Internet of Things wireless communication path optimization method based on artificial intelligence

Abstract

The invention discloses an Internet of Things wireless communication path optimization method based on artificial intelligence. The method comprises the steps of original data acquisition, original data optimization, network state prediction model construction, path selection optimization model design and Internet of Things wireless communication path optimization. According to the invention, original data is obtained through data acquisition; an improved bidirectional long-short-term memory network model is adopted as a network state prediction model, implicit multi-source time sequence data is converted into dominant demand intensity for different communication paths, and real-time demand intensity of each communication path is accurately recognized by fusing time sequence dependence analysis and a periodic attention mechanism; an improved reinforcement learning model is adopted as a path selection optimization model, a dynamic space comprehensively representing a decision-making environment is constructed, an action constraint network is introduced, action feasibility is ensured, and balance among multiple targets is achieved through near-end strategy optimization, so that a personalized path control strategy giving consideration to instant service quality and long-term network efficiency is generated.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of Internet of Things wireless communication path optimization, in particular to an Internet of Things wireless communication path optimization method based on artificial intelligence. BACKGROUND

[0002] The Internet of Things wireless communication path optimization refers to the process of intelligently adjusting and optimizing the data transmission path selection strategy of a wireless network with multiple communication modes such as multi-hop, multi-rate, and multiple quality of service levels by using intelligent technology. Through algorithmic continuous learning of network traffic patterns, node states, and environmental parameters, the bandwidth allocation, transmission rate, priority, and routing selection of different data transmission paths are dynamically planned, and the precise matching of communication paths and network demand and business objectives is achieved, meeting the individualized needs of Internet of Things applications for diversified communication services.

[0003] However, the traditional Internet of Things wireless communication path optimization method usually relies on preset rules or short-term historical statistics, and cannot effectively integrate the dynamic interaction characteristics of network environment, node state, and traffic pattern, resulting in the identification of network demand state being limited to shallow association, and lacking the ability to model long-period traffic patterns, only responding to immediate traffic and ignoring potential patterns, leading to the technical problems of rigid strategy and inability to adapt to dynamic network scenarios. The traditional Internet of Things wireless communication path optimization method often uses heuristic rules or single-target control, making it difficult to handle multi-dimensional state input, leading to the strategy deviating from the actual network physical and protocol constraints, causing network congestion, excessive energy consumption, or degradation of service quality, and the single-target optimization ignores the differences between business types, resulting in unfair resource allocation and low overall efficiency. SUMMARY

[0004] In view of the above, in order to overcome the defects of the prior art, the present application provides an Internet of Things wireless communication path optimization method based on artificial intelligence, which is aimed at the technical problems that the traditional Internet of Things wireless communication path optimization method usually relies on preset rules or short-term historical statistics, cannot effectively fuse the dynamic interaction characteristics of network environment, node state and traffic mode, leads to the identification of network demand state staying in shallow association, and lacks the modeling ability of long-period traffic law, can only respond to instant traffic and ignore potential rules, resulting in rigid strategy and inability to adapt to dynamic network scenarios. The present scheme creatively uses an improved bidirectional long short-term memory network model as a network state prediction model, converts the implicit network environment, traffic mode and node state and other multi-source time series data into explicit demand intensity indicators for different communication paths, adaptively learns the network traffic mode through the fusion of time series dependence analysis and periodic attention mechanism, accurately identifies the real-time demand intensity of each communication path, and provides an interpretable and high-precision demand input for subsequent path selection optimization; the present scheme creatively uses an improved reinforcement learning model as a path selection optimization model, integrates network basic conditions, real-time demand intensity and business scenarios through hierarchical state coding, constructs a dynamic space that comprehensively represents the decision environment, introduces an action constraint network, embeds network protocols and physical boundaries as learnable functions into strategy generation, ensures the feasibility of actions, realizes adaptive trade-off among multiple objectives by using proximal policy optimization, and generates a personalized path control strategy that takes into account both instant service quality and long-term network efficiency.

[0005] The technical scheme adopted by the present application is as follows: the Internet of Things wireless communication path optimization method based on artificial intelligence provided by the present application comprises the following steps:

[0006] Step S1: raw data acquisition;

[0007] Step S2: raw data optimization;

[0008] Step S3: network state prediction model construction;

[0009] Step S4: path selection optimization model design;

[0010] Step S5: Internet of Things wireless communication path optimization.

[0011] Further, in step S1, the original data collection is used to collect the original data required for the optimization of the Internet of Things wireless communication path, specifically by collecting data to obtain a path optimization original data set, which specifically includes a historical path original data set and a current path original data set, both of which include network environment data, traffic feature data and node state data, and the historical path original data set also includes service quality feedback data.

