Method and system for predicting network state of ad hoc network

Abstract

The application provides a kind of network state prediction method and system of self-organizing network, it is related to wireless communication technical field, the method comprises: obtaining the key parameter of self-organizing network network;According to the key parameter, the first key feature that influences the network condition of self-organizing network network is identified, and the first network state report of self-organizing network network is generated based on the first key feature;First network state report includes at least one of the following: the current state of self-organizing network network, the possible problem of self-organizing network network and the possible influence of self-organizing network network;Using target prediction network, according to the first key feature and the first network state report, the future network condition of self-organizing network network is predicted;The future network condition of self-organizing network network includes at least one of the following: link bandwidth, communication delay and data packet loss rate.The application realizes effectively to the network state of self-organizing network is predicted.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a method and system for predicting the network status of an ad hoc network. Background Art

[0002] Ad Hoc networks, also known as self-adaptive networks, are a type of network that forms independently through terminal devices, rather than relying on pre-deployed fixed network infrastructure. Ad Hoc networks are self-configuring, self-organizing, and self-managing, enabling rapid network establishment and dismantling. This makes them highly advantageous for flexibly handling specialized scenarios, such as impromptu meetings, emergency rescue operations, and battlefield communications.

[0003] However, the dynamic and self-organizing nature of ad hoc networks also presents a series of challenges, particularly in terms of network management and performance optimization. Because nodes may move, join, or leave the network, and because of various environmental factors (such as signal interference, physical obstacles, and background noise), the network topology can change rapidly and unpredictably. This dynamic change can significantly impact the network's communication performance, such as changes in link bandwidth, increased communication latency, and increased packet loss.

[0004] Traditional network management strategies, such as routing, flow control, and quality of service assurance, primarily make decisions based on current network status information. However, due to the highly dynamic and uncertain nature of ad hoc networks, these decisions based on current status often fail to achieve optimal network performance. For example, when a key node in the network moves or leaves the network, the previously selected route may become immediately invalid, resulting in communication interruption or performance degradation. In such cases, if such changes can be predicted, decisions can be made in advance, such as selecting a new route, thereby avoiding or minimizing communication interruption and performance degradation.

[0005] Therefore, how to effectively predict the network status of ad hoc networks has become a technical problem that urgently needs to be solved in the industry. Summary of the Invention

[0006] In view of the deficiencies in the prior art, the present invention provides a method and system for predicting the network status of an ad hoc network, which effectively predicts the network status of the ad hoc network.

[0007] In a first aspect, the present invention provides a method for predicting the network status of an ad hoc network, the method comprising the following steps:

[0008] Obtain key parameters of the ad hoc network; the key parameters include at least one of the following: number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0009] According to the key parameters, a first key feature that affects the network status of the ad hoc network is identified, and a first network status report of the ad hoc network is generated based on the first key feature; the first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible impacts of the ad hoc network;

[0010] Using the target prediction network, based on the first key feature and the first network status report, the future network status of the self-organizing network is predicted; the future network status of the self-organizing network includes at least one of the following: link bandwidth, communication delay and data packet loss rate.

[0011] According to a method for predicting a network status of an ad hoc network provided by the present invention, identifying a first key feature that affects a network status of the ad hoc network based on the key parameter, and generating a first network status report of the ad hoc network based on the first key feature, comprising:

[0012] Removing duplicate data from the key parameters to obtain first data;

[0013] Identifying missing data in the first data and correcting the missing data to obtain second data;

[0014] Correcting erroneous data in the second data to obtain cleaned data;

[0015] Normalizing the cleaned data to obtain third data;

[0016] Extracting the first key feature based on the third data;

[0017] Based on the first key feature, a first network status report of the ad hoc network is generated.

[0018] According to a network status prediction method for an ad hoc network provided by the present invention, the target prediction network is obtained by training an initial prediction network using a sample data set and sample labels, the sample data set includes multiple samples, any of the samples includes a second key feature and a second network status report of the ad hoc network, and the sample labels include the future network status corresponding to each of the samples; the target prediction network is a deep learning model.

[0019] According to a method for predicting network status of an ad hoc network provided by the present invention, the method further includes:

[0020] Determining a decision suggestion corresponding to the ad hoc network based on the future network status; the decision suggestion includes at least one of the following: route selection, data transmission rate adjustment, and service priority determination;

[0021] The determining, based on the future network status, a decision suggestion corresponding to the ad hoc network includes:

[0022] Visually displaying the future network status to obtain a visualization result;

[0023] The decision suggestion is determined based on the visualization result.

[0024] According to a method for predicting network status of an ad hoc network provided by the present invention, the method further includes:

[0025] Comparing the future network status of the ad hoc network with the current network status of the ad hoc network to obtain a comparison result;

[0026] Based on the comparison result, the model parameters of the target prediction network are optimized.

[0027] In a second aspect, the present invention further provides a network status prediction system for an ad hoc network, the network status prediction system for an ad hoc network comprising a data collection module, a data analysis module, a prediction module, a decision support module and a feedback module; wherein,

[0028] A data collection module is used to obtain key parameters of the ad hoc network, wherein the key parameters include at least one of the following: the number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0029] a data analysis module, configured to identify, based on the key parameters, a first key feature that affects the network status of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key feature;

[0030] A prediction module, configured to use a target prediction network to predict a future network status of the ad hoc network according to the first key feature and the first network status report;

[0031] A decision-making assistance module, configured to determine a decision suggestion corresponding to the ad hoc network based on the future network status;

[0032] The feedback module is used to compare the future network status of the self-organizing network with the current network status of the self-organizing network to obtain a comparison result; based on the comparison result, optimize the model parameters of the target prediction network.

