization problem of beamforming in wireless ad hoc networks is:

[0086] ;

[0087] ;

[0088] Where max is the maximum value function; is the beamformer for node i in a wireless ad hoc network, where node i is the transmitting node; This represents the number of nodes in a wireless ad hoc network. For nodes in a wireless ad hoc network achievable rate, node For receiving nodes; Maximum transmit power for each cluster head node; It is the set of all nodes in a wireless ad hoc network.

[0089] Furthermore, based on the communication enhancement model, the beamforming optimization problem of the wireless ad hoc network is solved to obtain the transmit power and phase of each node, and the communication enhancement of the wireless ad hoc network is performed based on the transmit power and phase of each node.

[0090] In some embodiments, the expression for the beamforming optimization problem of wireless ad hoc networks is:

[0091] ;

[0092] ;

[0093] Where max is the maximum value function; is the beamformer for node i in a wireless ad hoc network, where node i is the transmitting node; This represents the number of nodes in a wireless ad hoc network. For nodes in a wireless ad hoc network achievable rate, node For receiving nodes; Maximum transmit power for each cluster head node; It is the set of all nodes in a wireless ad hoc network.

[0094] In some embodiments, a beamforming optimization problem for a wireless ad hoc network is solved based on a communication enhancement model to obtain the transmit power and phase of each node. Based on the transmit power and phase of each node, communication enhancement is performed on the wireless ad hoc network, including: acquiring the observation signal of each node in the wireless ad hoc network; inputting the observation signal of each node into the communication enhancement model to obtain the transmit power and phase of each node output by the communication enhancement model; the communication enhancement model aims to maximize the total channel capacity of the transmitting and receiving nodes when there is co-channel interference among multiple nodes, and solves the beamforming optimization problem for the wireless ad hoc network; and adjusting each node in the wireless ad hoc network based on the transmit power and phase of each node.

[0095] To address the aforementioned beamforming optimization problem in wireless ad hoc networks, this embodiment employs the MAPPO algorithm. The communication enhancement model, built upon the MAPPO algorithm, is an Actor-Critic structure model. In wireless ad hoc networks operating in dense power transmission line scenarios, the communication enhancement model includes a Critic network and multiple Actor networks. It can be deployed using a centralized training and distributed execution approach: a central node is defined in the wireless ad hoc network, capable of interconnecting with all nodes, and the Critic network is deployed at the central node to acquire information from all nodes; the remaining nodes are defined as non-central nodes (i.e., ordinary nodes), and each non-central node deploys an Actor network. Each non-central node can be considered an agent. After centralized training, the training results can be fed back to each node. When observation information is limited, the remaining nodes can utilize their local distributed MAPPO networks for distributed execution, making decisions regarding beamforming parameters.

[0096] definition This represents the joint action process in the above scenario, where i represents any intelligent agent, i.e. Each agent has its own local PPO network, and the corresponding policy function for the network is... .

[0097] This represents the set of reward functions for all agents. In this embodiment, the network aims to maximize the objective function while minimizing its own interference with other agents. Therefore, the reward function of each agent is... Designed as follows:

[0098] ;

[0099] in, The gain term represents agent i; It is the penalty term for agent i, which is the penalty imposed on agent i by other agents. The sum of achievable rates that generate co-channel interference is expressed as:

[0100] ;

[0101] in, Let j be the desired signal source for node j; Let j be the undesired signal source for node j.

[0102] The state space represents the constrained observation state information of the i-th node, which includes three parts: local information, information of nodes that cause interference with it at the same frequency, and information of nodes affected by its interference at the same frequency.

[0103] ;

[0104] Among them, the local information at time slot t Including the channel between node i and node k in time slot t-1 and the expected signal received by node k. .

[0105] This includes the set of nodes that interfere with node k. and noise information of node k .

[0106] Including the set of nodes affected by it In time slot t-1, nodes i and m ( Interference channels between and the loss caused by interference .

[0107] Represents the set of all agent action spaces. Agent i must allocate power to itself within this continuous action space. It also needs to output its own phase. ,Right now The PPO algorithm defines a parameterized Gaussian distribution to represent the probability of choosing a certain action. and The results were obtained by amplifying the corresponding sampled values ​​using the corresponding unit Gaussian distribution by the appropriate factor:

[0108] ;

[0109] ;

[0110] in, and All values ​​are sampled from the Gaussian distribution function obtained by sampling the values ​​obtained from the Tanh activation function.

[0111] Represents the state transition function; Set as the discount factor, its role is to appropriately trade off the predicted reward value and the current reward value. The objective of each agent i is to optimize its network parameters and determine its optimal policy function. To achieve the best long-term returns for the entire network system:

[0112] ;

[0113] In the formula, ,Depend on and A joint decision.