[0012] Further, in step S2, the original data optimization is used to optimize the collected original data, specifically including the following steps:

[0013] Step S21: data cleaning, used to process missing values and correct outliers, specifically by filling in sensor or network element gap through time series linear interpolation, and identifying and correcting outliers through dynamic threshold algorithm to improve data quality;

[0014] Step S22: multi-source alignment processing, used to solve the difference in sampling frequency of heterogeneous data, specifically by realizing time domain alignment of network environment data, traffic feature data and node state data through sliding window aggregation;

[0015] Step S23: data normalization, used to adapt to network load and scene changes to normalize data, specifically by processing data through minimum-maximum normalization method by time slice to eliminate network fluctuation influence;

[0016] Step S24: data set segmentation, used to segment the historical data set into training set and test set, specifically by segmenting the historical path original data set into path training set and path test set;

[0017] Step S25: optimized original data, specifically by optimizing the current path original data set through the data cleaning, multi-source alignment processing and data normalization to obtain a to-be-processed data set, and optimizing the historical path original data set through the data cleaning, multi-source alignment processing, data normalization and data set segmentation to obtain the path training set and path test set.

[0018] Further, in step S3, the network state prediction model construction is used to construct a model required for extracting dynamic time sequence features of network traffic and environment and quantifying path demand intensity, specifically by constructing an improved bidirectional long short-term memory network model as a network state prediction model, which specifically includes a multi-source fusion module, a bidirectional feature extraction module, a periodic attention module and a demand intensity quantification module;

[0019] The network state prediction model is constructed, and specifically includes the following steps:

[0020] Step S31: Multi-source fusion module construction, for processing multi-source data scale difference and feature incompatibility problem, specifically through the learnable gating weight dynamic weighting network environment feature, traffic feature data and node state feature, to obtain multi-source fusion feature, the steps include:

[0021] Step S311: Gating weight generation, for adaptive allocation of data importance weight, specifically through linear transformation and Sigmoid activation function to generate weight ratio, to obtain fusion gating weight;

[0022] Step S312: Feature transformation, for improving the expression ability of features, specifically through linear mapping and then through the hyperbolic tangent function to process the network environment feature, traffic feature data and node state feature, to obtain enhanced network environment feature, enhanced traffic feature and enhanced node state feature;

[0023] Step S313: Feature fusion calculation, for effectively fusing multi-source information, specifically through the gating weight to weight and sum the enhanced features of each data source, to obtain multi-source fusion feature;

[0024] Step S32: Bidirectional feature extraction module construction, for capturing long and short term network traffic dependence relationship, specifically through bidirectional long and short term memory network to extract time series pattern from forward and backward respectively, to obtain bidirectional time series feature;

[0025] Step S33: Periodic attention module construction, for enhancing the ability of periodic network traffic pattern recognition, specifically through time position encoding to guide attention focus key cycle node, to obtain periodic reinforcement feature, the steps include:

[0026] Step S331: Time encoding generation, for injecting periodic priori knowledge, specifically through sine and cosine function to encode 24-hour daily cycle and 168-hour weekly cycle time points, to obtain periodic encoding vector for attention correction;

[0027] Step S332: Attention energy calculation, for identifying cycle sensitive moment, specifically through linear transformation to fuse bidirectional time series feature and periodic encoding vector, to obtain attention energy score of each moment;

[0028] Step S333: Obtain periodic reinforcement feature, for generating periodic reinforcement feature, specifically through Softmax function to convert attention energy score into probability distribution, and weight sum bidirectional time series feature, to obtain periodic reinforcement feature;

[0029] Step S34: a demand intensity quantification module is constructed for explicitly quantifying the implicit path demand, specifically, learning the demand intensity of each communication path by improving the activation function to obtain path demand intensity features, and the steps include:

[0030] Step S341: feature mapping is used to reduce and abstract features, specifically, compressing the periodic reinforcement features through a fully connected layer to obtain compressed periodic reinforcement features;

[0031] Step S342: an improved activation function is designed to enhance non-linear representation capability, specifically, expanding the output range of the Sigmoid activation function by introducing a learnable slope parameter to obtain an improved activation function, and processing the compressed periodic reinforcement features of each communication path based on the improved activation function to obtain the demand intensity of each communication path, which constitutes a demand intensity vector;

[0032] Step S35: the model is constructed and trained, specifically, the improved bidirectional long short-term memory network model is constructed by integrating the multi-source fusion module, the bidirectional feature extraction module, the periodic attention module, and the demand intensity quantification module, the model is trained based on the path training set, and the model performance is verified based on the path test set to obtain the improved bidirectional long short-term memory network model as the network state prediction model.

[0033] Further, in step S4, the path selection optimization model is designed to design the model required for dynamically generating personalized path selection control strategies, specifically, an improved reinforcement learning model is constructed as a path selection optimization model, and the improved reinforcement learning model specifically includes a state encoding module, an action constraint network, and a policy optimization module.