[0033] In a third aspect, the present invention further provides a network status prediction device for an ad hoc network, the device comprising the following modules:

[0034] An acquisition module is used to obtain key parameters of the ad hoc network, wherein the key parameters include at least one of the following: the number of access points, environmental impact, environmental sudden interference, channel conditions, background noise conditions, inter-node link conditions, and communication distance;

[0035] a prediction module, configured to identify, based on the key parameters, a first key feature that affects the network status of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key feature;

[0036] The target prediction network is used to predict the future network status of the ad hoc network according to the first key feature and the first network status report.

[0037] In a fourth aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for predicting the network status of a self-organizing network as described in any one of the above is implemented.

[0038] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the network status prediction method of an ad hoc network as described in any one of the above.

[0039] In a sixth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described methods for predicting the network status of an ad hoc network.

[0040] The present invention provides a method and system for predicting the network status of an ad hoc network. First, key parameters of the ad hoc network are obtained. The key parameters include at least one of the following: the number of access points, environmental impact, sudden environmental interference, channel conditions, background noise conditions, inter-node link conditions, and communication distance. Then, based on the key parameters, a first key feature that affects the network status of the ad hoc network is identified, and a first network status report of the ad hoc network is generated based on the first key feature. The first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible impacts of the ad hoc network. Then, using a target prediction network, the future network status of the ad hoc network is predicted based on the first key feature and the first network status report. The future network status of the ad hoc network includes at least one of the following: link bandwidth, communication delay, and data packet loss rate.

[0041] The present invention collects various key parameters of an ad hoc network (such as the number of access points, environmental impact, sudden environmental interference, channel conditions, noise floor, inter-node link conditions, and communication distance) in real time and uses advanced data analysis and target prediction networks to predict the future network status of the ad hoc network. Through real-time data collection, analysis, and prediction, it can more accurately predict the communication performance of the ad hoc network, thereby improving network efficiency and communication quality. The predicted future network status can provide network managers or commanders with real-time and accurate network performance forecasts to assist them in making effective network management decisions. The present invention effectively predicts the network status of an ad hoc network. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is one of the flow charts of the network status prediction method for an ad hoc network provided by the present invention.

[0044] Figure 2 It is a structural diagram of the network status prediction system of the ad hoc network provided by the present invention.

[0045] Figure 3 This is the second flow chart of the network status prediction method for an ad hoc network provided by the present invention.

[0046] Figure 4 It is a schematic diagram of the effect of the network status report provided by the present invention.

[0047] Figure 5 This is the third flow chart of the network status prediction method for an ad hoc network provided by the present invention.

[0048] Figure 6 It is a structural diagram of the network status prediction device of the ad hoc network provided by the present invention.

[0049] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0051] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects. For example, the first node can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0052] The following combination Figures 1-6 The present invention describes a method and system for predicting the network status of an ad hoc network.

[0053] Figure 1 This is one of the flow charts of the network status prediction method for an ad hoc network provided by the present invention, such as Figure 1 As shown, the method includes the following:

[0054] Step 101: Acquire key parameters of the ad hoc network; the key parameters include at least one of the following: number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0055] Specifically, it should be noted that the execution subject of the present invention is a network status prediction system for an ad hoc network, which is used to predict the future network status of the ad hoc network.

[0056] Figure 2 This is a schematic diagram of the structure of the network status prediction system for the self-organizing network provided by the present invention. Figure 2 As shown, the network status prediction system 200 of the ad hoc network mainly includes five modules: a data collection module 210, a data analysis module 220, a prediction module 230, a decision support module 240 and a feedback module.

[0057] In this embodiment, key parameters of the ad hoc network are collected in real time by the data collection module 210. Specifically, the data collection module 210 connects to the communication interface of each network node and acquires and records the status information of the network node in real time, including the number of access points, environmental impact, sudden environmental interference, channel conditions, noise floor, inter-node link status, and communication distance. The data collection module can store this data in a database for use by subsequent modules.

[0058] More specifically, Figure 3 This is the second flow chart of the network status prediction method for an ad hoc network provided by the present invention, illustrating the working principle and submodule composition of the data collection module. The data collection module includes: an access point number collection submodule, an environmental impact collection submodule, a burst interference collection submodule, a burst interference collection submodule, a channel status collection submodule, a noise floor collection submodule, a link status collection submodule, and a communication distance collection submodule. The submodules are described as follows:

[0059] a) Access Point Count Collection Submodule: This submodule monitors and records the number of access points in the network in real time. The number of access points directly affects the network coverage and service quality, so it is an important parameter.

[0060] b) Environmental impact collection submodule: This submodule is responsible for collecting and recording the impact of environmental factors on the network, including weather conditions, building obstructions, etc. These factors may affect the performance of the network.