[0114] The action value function corresponding to the i-th agent is:

[0115] ;

[0116] The state-value function of agent i can be described as:

[0117] ;

[0118] Define the agent's policy function as follows: ,in ; These represent parameters related to the policy function of agent i. Furthermore, in the distributed PPO network of this embodiment, the agent cannot obtain the global state. Let be the constrained observations of agent i, then the policy gradient of agent i is:

[0119] ;

[0120] The optimization objective of agent i is:

[0121] ;

[0122] The significance of the Clip function lies in limiting the variation ratio of this network strategy to a finite range; Defined as a hyperparameter, it is used to limit the rate of change of network policy. Network dominance function. The estimation method is the Generalized Advantage Estimation (GAE), which is expressed as follows:

[0123] ;

[0124] ;

[0125] in, This indicates the advantage gained from performing a specific action at step t, and introduces... Balance the weight of the advantages of each step.

[0126] Meanwhile, the objective function of the Critic network The meaning is the square of the difference between the estimated state value and the current state value:

[0127] ;

[0128] in, This is the currently estimated state value; This is the current target state value calculated based on the reward value.

[0129] In summary, the training process for the model within each time slot is as follows:

[0130] (1) The transmitting node i selects a beamforming scheme and transmits a signal based on its state and the current strategy function.

[0131] (2) Receiver node k receives the signal and feeds back the desired signal strength to sender node i. Noise intensity and channel state information .

[0132] (3) The receiving node k feeds back the interference node to the central node. Loss and channel state information .

[0133] (4) The sending node i obtains information about the interfered node from the central node. The resulting loss, channel state information And calculate the penalty item. .

[0134] (5) Send node i updates the local policy function, and the central node updates the evaluation function at the end of each training batch.

[0135] Specifically, after training the communication enhancement model, the beamforming optimization problem of the wireless ad hoc network can be solved based on the communication enhancement model: First, the observation signal of each node in the wireless ad hoc network is obtained, and the observation signal of each node is input into the communication enhancement model. The communication enhancement model can solve the beamforming optimization problem of the wireless ad hoc network, predict and output the solution result that satisfies the solution objective of the beamforming optimization problem of the wireless ad hoc network, namely the transmit power of each node and the phase of each node.

[0136] Furthermore, each node in the wireless ad hoc network is adjusted based on its transmit power and phase.

[0137] The transmission line ad hoc network communication enhancement method provided in this embodiment adopts an optimized scheme based on the MAPPO algorithm, which can achieve efficient scheduling of network resources and interference management, thereby ensuring efficient communication among nodes of the wireless ad hoc network in complex environments. This method not only improves the anti-interference capability of the power information system in harsh environments and ensures efficient communication of the wireless ad hoc network in complex environments, but also enhances the overall capacity and stability of the network, providing important technical support for the communication security of future smart grids.

[0138] In some embodiments, the communication enhancement model includes a Critic network and multiple Actor networks; wherein the Critic network is deployed at a central node, and each Actor network is deployed at a non-central node, and the central node is a node in the wireless ad hoc network that can communicate and interconnect with all nodes.

[0139] This embodiment proposes a beamforming-based wireless ad hoc network communication enhancement method in dense power transmission line environments. Based on noise modeling and wireless ad hoc network channel modeling, the MAPPO algorithm is used to solve the distributed beamforming problem, dynamically adjusting the transmit power and phase of each communication node in the wireless ad hoc network to maximize network capacity. This effectively solves the electromagnetic interference and co-channel interference problems of wireless ad hoc networks in dense power transmission line environments, improves the communication quality of wireless ad hoc networks in dense power transmission line environments, and enhances communication reliability.

[0140] This invention also provides a communication enhancement device for power transmission line self-organizing networks. Please refer to [link / reference]. Figure 4 , Figure 4This is a schematic diagram of the structure of the transmission line self-organizing network communication enhancement device provided by the present invention. In this embodiment, the transmission line self-organizing network communication enhancement device includes a first building module 410, a second building module 420, and a communication enhancement module 430.

[0141] The first building module 410 is used to build a mixed noise model.

[0142] The second building module 420 is used to build a wireless ad hoc network channel model.

[0143] The communication enhancement module 430 is used to enhance the communication of wireless ad hoc networks based on a hybrid noise model and a wireless ad hoc network channel model, using a distributed waveforming beamforming method.