[0034] The path selection optimization model design specifically includes the following steps:

[0035] Step S41: the state encoding module is constructed to structure the decision state, specifically, by separating three layers of information of the basic state, the context state, and the time state to obtain a hierarchical state space, the basic state is used to represent network environment and node basic information, the context state is used to represent path demand intensity information and service quality feedback information, and the time state is used to represent time period information, and the state encoding module construction includes the following steps:

[0036] Step S411: state hierarchical encoding is used to distinguish state type importance, specifically, three groups of state vectors are obtained by processing the information of the three states through independent fully connected layers;

[0037] Step S412: state space integration, for constructing a joint state representation, specifically, by concatenating the base state vector, the context state vector and the time state vector to obtain a comprehensive decision state space;

[0038] Step S42: action constraint network design, for guaranteeing the network feasibility of the path selection strategy, specifically, by learning the mapping from the network state to the protocol boundary through a neural network to obtain a real-time actionable interval, the step includes:

[0039] Step S421: constraint boundary prediction, for modeling the network physical and protocol restriction rules, specifically, by processing the node state data through a two-layer ReLU network to output path selection boundary parameters;

[0040] Step S422: constraint matrix generation, for formatting the action boundary, specifically, by scaling the minimum and maximum values of the pre-defined parameters through a Sigmoid activation function to obtain a constraint matrix executable for the network system;

[0041] Step S43: reward function design, for balancing the quality of service and the network performance, specifically, by weighting the communication quality index and the network resource consumption index to obtain a composite reward function guiding the optimization of the strategy;

[0042] Step S44: strategy optimization module construction, for stabilizing the learning of the optimal path selection strategy, specifically, by adopting the proximal policy optimization to update the strategy under the restriction of the action constraint network;

[0043] Step S45: model construction and training, specifically, by integrating the state encoding module construction, the action constraint network design, the reward function design and the strategy optimization module construction to construct an improved reinforcement learning model, training the model based on the path training set, verifying the model performance based on the path test set, obtaining the improved reinforcement learning model as the path selection optimization model.

[0044] Further, in step S5, the Internet of Things wireless communication path optimization, specifically, taking the to-be-processed data set as the input of the network state prediction model to obtain a demand intensity reference result, and taking the demand intensity reference result combined with the to-be-processed data set as the input of the path selection optimization model to obtain an optimal path selection control strategy, the demand intensity reference result is specifically a demand intensity vector set obtained based on the input.

[0045] The above-mentioned scheme has the following beneficial effects:

[0046] (1) The traditional wireless communication path optimization method for the Internet of Things has the technical problems that it usually relies on preset rules or short-term historical statistics, cannot effectively fuse the dynamic interaction characteristics of network environment, node state and traffic mode, leads to the identification of network demand state staying in shallow association, and lacks the modeling ability of long-period traffic law, can only respond to instant traffic and ignore potential rules, resulting in rigid strategy and inability to adapt to dynamic network scenarios. The scheme creatively uses an improved bidirectional long short-term memory network model as a network state prediction model, converts the implicit network environment, traffic mode and node state and other multi-source time series data into explicit demand intensity indicators for different communication paths, adaptively learns the network traffic mode through the fusion of time series dependence analysis and periodic attention mechanism, accurately identifies the real-time demand intensity of each communication path, and provides an interpretable and high-precision demand input for subsequent path selection optimization.

[0047] (2) The traditional wireless communication path optimization method for the Internet of Things has the technical problems that it usually uses heuristic rules or single-objective control, is difficult to handle multi-dimensional state input, leads to the strategy deviating from the actual network physical and protocol constraints, causes network congestion, high energy consumption or degradation of service quality, and single-objective optimization ignores the differences between business types, resulting in unfair resource allocation and low overall efficiency. The scheme creatively uses an improved reinforcement learning model as a path selection optimization model, integrates network basic conditions, real-time demand intensity and business context through hierarchical state coding, builds a dynamic space that comprehensively represents the decision environment, and introduces an action constraint network to embed network protocols and physical boundaries as a learnable function into strategy generation, ensuring the feasibility of actions, and using proximal policy optimization to achieve adaptive trade-off between multiple objectives, thereby generating a personalized path control strategy that takes into account both instant service quality and long-term network efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 The flowchart of the wireless communication path optimization method for the Internet of Things based on artificial intelligence provided by the present application is shown in the figure.

[0049] Figure 2 The flowchart of the original data optimization of step S2 is shown in the figure.

[0050] Figure 3 The flowchart of the network state prediction model construction of step S3 is shown in the figure.

[0051] Figure 4 The flowchart of the path selection optimization model design of step S4 is shown in the figure.