[0061] c) Burst Interference Collection Submodule: This submodule is used to detect and record sudden interference in the network, such as sudden electromagnetic interference, hardware failure, etc. These sudden events may seriously affect the stability of the network.

[0062] d) Channel status collection submodule: This submodule is responsible for monitoring and recording the channel status in the network, including channel capacity, utilization, signal-to-noise ratio, etc.

[0063] e) Noise background collection submodule: This submodule is responsible for collecting and recording the network noise background to evaluate the network's signal-to-noise ratio.

[0064] f) Link status collection submodule: This submodule monitors and records the link status between each node in the network, including the quality, stability and bandwidth of the link.

[0065] g) Communication distance collection submodule: This submodule is responsible for collecting and recording the communication distance of each node in the network, which is very important for evaluating the coverage and service quality of the network.

[0066] Each submodule can communicate with network nodes through the network's hardware and software interfaces to acquire and record these parameters in real time. All collected data is stored in a unified database for subsequent module processing and analysis.

[0067] By acquiring key parameters in real time, the key parameters can be stored to facilitate subsequent data calls.

[0068] Step 102: Identify a first key feature that affects the network status of the ad hoc network based on the key parameters, and generate a first network status report of the ad hoc network based on the first key feature; the first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible impacts of the ad hoc network;

[0069] Specifically, after collecting the key parameters of the ad hoc network, the raw data may be preliminarily analyzed and processed, using the data analysis module 220 to process and analyze the data collected by the data collection module.

[0070] It can be further divided into several steps, including but not limited to:

[0071] Data cleaning, data normalization, feature extraction, data analysis, and report generation. The output of this module is a network status report and a set of key features. These outputs will be passed to the prediction module 230 for prediction of future network status.

[0072] For example, based on characteristics such as the number of access points, environmental impact, sudden environmental interference, channel conditions, background noise conditions, inter-node link conditions, and communication distance, it is necessary to determine the number of access users, calculate (or obtain) the signal-to-noise ratio of each link, and calculate the remaining bandwidth.

[0073] The Shannon equation can be used to determine channel capacity when the signal-to-noise ratio is known. In the presence of interference, the equation can be optimized to determine available bandwidth and remaining bandwidth after knowing the interference power. Using the path loss model, the total available bandwidth can be calculated based on the communication distance.

[0074] Combining the above formulas and models, we can analyze the network status and obtain the total available bandwidth and remaining bandwidth. The network topology can be obtained based on the link status between nodes in the ad hoc network itself.

[0075] Step 103: Using the target prediction network, based on the first key feature and the first network status report, predict the future network status of the ad hoc network; the future network status of the ad hoc network includes at least one of the following: link bandwidth, communication delay, and data packet loss rate.

[0076] Specifically, after obtaining a network status report and a set of key features, the target prediction network can be further used to predict the future network status of the ad hoc network based on the first key feature and the first network status report.

[0077] The future network status of an ad hoc network includes at least one of the following: link bandwidth, communication delay, and packet loss rate. Link bandwidth, communication delay, and packet loss rate are three key indicators of network performance and have a significant impact on the efficiency and reliability of network communications:

[0078] 1. Link Bandwidth: Link bandwidth refers to the maximum data transmission rate of the communication link between two devices in the network, usually measured in bits per second (bps).

[0079] It determines the maximum speed at which data can be transmitted on a link and is an important parameter for measuring network transmission capacity. Link bandwidth is limited by the technical specifications of the physical medium (such as optical fiber, copper cable, etc.) and network equipment (such as routers, switches, etc.).

[0080] 2. Communication Latency: Communication latency refers to the time required for data to travel from the sender to the receiver, including propagation delay, transmission delay, processing delay, and queuing delay.

[0081] Propagation delay is the time it takes for a signal to propagate through a physical medium and is related to the length of the medium and the speed of the signal. Transmission delay is the time it takes for data to travel across a link and is related to link bandwidth and packet size. Processing delay is the time it takes for network devices to process a packet, such as by looking up routing tables and classifying packets. Queuing delay is the time a packet waits for processing within a network device and often occurs during periods of network congestion.

[0082] 3. Packet Loss Rate: Packet loss rate refers to the ratio of the number of data packets lost during network transmission to the total number of data packets sent.

[0083] Packet loss can be caused by network congestion, link failures, device malfunctions, signal interference, and other factors. High packet loss rates can degrade communication quality and impact the integrity and reliability of data transmission. The impact of packet loss on user experience is particularly pronounced in real-time communications, such as voice and video calls.

[0084] The target prediction network is, for example, a deep learning model, which is a branch of machine learning that uses multi-layer neural networks to simulate the information processing of the human brain. By learning the features of the ad hoc network, the target prediction network predicts the future network status of the ad hoc network based on the first key features and the first network status report.

[0085] This prediction algorithm can also be any prediction model suitable for time series data, such as an autoregressive model, a moving average model, a deep learning model, etc. The prediction module outputs the predicted future network status, which can include link bandwidth, communication delay, packet loss rate, etc.