[0144] In some embodiments, the mixed noise model is a mathematical model constructed based on background noise, impulse noise, and modulated Gaussian impulse noise. The background noise follows a zero-mean Gaussian distribution, the impulse noise follows a non-zero-mean Gaussian distribution, and the modulated Gaussian impulse noise follows a Poisson distribution. The expression for the mixed noise model is:

[0145] ;

[0146] ;

[0147] in, This represents the probability of background noise occurring. This represents the probability of impulse noise occurring. To modulate the probability of Gaussian impulse noise occurring; This represents the mean value of the impulse noise. The mean of the modulated Gaussian impulse noise; The variance of the background noise; The variance of the impulse noise; Noise intensity; Indicates noise intensity as The probability of.

[0148] In some embodiments, the wireless ad hoc network channel model is a mathematical model; the expression for the wireless ad hoc network channel model is:

[0149] ;

[0150] Where r is the actual distance between the transmitting node and the receiving node in the wireless ad hoc network; This is the reference distance between the transmitting and receiving nodes in a wireless ad hoc network. The received signal strength of the receiving node at a distance r from the transmitting node in a wireless ad hoc network; For a receiving node in a wireless ad hoc network, the distance to the transmitting node is... The received signal strength at that location; The slope of the path loss; As a reference frequency calibration standard; This is the path loss coefficient; This is the measured frequency; This is the diffraction loss component; This is the model correction factor.

[0151] In some embodiments, a wireless ad hoc network includes multiple nodes.

[0152] The communication enhancement module 430 is used to construct a wireless ad hoc network beamforming optimization problem based on a hybrid noise model and a wireless ad hoc network channel model; based on the communication enhancement model, it solves the wireless ad hoc network beamforming optimization problem to obtain the transmit power and phase of each node, and enhances the communication of the wireless ad hoc network based on the transmit power and phase of each node; wherein, the communication enhancement model is a model constructed based on the MAPPO algorithm.

[0153] In some embodiments, the expression for the beamforming optimization problem of wireless ad hoc networks is:

[0154] ;

[0155] ;

[0156] Where max is the maximum value function; is the beamformer for node i in a wireless ad hoc network, where node i is the transmitting node; This represents the number of nodes in a wireless ad hoc network. For nodes in a wireless ad hoc network achievable rate, node For receiving nodes; Maximum transmit power for each cluster head node; It is the set of all nodes in a wireless ad hoc network.

[0157] In some embodiments, the communication enhancement module 430 is used to acquire the observation signal of each node in the wireless ad hoc network; input the observation signal of each node into the communication enhancement model to obtain the transmit power and phase of each node output by the communication enhancement model; the communication enhancement model aims to maximize the total channel capacity of the transmitting and receiving nodes when there is co-channel interference among multiple nodes, and solves the beamforming optimization problem of the wireless ad hoc network; and adjusts each node in the wireless ad hoc network based on the transmit power and phase of each node.

[0158] In some embodiments, the communication enhancement model includes a Critic network and multiple Actor networks; wherein the Critic network is deployed at a central node, and each Actor network is deployed at a non-central node, and the central node is a node in the wireless ad hoc network that can communicate and interconnect with all nodes.

[0159] The present invention also provides an electronic device. Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 5 As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions from the memory 530 to execute the transmission line ad hoc network communication enhancement method.

[0160] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0161] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the transmission line ad hoc network communication enhancement methods provided by the above methods.

[0162] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0163] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for enhancing communication in a transmission line ad hoc network, characterized in that, include: Construct a mixed noise model; Construct a wireless ad hoc network channel model; Based on the hybrid noise model and the wireless ad hoc network channel model, a distributed beamforming method is used to enhance the communication of the wireless ad hoc network. The hybrid noise model is a mathematical model built based on background noise, impulse noise and modulated Gaussian impulse noise. The background noise follows a zero-mean Gaussian distribution, the impulse noise follows a Gaussian distribution with a non-zero mean, and the modulated Gaussian impulse noise follows a Poisson distribution. The expression for the mixed noise model is: ； ； in, The probability of the background noise occurring; The probability of the occurrence of the impulse noise; The probability of occurrence of the modulated Gaussian impulse noise; The mean value of the impulse noise; The mean value of the modulated Gaussian impulse noise; The variance of the background noise; The variance of the impulse noise; Noise intensity; Indicates noise intensity as The probability of; The wireless ad hoc network channel model is a mathematical model; The expression for the wireless ad hoc network channel model is as follows: ； Where r is the actual distance between the transmitting node and the receiving node in the wireless ad hoc network; This is the reference distance between the transmitting node and the receiving node in the wireless ad hoc network. The received signal strength of the receiving node at a distance r from the transmitting node in the wireless ad hoc network; For the receiving node in the wireless ad hoc network, the distance to the transmitting node is... The received signal strength at that location; The slope of the path loss; As a reference frequency calibration standard; This is the path loss coefficient; This is the measured frequency; This is the diffraction loss component; This is the model correction factor; The wireless ad hoc network includes multiple nodes; The method of enhancing communication in the wireless ad hoc network using distributed beamforming, based on the hybrid noise model and the wireless ad hoc network channel model, includes: Based on the hybrid noise model and the wireless ad hoc network channel model, a wireless ad hoc network beamforming optimization problem is constructed. Based on the communication enhancement model, the beamforming optimization problem of the wireless ad hoc network is solved to obtain the transmit power and phase of each node. Based on the transmit power and phase of each node, the communication of the wireless ad hoc network is enhanced. The communication enhancement model is a model built based on the MAPPO algorithm. The expression for the beamforming optimization problem of the wireless ad hoc network is: ； ； Where max is the maximum value function; This is the beamformer for node i in the wireless ad hoc network, where node i is the transmitting node. The number of nodes in the wireless ad hoc network; For the nodes in the wireless ad hoc network achievable rate, node For receiving nodes; Maximum transmit power for each cluster head node; It is the set of all the nodes in the wireless ad hoc network.