[0052] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation of the present application. DETAILED DESCRIPTION

[0053] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0054] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0055] Example 1, see Figure 1 The present invention provides an AI-based IoT wireless communication path optimization method, which includes the following steps:

[0056] Step S1: Raw data acquisition;

[0057] Step S2: Optimize the raw data;

[0058] Step S3: Constructing the network state prediction model;

[0059] Step S4: Path selection optimization model design;

[0060] Step S5: IoT wireless communication path optimization.

[0061] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the raw data acquisition is used to collect the raw data required for IoT wireless communication path optimization. Specifically, by performing data acquisition, a path optimization raw dataset is obtained. The path optimization raw dataset specifically includes a historical path raw dataset and a current path raw dataset. Both the historical path raw dataset and the current path raw dataset include network environment data, traffic characteristic data, and node status data. The historical path raw dataset also includes service quality feedback data.

[0062] The communication path modes of the Internet of Things (IoT) wireless network specifically include high-bandwidth paths, low-latency paths, and high-reliability paths. The network environment data specifically includes channel quality data, interference intensity data, and link packet loss rate data collected by sensors or network elements. The traffic characteristic data specifically includes data packet timestamps, data stream types, data packet sizes, data stream transmission durations, bandwidth requirements, and latency requirements collected from network traffic monitoring and logs. The node status data specifically includes node remaining energy data, single transmission energy consumption data, node load data, buffer occupancy rate data, wireless module operating status data, and routing table status data collected in real time by node devices. The service quality feedback data specifically includes end-to-end latency data, throughput data, packet loss rate data, and service success rate data.

[0063] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S2, the raw data optimization is used to optimize the collected raw data, specifically including the following steps:

[0064] Step S21: Data cleaning, used to handle missing values ​​and correct outliers. Specifically, it involves filling gaps in sensors or network elements through time series linear interpolation and identifying and correcting outliers through dynamic thresholding algorithms to improve data quality.

[0065] Step S22: Multi-source alignment processing, used to solve the difference in sampling frequency of heterogeneous data, specifically to achieve temporal alignment of network environment data, traffic feature data and node status data through sliding window aggregation;

[0066] Step S23: Data normalization, used to normalize data to adapt to network load and scene changes. Specifically, the data is processed by using the minimum-maximum normalization method by time slice to eliminate the impact of network fluctuations.

[0067] Step S24: Dataset splitting, used to split the historical dataset into training set and test set, specifically splitting the original dataset of the historical path into path training set and path test set;

[0068] Step S25: Optimize the original data, specifically by optimizing the original dataset of the current path through data cleaning, multi-source alignment processing, and data normalization to obtain the dataset to be processed, and by optimizing the original dataset of the historical path through data cleaning, multi-source alignment processing, data normalization, and dataset segmentation to obtain the path training set and the path test set.

[0069] Example 4, see Figure 1 and Figure 3This embodiment is based on the above embodiment. In step S3, the network state prediction model is constructed to build a model for extracting the dynamic temporal features of network traffic and environment and quantifying the path demand intensity. Specifically, it is to construct an improved bidirectional long short-term memory network model as the network state prediction model. The improved bidirectional long short-term memory network model specifically includes a multi-source fusion module, a bidirectional feature extraction module, a periodic attention module, and a demand intensity quantification module.

[0070] The construction of the network state prediction model specifically includes the following steps:

[0071] Step S31: Construction of a multi-source fusion module to address the issues of scale differences and feature incompatibility among multi-source data. Specifically, this involves dynamically weighting network environment features, traffic feature data, and node state features using learnable gating weights to obtain multi-source fusion features. The steps include:

[0072] Step S311: Gated weight generation, used for adaptive allocation of data importance weights. Specifically, it generates weight ratios through linear transformation and the Sigmoid activation function to obtain fused gated weights. The formula used is as follows:

[0073] ;

[0074] In the formula, This indicates that the gating weights are fused at time t. This represents the Sigmoid activation function. Indicates the gating mapping weights, Indicates the gating mapping bias term. This represents the network environment characteristics at time t. This represents the flow characteristics at time t. This represents the state characteristics of a node at time t;

[0075] Step S312: Feature transformation, used to improve the expressive power of features. Specifically, the network environment features, traffic features, and node state features are linearly mapped and then processed by the hyperbolic tangent function to obtain enhanced network environment features, enhanced traffic features, and enhanced node state features. The formulas used are as follows:

[0076] ;

[0077] In the formula, This indicates the enhanced network environment characteristics at time t. This indicates that the enhanced flow characteristics are at time t. This indicates that the state characteristics of the enhanced node are represented at time t. Represents the hyperbolic tangent function. Indicates the network environment mapping weights. This represents the network environment mapping bias term. Indicates traffic mapping weights, This represents the traffic mapping bias term. Indicates the node state mapping weight. This represents the node state mapping bias term;

[0078] Step S313: Feature fusion calculation, used to effectively fuse multi-source information. Specifically, it involves weighted summation of the enhanced features from each data source using gated weights to obtain multi-source fused features. The formula used is as follows:

[0079] ;

[0080] In the formula, Indicates multi-source fusion characteristics, This represents element-wise multiplication.