[0086] The method provided by the embodiment first acquires key parameters of the ad hoc network; wherein the key parameters include at least one of the following: the number of access points, environmental influences, environmental burst interference, channel conditions, noise conditions, inter-node link conditions, and communication distances; then, according to the key parameters, the first key features affecting the network status of the ad hoc network are identified, and the first network status report of the ad hoc network is generated based on the first key features; wherein the first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible influences of the ad hoc network; then, using the target prediction network, the future network status of the ad hoc network is predicted according to the first key features and the first network status report; the future network status of the ad hoc network includes at least one of the following: link bandwidth, communication delay, and packet loss rate.

[0087] The present application can collect various key parameters (such as the number of access points, environmental influences, environmental burst interference, channel conditions, noise conditions, inter-node link conditions, and communication distances) in real time, and use advanced data analysis and target prediction networks to predict the future network status of the ad hoc network. Through real-time data collection and analysis prediction, the communication effect of the ad hoc network can be more accurately predicted, thereby improving network efficiency and communication quality. The predicted future network status can provide real-time and accurate network performance prediction for network managers or commanders to assist them in making effective network management decisions. The present application realizes effective prediction of the network status of the ad hoc network.

[0088] According to the network status prediction method of the ad hoc network provided by the present application, according to the key parameters, the first key features affecting the network status of the ad hoc network are identified, and the first network status report of the ad hoc network is generated based on the first key features, which includes:

[0089] Removing duplicate data in the key parameters to obtain first data;

[0090] identify missing data in the first data and correct the missing data to obtain second data;

[0091] correct error data in the second data to obtain cleaned data;

[0092] normalize the cleaned data to obtain third data;

[0093] extract first key features based on the third data;

[0094] generate a first network status report of the ad hoc network based on the first key features.

[0095] Specifically, in some embodiments, step 102 can be implemented according to the following steps, including:

[0096] First, data cleaning of key parameters. This step is responsible for removing invalid, incomplete or incorrect data in the collected data to improve data quality. This can include removing duplicate data, handling missing data, correcting error data, etc. The specific steps include: (1) removing duplicate data in the key parameters to obtain first data. (2) Identify missing data in the first data and correct the missing data to obtain second data. (3) Correct error data in the second data to obtain cleaned data.

[0097] Further, normalize the cleaned data to obtain third data. Since the collected data can come from different units of measurement or orders of magnitude, normalization is needed to facilitate subsequent analysis. This can include maximum and minimum normalization, Z-score standardization, etc.

[0098] Further, based on the third data, first key features are extracted. This step is to identify and extract the key features that have the greatest impact on network performance. This can include the number of access points, channel status, link status, etc. This step is to analyze the status of the network based on the extracted features. This can include descriptive statistical analysis, correlation analysis, trend analysis, etc.

[0099] The goal of data analysis in this application is to obtain effective bandwidth. Effective bandwidth can be determined by the Shannon formula, and is also related to signal power and signal-to-noise ratio (i.e. noise floor). Effective bandwidth can also be affected by communication environment (e.g. channel spacing, communication distance), and effective bandwidth can also be affected by the number of access points. More access users will occupy time slot resources and affect the overall number of bandwidths. The above factors can all affect the remaining bandwidth, and the key factors vary depending on the communication environment (i.e. different features). For example, in the case of very low signal-to-noise ratio, other factors cannot achieve good network results even if they are good.

[0100] Furthermore, based on the first key feature, a first network status report of the ad hoc network is generated. Based on the above data analysis, a detailed network status report is generated. This report may include the current status of the network, possible problems, possible impacts, etc.

[0101] Network status reports may include information such as link bandwidth, communication latency, and packet loss rate. The process of generating a network status report involves calculating link bandwidth based on the aforementioned data (number of access points, etc.). Communication latency (i.e., delay) and packet loss rate can be calculated based on inter-node link status or reported content. Network status reports also include network connectivity and topology.

[0102] For example, the network status report may be presented in the form of a graph. Figure 4 This is a schematic diagram of the effect of the network status report provided by the present invention, such as Figure 4 The graph shows the network topology, signal-to-noise ratio, and node traffic share. Tables can be used to present environmental impacts, channel interference, and communication distance.

[0103] For example, Figure 5 This is the third flow chart of the network status prediction method of the self-organizing network provided by the present invention, which shows the process of data analysis, such as Figure 5 As shown, the method includes:

[0104] Step 501: Data cleaning.

[0105] Obtain the original data of the networking environment and perform data cleaning on it.

[0106] Step 502: Data normalization.

[0107] Step 503: Feature extraction.

[0108] Step 504: Data analysis.

[0109] Step 505: Generate a networking status report.

[0110] Step 506: Data prediction.

[0111] Data prediction results can provide decision support.

[0112] The method provided in this embodiment collects data from the ad hoc network, such as key parameters, and performs preliminary processing and analysis on it. This data analysis includes steps such as data cleaning, data normalization, and feature extraction. Furthermore, the data analysis module can identify key factors that may affect network performance and generate a network status report. This facilitates subsequent prediction of future network conditions based on these key factors and the network status report, thus enabling effective prediction of the ad hoc network.

[0113] According to a network status prediction method for an ad hoc network provided by the present invention, a target prediction network is obtained by training an initial prediction network using a sample data set and a sample label. The sample data set includes multiple samples, any sample includes a second key feature and a second network status report of the ad hoc network, and the sample label includes the future network status corresponding to each sample. The target prediction network is a deep learning model.