2. The method for enhancing communication in a transmission line ad hoc network according to claim 1, characterized in that, The method involves solving the beamforming optimization problem of the wireless ad hoc network based on a communication enhancement model to obtain the transmit power and phase of each node. Based on the transmit power and phase of each node, communication enhancement is performed on the wireless ad hoc network, including: Acquire the observation signal of each node in the wireless ad hoc network; The observation signal of each node is input into the communication enhancement model to obtain the transmit power and phase of each node output by the communication enhancement model; the communication enhancement model aims to maximize the total channel capacity of the transmitting and receiving nodes when there is co-channel interference among multiple nodes, and solves the beamforming optimization problem of the wireless ad hoc network. The wireless ad hoc network is adjusted based on the transmit power and phase of each node.

3. The method for enhancing communication in a transmission line ad hoc network according to claim 1, characterized in that, The communication enhancement model includes a Critic network and multiple Actor networks; The Critic network is deployed at a central node, and each Actor network is deployed at a non-central node. The central node is a node in the wireless ad hoc network that can communicate and interconnect with all the nodes.

4. A communication enhancement device for self-organizing networks of transmission lines, characterized in that, include: The first building block is used to construct the mixed noise model; The second building module is used to build a wireless ad hoc network channel model; The communication enhancement module is used to enhance the communication of the wireless ad hoc network based on the hybrid noise model and the wireless ad hoc network channel model, using a distributed beamforming method. The hybrid noise model is a mathematical model built based on background noise, impulse noise and modulated Gaussian impulse noise. The background noise follows a zero-mean Gaussian distribution, the impulse noise follows a Gaussian distribution with a non-zero mean, and the modulated Gaussian impulse noise follows a Poisson distribution. The expression for the mixed noise model is: ； ； in, The probability of the background noise occurring; The probability of the occurrence of the impulse noise; The probability of occurrence of the modulated Gaussian impulse noise; The mean value of the impulse noise; The mean value of the modulated Gaussian impulse noise; The variance of the background noise; The variance of the impulse noise; Noise intensity; Indicates noise intensity as The probability of; The wireless ad hoc network channel model is a mathematical model; The expression for the wireless ad hoc network channel model is as follows: ； Where r is the actual distance between the transmitting node and the receiving node in the wireless ad hoc network; This is the reference distance between the transmitting node and the receiving node in the wireless ad hoc network. The received signal strength of the receiving node at a distance r from the transmitting node in the wireless ad hoc network; For the receiving node in the wireless ad hoc network, the distance to the transmitting node is... The received signal strength at that location; The slope of the path loss; As a reference frequency calibration standard; This is the path loss coefficient; This is the measured frequency; This is the diffraction loss component; This is the model correction factor; The wireless ad hoc network includes multiple nodes; The communication enhancement module is used to construct a wireless ad hoc network beamforming optimization problem based on the hybrid noise model and the wireless ad hoc network channel model; solve the wireless ad hoc network beamforming optimization problem based on the communication enhancement model to obtain the transmit power and phase of each node; and enhance the communication of the wireless ad hoc network based on the transmit power and phase of each node; wherein, the communication enhancement model is a model constructed based on the MAPPO algorithm. The expression for the beamforming optimization problem of the wireless ad hoc network is: ； ； Where max is the maximum value function; This is the beamformer for node i in the wireless ad hoc network, where node i is the transmitting node. The number of nodes in the wireless ad hoc network; For the nodes in the wireless ad hoc network achievable rate, node For receiving nodes; Maximum transmit power for each cluster head node; It is the set of all the nodes in the wireless ad hoc network.

5. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the transmission line self-organizing network communication enhancement method as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the transmission line self-organizing network communication enhancement method as described in any one of claims 1 to 3.

Images