[0081] Step S32: Construction of a bidirectional feature extraction module, used to capture the traffic dependencies of long short-term memory networks. Specifically, it extracts temporal patterns from both the forward and backward directions using a bidirectional long short-term memory network to obtain bidirectional temporal features. The formula used is as follows:

[0082] ;

[0083] In the formula, This represents the forward hidden state at time t. This represents the backward hidden state at time t. This represents the forward hidden state at time t-1. This represents the backward hidden state at time t-1. This represents the bidirectional time series characteristics at time t. Represents a long short-term memory network function;

[0084] Step S33: Construction of a periodic attention module to enhance the ability to recognize periodic network traffic patterns. Specifically, attention is guided to focus on key periodic nodes through temporal location encoding to obtain periodic enhanced features. The steps include:

[0085] Step S331: Time encoding generation, used to inject periodic prior knowledge. Specifically, it encodes 24-hour daily and 168-hour weekly time points using sine and cosine functions to obtain a periodic encoding vector for attention correction. The formula used is as follows:

[0086] ;

[0087] In the formula, This represents the periodic encoded vector at time t, where t represents the time index.

[0088] Step S332: Attention energy calculation, used to identify periodic sensitive moments. Specifically, it involves fusing bidirectional temporal features and periodic encoding vectors through linear transformation to obtain the attention energy score at each moment. The formula used is as follows:

[0089] ;

[0090] In the formula, Let represent the attention energy score at time t, and lv represent the learnable energy score calculation vector. Represents the weights for bidirectional time-series feature transformation. This represents the weights of the periodic encoding vector transformation. This represents the energy fraction transformation bias term, and T represents the transpose operation;

[0091] Step S333: Obtain periodic enhancement features, which are used to generate periodic enhancement features. Specifically, the attention energy score is transformed into a probability distribution using the Softmax function, and the bidirectional temporal features are weighted and summed to obtain the periodic enhancement features. The formula used is as follows:

[0092] ;

[0093] In the formula, Cf represents the periodic enhancement feature, and Time represents the total number of time points. express Attention energy score at any given moment;

[0094] Step S34: Construction of the demand intensity quantification module, used to explicitly quantify implicit path demand. Specifically, this involves learning the demand intensity of each communication path by improving the activation function to obtain path demand intensity features. The steps include:

[0095] Step S341: Feature mapping, used for dimensionality reduction and feature abstraction, specifically by compressing periodic enhancement features through a fully connected layer to obtain compressed periodic enhancement features;

[0096] Step S342: Design an improved activation function to enhance nonlinear representation capabilities. Specifically, this involves expanding the output range of the Sigmoid activation function by introducing a learnable slope parameter to obtain the improved activation function. Based on this improved activation function, the compressed periodic enhancement features of each communication path are processed to obtain the demand intensity of each communication path, forming a demand intensity vector. The formula used is as follows:

[0097] ;

[0098] In the formula, This indicates an improved activation function. This represents the compressed periodic enhancement feature of the a-th communication path. The slope parameter represents the learnable slope parameter, and DI represents the demand intensity vector. This indicates the demand intensity of the first communication path. This indicates the demand intensity for the second communication path. This indicates the demand intensity for communication path A. This represents the compressed periodic enhancement feature of the first communication path. This represents the compressed periodic enhancement feature of the second communication path. This represents the compressed periodic enhancement feature of the Ath type of communication path, where A represents the total number of communication path types.

[0099] Step S35: Construct and train the model, specifically by constructing the improved bidirectional long short-term memory network model through the multi-source fusion module, the bidirectional feature extraction module, the periodic attention module, and the demand intensity quantification module. The improved bidirectional long short-term memory network model is constructed by integrating these modules. The model is trained based on the path training set and its performance is verified based on the path test set to obtain the improved bidirectional long short-term memory network model, which serves as the network state prediction model.

[0100] By performing the above operations, this solution addresses the technical problems of traditional IoT wireless communication path optimization methods, which typically rely on preset rules or short-term historical statistics, failing to effectively integrate the dynamic interaction characteristics of network environment, node status, and traffic patterns. This results in the identification of network demand status remaining at a shallow level and lacking the ability to model long-term traffic patterns, only responding to immediate traffic while ignoring potential patterns, leading to rigid strategies that cannot adapt to dynamic network scenarios. This solution creatively adopts an improved bidirectional long short-term memory network model as the network state prediction model. It transforms implicit multi-source time-series data such as network environment, traffic patterns, and node status into explicit demand intensity indicators for different communication paths. By integrating time-series dependency analysis and periodic attention mechanisms, it adaptively learns network traffic patterns and accurately identifies the real-time demand intensity of each communication path, providing interpretable and high-precision demand input for subsequent path selection optimization.