[0114] Specifically, in some embodiments, the target prediction network is a deep learning model, and the target prediction network is obtained by training the initial prediction network using a sample data set and a sample label. The sample data set includes multiple samples, and any sample includes a second key feature and a second network status report of the self-organizing network. The sample label includes the future network status corresponding to each sample.

[0115] Furthermore, the specific implementation process of using the target prediction network to predict the future network status of the ad hoc network according to the first key feature and the first network status report includes:

[0116] The target prediction network is a machine learning model, which is used to predict the future network status of the self-organizing network. Data needs to be collected in advance, including the network status report at a certain point in time and the subsequent possible transmission behavior and transmission results between nodes (such as Figure 4 The network status in the figure may subsequently show 33 sending broadband data to 0, such as video, resulting in lag and communication interruption. Prediction algorithms can use machine learning algorithms, such as RNNs. The training data sources are network status reports and the data collected in the first step (as the first key feature), as well as time-series data transmission behavior and transmission status (assessed using latency, packet loss rate, and interruptions).

[0117] During prediction, for a trained model, the input data is the network status report and the data extracted in the first step, and the output data is the network data transmission behavior in the future (in terms of traffic, for example, the ad hoc network reduces the available bandwidth by 10M).

[0118] The factors (features) and structure included in the network status report and the future network status are the same. The only difference lies in the internal data and the services that may be generated next (such as voice, video, short message, etc.).

[0119] The method provided in this embodiment is that the target prediction network is obtained by training the initial prediction network using a sample data set and a sample label. The sample data set includes multiple samples, any sample includes a second key feature and a second network status report of the self-organizing network, and the sample label includes the future network status corresponding to each sample. The target prediction network is a deep learning model. The target prediction network is used to predict the future network status of the self-organizing network based on the first key feature and the first network status report, thereby achieving effective prediction of the self-organizing network.

[0120] According to a method for predicting the network status of an ad hoc network provided by the present invention, the method further includes:

[0121] Determine decision recommendations for the ad hoc network based on future network conditions; the decision recommendations include at least one of the following: route selection, data rate adjustment, and service priority determination;

[0122] Based on the future network conditions, determine the corresponding decision recommendations for the ad hoc network, including:

[0123] Visualize the future network status and obtain visualization results;

[0124] Determine decision recommendations based on the visualization results.

[0125] Specifically, in some embodiments, the method further includes:

[0126] Determine decision recommendations for the ad hoc network based on future network conditions. These recommendations include at least one of the following: route selection, data rate adjustment, and service priority determination. Specifically, the ad hoc network recommendations can be made from the following aspects:

[0127] 1. Routing: Routing protocols must be able to quickly respond to changes in network topology, converge quickly when calculating routes, obtain valid routes, and minimize routing loops. During routing, nodes whose local topology changes slowly should be selected, and the number of link hops should be reduced by multiplying the change rate of node neighbors. Given the dynamic nature of ad hoc networks, routing algorithms should be able to dynamically adjust paths to adapt to environmental changes and node mobility. In scenarios such as military communications, routing should support message content of varying priorities to ensure extremely low latency for high-priority data.

[0128] 2. Data Rate Adjustment: Ad hoc networks must be able to adaptively change their transmission rates to flexibly provide appropriate transmission rates for a variety of services. Variable rate modulation methods, such as variable rate quadrature amplitude modulation (VR-QAM) and variable spreading gain code division multiple access (VSG-CDMA), can dynamically adjust the transmission rate based on link bandwidth and communication latency. Adaptive coding modulation (such as ATCQAM) dynamically matches the channel by changing the code rate and modulation constellation to minimize energy and achieve high spectral efficiency.

[0129] 3. Service Prioritization: In military communications scenarios, messages are prioritized based on their urgency. For example, tactical instructions are often time-critical, while information about the physical environment can tolerate slightly higher delays. In the design and simulation of a distributed ad hoc network system based on statistical priority, the Statistical Priority Multiple Access (SPMA) protocol is employed. Compared to traditional MAC protocols, this protocol always selects the highest-priority packets for transmission. In high-volume situations, the SPMA compares the load to a threshold, delaying or denying access to lower-priority packets. This ensures a high packet delivery success rate and a stable load.

[0130] Based on the above information, the decision-making recommendations for ad hoc networks should include:

[0131] Routing: Utilizes routing protocols that can quickly respond to changes in network topology, selects nodes where local topology changes slowly, and dynamically adjusts routes to adapt to environmental changes. Data rate adjustment: Dynamically adjusts the transmission rate based on link bandwidth and communication latency, using adaptive modulation and coding modulation techniques to adapt to varying network conditions. Service prioritization: Prioritizes different data packets based on message urgency and service type, prioritizing the transmission of high-priority data, especially under high-load conditions.

[0132] Correspondingly, in some embodiments, the specific implementation process of determining the decision recommendation corresponding to the ad hoc network based on the future network status includes the following steps:

[0133] The future network status is visualized to obtain visualization results; based on the visualization results, decision recommendations are determined. The decision support module provides a visualization of the prediction results to facilitate commanders' decision-making.

