Load Balancing Selection Method and Simulation in Network Communication Based on AHP-DS Heterogeneous Network Selection Algorithm

Weiwei Xiao

doi:10.1155/2021/4239750

Abstract

This article proposes an Analytic Hierarchy Process Dempster-Shafer (AHP-DS) and similarity-based network selection algorithm for the scenario of dynamic changes in user requirements and network environment; combines machine learning with network selection and proposes a decision tree-based network selection algorithm; combines multiattribute decision-making and genetic algorithm to propose a weighted Gray Relation Analysis (GRA) and genetic algorithm-based network access decision algorithm. Firstly, the training data is obtained from the collaborative algorithm, and it is used as the training set, and the network attributes are used as the attribute set, and the continuous attributes are discretized by dichotomization, and the attribute that can make the greatest information gain is selected as the division feature, and a decision tree with strong generalization ability is finally obtained, which is used as the decision basis for network access selection. The simulation results show that the algorithm proposed in this thesis can effectively improve user service quality under three services, and the algorithm is simple and effective with low complexity. It first uses AHP-DS hierarchical analysis to establish a recursive hierarchy for the network selection problem and obtains the subjective weights of network attributes through the judgment matrix. Then, it uses a genetic algorithm to adjust the subjective weight, defines the fitness function in the genetic algorithm-based on gray correlation analysis, adjusts the weights of the selection operator, crossover operator, and variation operator in the genetic algorithm, and gets the network with the largest fitness as the target network, which can effectively improve the user service quality.

Highlights

With the rapid development of wireless network communication technology in recent years, wireless networks that comply with the new network communication standards of higher generation are continuously generated to meet the increasingly diverse needs of modern society in terms of available bandwidth, transmission rate, response latency, and usage price of the network
When users are in an environment that incorporates different wireless networks, they need to choose the right network to access or switch to obtain better network resources based on the properties of each of these wireless networks and their own needs
The in-vehicle heterogeneous network system needs to rely on the traffic mechanical and electrical systems, including traffic signals, traffic networks, roadside base stations, and access points [25,26,27]. e feasibility of the in-vehicle heterogeneous network must be established on the basis that its structure can be implemented on real traffic mechanical and electrical systems. e related feasibility needs to be reflected in the economic feasibility, structural feasibility, and service feasibility of the network system

Summary

Introduction

With the rapid development of wireless network communication technology in recent years, wireless networks that comply with the new network communication standards of higher generation are continuously generated to meet the increasingly diverse needs of modern society in terms of available bandwidth, transmission rate, response latency, and usage price of the network. The network access selection mechanism plays a key role On one hand, it determines the continuity and effectiveness of user network switching, helps users access the right network, and makes the network usage experience guaranteed. Some network access selection algorithms lack flexibility and cannot be combined with the real-time condition of network resources; how to do a good balance between the computational complexity and practical effectiveness of the algorithm; how to fully take into account the quality of service of users and the overall utilization of network resources [5]. To improve the overall effectiveness of the network and achieve efficient utilization, it is of positive significance to study the access selection mechanism of heterogeneous networks. In the more complex latter model, if the terminals still have uncontrolled decision-making power as in the above scenario of terminal-initiated network selection, it is inevitable that the network with good overall performance is used as the target access network too often (in the extreme case, all terminals select the same network), while the probability of the rest of the networks being selected is significantly smaller or even zero. e original network with better overall performance is overloaded with too many terminals, and the channel blocking rate increases reducing the experience of the end-users connected to this type of network. e remaining networks with average performance have a high probability of being idle due to the low number of terminals connected to them, and the corresponding resources are wasted, which significantly reduces the overall system performance. erefore, it is necessary to restrict the decision-making power of terminals to avoid the phenomenon of “overcooling and overheating” of the load of each network. is can be solved by using the so-called centralized network selection scheme

Current Status of Research

Analysis of Results

Findings

Conclusion