[0101] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S4, the path selection optimization model design is used to design the model required for dynamically generating personalized path selection control strategies. Specifically, it is to construct an improved reinforcement learning model as the path selection optimization model. The improved reinforcement learning model specifically includes a state encoding module, an action constraint network, and a policy optimization module.

[0102] The path selection optimization model design specifically includes the following steps:

[0103] Step S41: Construction of the state encoding module for structured representation of decision states. Specifically, this involves obtaining a hierarchical state space by separating three layers of information: basic state, contextual state, and temporal state. The basic state represents the network environment and basic node information; the contextual state represents path demand intensity information and service quality feedback information; and the temporal state represents time period information. The construction of the state encoding module includes the following steps:

[0104] Step S411: State hierarchical encoding, used to distinguish the importance of state types, specifically by processing the information of the three states separately through independent fully connected layers to obtain three sets of state vectors, using the following formula:

[0105] ;

[0106] In the formula, Represents the basic state vector. Represents the situational state vector. Represents the time state vector. Represents the ReLU activation function. Represents the weights of the basic state mapping. This represents the bias term of the basic state mapping. Represents the context state mapping weights. This represents the context state mapping bias term. Represents the BERT model function. This indicates the input of service quality feedback data. Indicates the weights of the time-state mapping. The time state mapping bias term is represented by Hour, which represents the hour encoding vector of the current time, and DType, which represents the date type encoding vector of the current time, used to introduce the effects of weekdays, weekends, and holidays.

[0107] Step S412: State space integration, used to construct a joint state representation, specifically by concatenating the basic state vector, the context state vector, and the time state vector to obtain the integrated decision state space;

[0108] Step S42: Action constraint network design, used to ensure the network feasibility of the path selection strategy, specifically involves learning the mapping from network state to protocol boundary through a neural network to obtain the real-time feasible action range. The steps include:

[0109] Step S421: Constraint boundary prediction, used to model network physical and protocol constraint rules, specifically by processing node state data through a two-layer ReLU network and outputting six boundary parameters, including bandwidth allocation lower limit parameter, bandwidth allocation upper limit parameter, transmission rate lower limit parameter, transmission rate upper limit parameter, path hop count baseline parameter, and path reliability fluctuation range parameter.

[0110] Step S422: Constraint matrix generation, used to format action boundaries. Specifically, this involves scaling the minimum and maximum values ​​of predefined parameters using the Sigmoid activation function to obtain the constraint matrix executable by the network system. The formula used is as follows:

[0111] ;

[0112] In the formula, PC represents the constraint matrix. This represents the lower limit parameter for bandwidth allocation. This indicates the upper limit parameter for bandwidth allocation. This represents the lower limit parameter of the transmission rate. This parameter represents the upper limit of the transmission rate. Indicates the baseline parameter for path hop count. This parameter represents the range of path reliability fluctuations. Indicates the bandwidth adjustment range. Indicates the range of transmission rate adjustment. Indicates the physical minimum bandwidth. Indicates the physical minimum transmission rate;

[0113] Step S43: Reward function design to balance service quality and network performance. Specifically, this involves obtaining a composite reward function for guiding strategy optimization by weighting communication quality metrics and network resource consumption metrics. The steps include:

[0114] Step S431: Design of communication quality reward, used to quantify the satisfaction of service quality by path selection. Specifically, it calculates the end-to-end latency penalty and the logarithmic reward of throughput to obtain the communication quality reward. The formula used is as follows:

[0115] ;

[0116] In the formula, Indicates a reward for communication quality. Indicates the delayed matching weight. Indicates throughput matching weight, This indicates a delay in expected business operations. Indicates the actual end-to-end delay. Indicates the maximum permissible delay deviation. Indicates actual throughput;

[0117] Step S432: Design of network performance index reward to quantify network resource costs. Specifically, this involves calculating the negative energy consumption value and the network load balancing gain to obtain the network performance index reward. The formula used is as follows:

[0118] ;

[0119] In the formula, Indicates rewards based on network performance metrics. This represents the energy consumption penalty coefficient. This represents the load balancing gain coefficient. This indicates the energy consumption of a single data transmission. Indicates changes in the load of critical nodes;

[0120] Step S433: Calculate the composite reward, specifically by weighting and summing the communication quality reward and the network performance indicator reward to obtain the composite reward;

[0121] Step S44: Construction of the policy optimization module, used to stably learn the optimal path selection policy, specifically adopting near-end policy optimization, updating the policy under the constraints of the action constraint network, and outputting the action dimension including the allocated bandwidth, transmission rate and selected path;

[0122] Step S45: Construct and train the model. Specifically, this involves constructing an improved reinforcement learning model by integrating the state encoding module, the action constraint network design, the reward function design, and the policy optimization module. The model is then trained based on the path training set and its performance is verified based on the path test set to obtain the improved reinforcement learning model, which serves as the path selection optimization model.