[0134] Exemplarily, determining the decision suggestion corresponding to the ad hoc network is implemented as follows:

[0135] Assumptions Figure 4To predict the future network status, since the network status of node 33 is poor, if it continues to move forward, it may cause communication interruption, so other nodes are needed to supplement it. For example, the position of node 30 is adjusted to improve its link quality, and node 7 is moved to nodes 30 and 33 to take on the relay function to ensure the link quality and bandwidth of node 33.

[0136] The method provided in this embodiment includes at least one of the following: route selection, data transmission rate adjustment, and service priority determination. First, the future network status is visualized to obtain a visualization result, and a decision recommendation is determined based on the visualization result. The future network status predicted by the present invention can provide a basis for network management decisions. Network managers or commanders can make decisions in advance based on the predicted network status, thereby improving network performance, service quality, and user experience.

[0137] According to a method for predicting the network status of an ad hoc network provided by the present invention, the method further includes:

[0138] Comparing the future network status of the ad hoc network with the current network status of the ad hoc network to obtain a comparison result;

[0139] Based on the comparison results, the model parameters of the target prediction network are optimized.

[0140] Specifically, in some embodiments, the method further includes:

[0141] The future network status of the ad hoc network is compared with the current network status of the ad hoc network to obtain a comparison result; based on the comparison result, the model parameters of the target prediction network are optimized. For example, the feedback module of the system is used to compare the actual network performance with the predicted network performance to optimize the prediction performance of the data analysis and prediction module.

[0142] The method provided in this embodiment can optimize the prediction performance of the data analysis and prediction module based on the predicted network performance.

[0143] The present invention also provides a network status prediction system for an ad hoc network, illustratively, as Figure 2 As shown, the network status prediction system of the ad hoc network includes a data collection module 210, a data analysis module 220, a prediction module 230, a decision support module 240 and a feedback module 250; wherein,

[0144] The data collection module 210 is used to obtain key parameters of the ad hoc network, wherein the key parameters include at least one of the following: the number of access points, environmental impact, sudden environmental interference, channel conditions, noise floor conditions, inter-node link conditions, and communication distance;

[0145] The data analysis module 220 is configured to identify, based on the key parameters, a first key feature that affects the network status of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key feature;

[0146] A prediction module 230 is configured to use a target prediction network to predict a future network status of the ad hoc network according to the first key feature and the first network status report;

[0147] A decision support module 240 is configured to determine a decision suggestion corresponding to the ad hoc network based on the future network status;

[0148] The feedback module 250 is configured to compare the future network status of the ad hoc network with the current network status of the ad hoc network to obtain a comparison result; and optimize the model parameters of the target prediction network based on the comparison result.

[0149] Specifically, the system described above is only one embodiment of the present invention, and the present invention may also have other embodiments. For example, the data collection module, data analysis module, prediction module, and decision support module may exist independently or be integrated on one or more devices. The data collection module and the data analysis module may be integrated or separate. The prediction module may use various prediction algorithms, including but not limited to regression analysis, time series analysis, machine learning, etc. The decision support module may provide various decision recommendations, including but not limited to routing selection, traffic control, quality of service optimization, etc.

[0150] In the system provided in this embodiment, a data collection module 210 is configured to obtain key parameters of the ad hoc network. The key parameters include at least one of the following: the number of access points, environmental impact, sudden environmental interference, channel conditions, noise floor conditions, inter-node link conditions, and communication distance. A data analysis module 220 is configured to identify, based on the key parameters, a first key feature that affects the network status of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key feature. The first network status report includes at least one of the following: the current status of the ad hoc network, possible problems with the ad hoc network, and possible impacts on the ad hoc network. A prediction module 230 is configured to use a target prediction network to predict the future network status of the ad hoc network based on the first key feature and the first network status report. The future network status of the ad hoc network includes at least one of the following: link bandwidth, communication delay, and packet loss rate. A decision support module 240 is configured to determine a decision recommendation corresponding to the ad hoc network based on the future network status. A feedback module 250 is configured to compare the future network status of the ad hoc network with the current network status of the ad hoc network to obtain a comparison result, and optimize the model parameters of the target prediction network based on the comparison result.

[0151] The network status prediction system for an ad hoc network provided by the present invention can collect various key parameters of the ad hoc network in real time (such as the number of access points, environmental impact, sudden environmental interference, channel conditions, noise floor, inter-node link conditions, and communication distance). It then uses advanced data analysis and target prediction networks to predict the future network status of the ad hoc network. Through real-time data collection, analysis, and prediction, it can more accurately predict the communication performance of the ad hoc network, thereby improving network efficiency and communication quality. The predicted future network status can provide network managers or commanders with real-time and accurate network performance predictions, assisting them in making effective network management decisions. The present invention effectively predicts the network status of an ad hoc network.

[0152] The network status prediction device for an ad hoc network provided by the present invention is described below. The network status prediction device for an ad hoc network described below and the network status prediction method for an ad hoc network described above can be referenced to each other.

[0153] Figure 6 Schematic diagram of the structure of the network status prediction device of the self-organizing network provided by the present invention, such as Figure 6 As shown, the network status prediction device 600 of the ad hoc network includes the following modules: an acquisition module 610 and a prediction module 620; wherein:

[0154] An acquisition module 610 is configured to acquire key parameters of the ad hoc network, wherein the key parameters include at least one of the following: number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0155] A prediction module 620 is configured to identify, based on the key parameters, a first key feature that affects the network status of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key feature;

[0156] The target prediction network is used to predict the future network status of the ad hoc network according to the first key feature and the first network status report.