[0123] By performing the above operations, this solution addresses the technical problems of traditional IoT wireless communication path optimization methods, which often employ heuristic rules or single-objective control, making it difficult to handle multi-dimensional state inputs. This leads to policies deviating from actual network physical and protocol constraints, causing network congestion, excessive energy consumption, or degraded service quality. Furthermore, single-objective optimization ignores differences in service types, resulting in unfair resource allocation and overall low efficiency. This solution creatively adopts an improved reinforcement learning model as the path selection optimization model. By integrating network infrastructure conditions, real-time demand intensity, and service context through hierarchical state coding, it constructs a dynamic space that comprehensively represents the decision-making environment. It also introduces an action constraint network, embedding network protocols and physical boundaries as learnable functions into policy generation to ensure action feasibility. By utilizing near-end policy optimization, it achieves adaptive trade-offs among multiple objectives, thereby generating personalized path control strategies that balance immediate service quality and long-term network performance.

[0124] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the IoT wireless communication path optimization specifically involves using the dataset to be processed as the input of the network state prediction model to obtain a demand intensity reference result, and combining the demand intensity reference result with the dataset to be processed as the input of the path selection optimization model to obtain an optimal path selection control strategy. The demand intensity reference result is specifically a demand intensity vector set obtained based on the input.

[0125] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0126] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

[0127] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. An artificial intelligence-based method for optimizing a wireless communication path of an Internet of Things, characterized by: The method comprises the following steps: S1: original data acquisition, through data acquisition, obtaining a path optimization original data set, the path optimization original data set specifically comprising a historical path original data set and a current path original data set; S2: original data optimization, through data optimization on the collected original data, obtaining a to-be-processed data set, a path training set and a path test set; S3: network state prediction model construction, used for constructing a model required for extracting dynamic timing features of network flow and environment and quantifying path demand intensity, specifically constructing an improved bidirectional long short-term memory network model as a network state prediction model, the improved bidirectional long short-term memory network model specifically comprising a multi-source fusion module, a bidirectional feature extraction module, a cycle attention module and a demand intensity quantification module; S4: path selection optimization model design, used for designing a model required for dynamically generating a personalized path selection control strategy, specifically constructing an improved reinforcement learning model as a path selection optimization model, the improved reinforcement learning model specifically comprising a state coding module, an action constraint network and a strategy optimization module; S5: Internet of Things wireless communication path optimization, specifically taking the to-be-processed data set as the input of the network state prediction model to obtain a demand intensity reference result, and taking the demand intensity reference result and the to-be-processed data set as the input of the path selection optimization model to obtain an optimal path selection control strategy, the demand intensity reference result specifically being a demand intensity vector set obtained based on the input. 2.The AI-based IoT wireless communication path optimization method of claim 1, wherein: The network state prediction model construction specifically comprises the following steps: Step S31: multi-source fusion module construction; Step S32: bidirectional feature extraction module construction; Step S33: cycle attention module construction; Step S34: demand intensity quantification module construction; Step S35: model construction and training. 3.The AI-based IoT wireless communication path optimization method of claim 2, wherein: The multi-source fusion module construction is used for processing multi-source data scale difference and feature incompatibility problems, specifically through a learnable gating weight to dynamically weight network environment features, flow feature data and node state features to obtain multi-source fusion features, and the steps comprise: Step S311: gating weight generation, used for adaptively allocating data importance weights, specifically generating weight ratios through linear transformation and a Sigmoid activation function to obtain fusion gating weights; Step S312: feature transformation, used for improving the expression ability of features, specifically processing enhanced network environment features, enhanced flow features and enhanced node state features through hyperbolic tangent functions after linear mapping of network environment features, flow feature data and node state features; Step S313: feature fusion calculation, used for effectively fusing multi-source information, specifically performing weighted summation on enhanced features of each data source through gating weights to obtain multi-source fusion features; The bidirectional feature extraction module construction is used for capturing long short-term network flow dependency, specifically extracting timing patterns from forward and backward directions respectively through a bidirectional long short-term memory network to obtain bidirectional timing features; The periodic attention module is constructed to enhance the periodic network traffic mode recognition capability, specifically by guiding the attention focus on the key periodic nodes through time position coding to obtain periodic reinforced features, and the steps include: Step S331: time coding generation, used to inject periodic priori knowledge, specifically by coding the 24-hour daily cycle and 168-hour weekly cycle time points through sine and cosine functions to obtain a periodic coding vector for modifying attention; Step S332: attention energy calculation, used to identify periodic sensitive moments, specifically by linearly transforming the fusion of bidirectional time sequence features and periodic coding vectors to obtain the attention energy score of each moment; Step S333: obtain periodic reinforced features, used to generate periodic reinforced features, specifically by converting the attention energy score into a probability distribution through a Softmax function, and weighting the sum of bidirectional time sequence features to obtain periodic reinforced features; The demand intensity quantification module is constructed to explicitly quantify the implicit path demand, specifically by learning the demand intensity of each communication path through an improved activation function to obtain path demand intensity features, and the steps include: Step S341: feature mapping, used to reduce and abstract features, specifically by compressing periodic reinforced features through a fully connected layer to obtain compressed periodic reinforced features; Step S342: design an improved activation function, used to enhance the non-linear representation capability, specifically by introducing a learnable slope parameter to expand the output range of the Sigmoid activation function to obtain an improved activation function, and processing the compressed periodic reinforced features of each communication path based on the improved activation function to obtain the demand intensity of each communication path, which constitutes a demand intensity vector; The model is constructed and trained, specifically by constructing the multi-source fusion module, the bidirectional feature extraction module, the periodic attention module, and the demand intensity quantification module, integrating the construction of the improved bidirectional long short-term memory network model, training the model based on the path training set, verifying the model performance based on the path test set, and obtaining the improved bidirectional long short-term memory network model as the network state prediction model. 4.The AI-based IoT wireless communication path optimization method of claim 1, wherein: The path selection optimization model is designed, specifically including the following steps: Step S41: state coding module construction; Step S42: action constraint network design; Step S43: reward function design; Step S44: strategy optimization module construction; Step S45: model construction and training. 5.The AI-based IoT wireless communication path optimization method of claim 4, wherein: The state coding module is constructed to structure the decision state, specifically by separating three layers of information, including the basic state, the context state, and the time state, to obtain a hierarchical state space, the basic state is used to represent network environment and node basic information, the context state is used to represent path demand intensity information and service quality feedback information, and the time state is used to represent time period information, and the state coding module construction includes the following steps: Step S411: state hierarchical coding, used to distinguish state type importance, specifically by processing the information of the three states through independent fully connected layers to obtain three groups of state vectors; Step S412: state space integration, for constructing a joint state representation, specifically, by concatenating the base state vector, the context state vector and the time state vector to obtain a comprehensive decision state space; The action constraint network design is used to guarantee the network feasibility of the path selection strategy, specifically, by learning the mapping from the network state to the protocol boundary through the neural network to obtain the real-time actionable interval, and the steps include: Step S421: constraint boundary prediction, for modeling the network physical and protocol limit rules, specifically, by processing the node state data through a two-layer ReLU network to output the path selection boundary parameters; Step S422: constraint matrix generation, for formatting the action boundary, specifically, by scaling the minimum and maximum values of the pre-defined parameters through the Sigmoid activation function to obtain the constraint matrix executable by the network system; The reward function design is used to balance the quality of service and network performance, specifically, by weighting the communication quality indicators and network resource consumption indicators to obtain a composite reward function guiding the optimization of the strategy; The strategy optimization module is constructed to stabilize the learning of the optimal path selection strategy, specifically, by using the proximal policy optimization to update the strategy under the constraint of the action constraint network; The model is constructed and trained, specifically, by constructing the state encoding module, designing the action constraint network, designing the reward function, and constructing the strategy optimization module, to integrate the construction of the improved reinforcement learning model, train the model based on the path training set, verify the model performance based on the path test set, and obtain the improved reinforcement learning model as the path selection optimization model. 6.The AI-based IoT wireless communication path optimization method of claim 1, wherein: The historical path original data set and the current path original data set both include network environment data, traffic feature data and node state data, and the historical path original data set further includes service quality feedback data. 7.The AI-based IoT wireless communication path optimization method of claim 1, wherein: The original data optimization specifically includes the following steps: Step S21: data cleaning, for processing missing values and correcting outliers, specifically, by filling in the gaps between sensors or network elements through time series linear interpolation, and identifying and correcting outliers through a dynamic threshold algorithm to improve data quality; Step S22: multi-source alignment processing, for solving the difference in sampling frequency of heterogeneous data, specifically, by realizing the time domain alignment of network environment data, traffic feature data and node state data through sliding window aggregation; Step S23: data normalization, for adapting to network load and scene changes, specifically, by processing the data through the minimum-maximum normalization method by time slice to eliminate the influence of network fluctuations; Step S24: data set segmentation, for segmenting the historical data set into training set and test set, specifically, by segmenting the historical path original data set into path training set and path test set; Step S25: optimizing the original data, specifically, optimizing the current path original data set through the data cleaning, the multi-source alignment processing and the data normalization to obtain a to-be-processed data set, and optimizing the historical path original data set through the data cleaning, the multi-source alignment processing, the data normalization and the data set segmentation to obtain a path training set and a path test set.

Images