[0157] The device provided by the embodiment comprises an acquisition module 610 and a prediction module 620, wherein the acquisition module 610 is configured to acquire key parameters of the ad hoc network; the key parameters comprise at least one of the following: the number of access points, environmental influence, environmental burst interference, channel condition, noise floor condition, inter-node link condition and communication distance; the prediction module 620 is configured to identify a first key feature of the network condition of the ad hoc network according to the key parameters, and generate a first network status report of the ad hoc network based on the first key feature; the first network status report comprises at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network and possible influence of the ad hoc network; then, a target prediction network is used to predict a future network condition of the ad hoc network according to the first key feature and the first network status report; the future network condition of the ad hoc network comprises at least one of the following: link bandwidth, communication delay and data packet loss rate.

[0158] The application can collect various key parameters (such as the number of access points, environmental influence, environmental burst interference, channel condition, noise floor condition, inter-node link condition and communication distance) in the ad hoc network in real time, and use an advanced data analysis and target prediction network to predict the future network condition of the ad hoc network, so that the communication effect of the ad hoc network can be more accurately predicted through real-time data collection and analysis prediction, thereby improving the network efficiency and communication quality; the predicted future network condition can provide real-time and accurate network performance prediction for network managers or commanders, so as to assist them to make effective network management decisions. The application realizes effective prediction of the network status of the ad hoc network.

[0159] According to the network status prediction device 600 of the ad hoc network provided by the application, the prediction module 620 is specifically configured to:

[0160] Remove the repeated data in the key parameters to obtain first data;

[0161] Identify missing data in the first data, and correct the missing data to obtain second data;

[0162] Correct error data in the second data to obtain cleaned data;

[0163] Perform normalization processing on the cleaned data to obtain third data;

[0164] Extract the first key feature based on the third data;

[0165] Generate a first network status report of the ad hoc network based on the first key feature.

[0166] According to a network status prediction device 600 for a self-organizing network provided by the present invention, the target prediction network is obtained after training the initial prediction network using a sample data set and a sample label, the sample data set includes multiple samples, any of the samples includes a second key feature and a second network status report of the self-organizing network, and the sample label includes the future network status corresponding to each of the samples; the target prediction network is a deep learning model.

[0167] According to the present invention, a network status prediction device 600 for an ad hoc network further includes a decision-making auxiliary module;

[0168] The decision support module is used to:

[0169] Determining a decision suggestion corresponding to the ad hoc network based on the future network status; the decision suggestion includes at least one of the following: route selection, data transmission rate adjustment, and service priority determination;

[0170] The determining, based on the future network status, a decision suggestion corresponding to the ad hoc network includes:

[0171] Visually displaying the future network status to obtain a visualization result;

[0172] The decision suggestion is determined based on the visualization result.

[0173] According to a network status prediction device 600 of an ad hoc network provided by the present invention, the device further includes a feedback module;

[0174] The feedback module is used to:

[0175] Comparing the future network status of the ad hoc network with the current network status of the ad hoc network to obtain a comparison result;

[0176] Based on the comparison result, the model parameters of the target prediction network are optimized.

[0177] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the network status prediction method of the ad hoc network, which includes:

[0178] Obtain key parameters of the ad hoc network; the key parameters include at least one of the following: number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0179] According to the key parameters, a first key feature that affects the network status of the ad hoc network is identified, and a first network status report of the ad hoc network is generated based on the first key feature; the first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible impacts of the ad hoc network;

[0180] Using the target prediction network, based on the first key feature and the first network status report, the future network status of the self-organizing network is predicted; the future network status of the self-organizing network includes at least one of the following: link bandwidth, communication delay and data packet loss rate.

[0181] Furthermore, the logic instructions in the aforementioned memory 730 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 portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0182] On the other hand, the present invention further provides a computer program product, the computer program product including a computer program, the computer program being storable on a non-transitory computer-readable storage medium, and the computer program being executed by a processor, enabling the computer to perform the network status prediction method for an ad hoc network provided by each of the above methods, the method including:

[0183] Obtain key parameters of the ad hoc network; the key parameters include at least one of the following: number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0184] According to the key parameters, a first key feature that affects the network status of the ad hoc network is identified, and a first network status report of the ad hoc network is generated based on the first key feature; the first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible impacts of the ad hoc network;

[0185] Using the target prediction network, based on the first key feature and the first network status report, the future network status of the self-organizing network is predicted; the future network status of the self-organizing network includes at least one of the following: link bandwidth, communication delay and data packet loss rate.

[0186] In another aspect, the present invention further 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 network status prediction method for an ad hoc network provided by each of the above methods, the method comprising:

[0187] Obtain key parameters of the ad hoc network; the key parameters include at least one of the following: number of access points, environmental impact, sudden environmental interference, channel conditions, background noise, inter-node link conditions, and communication distance;

[0188] According to the key parameters, a first key feature that affects the network status of the ad hoc network is identified, and a first network status report of the ad hoc network is generated based on the first key feature; the first network status report includes at least one of the following: the current status of the ad hoc network, possible problems of the ad hoc network, and possible impacts of the ad hoc network;

[0189] Using the target prediction network, based on the first key feature and the first network status report, the future network status of the self-organizing network is predicted; the future network status of the self-organizing network includes at least one of the following: link bandwidth, communication delay and data packet loss rate.

[0190] The device embodiments described above are merely illustrative. 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, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0191] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion 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, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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. However, 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 invention.

Claims

1. A method for predicting network status of an ad hoc network, characterized in that: include: Obtain key parameters of the ad hoc network; the key parameters include at least one of the following: number of access points, environment, sudden interference in the environment, channel conditions, background noise conditions, inter-node link conditions, and communication distance; Identifying, based on the key parameters, a first key feature that affects a network status of the ad hoc network, and generating a first network status report of the ad hoc network based on the first key feature; the first network status report including at least one of the following: a current status of the ad hoc network and a possible problem of the ad hoc network; Using the target prediction network, the future network status of the self-organizing network is predicted based on the first key feature and the first network status report; the future network status of the self-organizing network includes at least one of the following: link bandwidth, communication delay and data packet loss rate; the target prediction network is obtained after training the initial prediction network using a sample data set and a sample label, the sample data set includes multiple samples, any of the samples includes the second key feature and the second network status report of the self-organizing network, and the sample label includes the future network status corresponding to each of the samples; the target prediction network is a deep learning model.

2. The method for predicting the network status of an ad hoc network according to claim 1, wherein: The step of identifying, according to the key parameter, a first key feature that affects the network status of the ad hoc network, and generating a first network status report of the ad hoc network based on the first key feature, includes: Removing duplicate data from the key parameters to obtain first data; Identifying missing data in the first data and correcting the missing data to obtain second data; Correcting erroneous data in the second data to obtain cleaned data; Normalizing the cleaned data to obtain third data; Extracting the first key feature based on the third data; Based on the first key feature, a first network status report of the ad hoc network is generated.

3. The network status prediction method of an ad hoc network according to claim 1 or 2, characterized in that: The method further comprises: Determining a decision suggestion corresponding to the ad hoc network based on the future network status; the decision suggestion includes at least one of the following: route selection, data transmission rate adjustment, and service priority determination; The determining, based on the future network status, a decision suggestion corresponding to the ad hoc network includes: Visually displaying the future network status to obtain a visualization result; The decision suggestion is determined based on the visualization result.

4. The network status prediction method of an ad hoc network according to claim 1 or 2, characterized in that: The method further comprises: Comparing the future network status of the ad hoc network with the current network status of the ad hoc network to obtain a comparison result; Based on the comparison result, the model parameters of the target prediction network are optimized.

5. A network status prediction system for an ad hoc network, characterized in that: The network status prediction system of the self-organizing network includes a data collection module, a data analysis module, a prediction module, a decision support module and a feedback module; wherein, A data collection module is used to obtain key parameters of the ad hoc network, wherein the key parameters include at least one of the following: the number of access points, the environment, sudden interference in the environment, the channel condition, the background noise condition, the link condition between nodes, and the communication distance; a data analysis module, configured to identify, based on the key parameters, a first key characteristic that affects a network status of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key characteristic; the first network status report including at least one of the following: a current status of the ad hoc network and a possible problem with the ad hoc network; A prediction module is configured to use a target prediction network to predict a future network status of the ad hoc network based on the first key feature and the first network status report; the future network status of the ad hoc network includes at least one of the following: link bandwidth, communication delay, and packet loss rate; the target prediction network is obtained by training an initial prediction network using a sample data set and sample labels, the sample data set including a plurality of samples, any of the samples including the second key feature and the second network status report of the ad hoc network, and the sample labels including the future network status corresponding to each of the samples; the target prediction network is a deep learning model; A decision-making assistance module, configured to determine a decision suggestion corresponding to the ad hoc network based on the future network status; The feedback module is used to compare the future network status of the self-organizing network with the current network status of the self-organizing network to obtain a comparison result; based on the comparison result, optimize the model parameters of the target prediction network.

6. A network status prediction device for an ad hoc network, characterized in that: include: An acquisition module is used to obtain key parameters of the ad hoc network, wherein the key parameters include at least one of the following: the number of access points, the environment, sudden interference in the environment, the channel condition, the background noise condition, the link condition between nodes, and the communication distance; a prediction module, configured to identify, based on the key parameters, a first key characteristic that affects a network condition of the ad hoc network, and generate a first network status report of the ad hoc network based on the first key characteristic; the first network status report including at least one of the following: a current state of the ad hoc network and a possible problem with the ad hoc network; Using the target prediction network, the future network status of the self-organizing network is predicted based on the first key feature and the first network status report; the future network status of the self-organizing network includes at least one of the following: link bandwidth, communication delay and data packet loss rate; the target prediction network is obtained after training the initial prediction network using a sample data set and a sample label, the sample data set includes multiple samples, any of the samples includes the second key feature and the second network status report of the self-organizing network, and the sample label includes the future network status corresponding to each of the samples; the target prediction network is a deep learning model.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the network status prediction method for an ad hoc network according to any one of claims 1 to 4 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the network status of an ad hoc network according to any one of claims 1 to 4 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the network status of an ad hoc network according to any one of claims 1 to 4 is implemented.

Images