Improvement of Integrated Wireless Networks by Markov Games
Subject Areas : مهندسی برق و کامپیوترPayam Porkar Rezaeiye 1 , Hamid Shokrzadeh 2 , Dehghan Mehdi 3 , Amir Masoud Rahmani 4
1 - Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 -
3 - Department of Computer Engineering, Amirkabir University, Tehran, Iran
4 - Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
Keywords: Integrated local networks, Li-Fi network, Wi-Fi network, access points and load balancing,
Abstract :
Nowadays integrated wireless networks have become very important. Among the important technologies in this field is the combined technology of visible light and radio frequency communications, an important example of which is the combination of Wi-Fi and Li-Fi local networks. This combination covers the weaknesses and strengthens the strengths of the local wireless network.
Also, an issue that can increase productivity in the network is load balancing, especially when the presence of access points from both networks will lead to more choices. In fact, in the proposed access point selection algorithm in this research, it has been done in such a way that when being at an access point, the decision to choose the location is based on the balance between the factors in the Markov game based on the strategic behavior of objects. In this way, network delay will be reduced and load balance will be increased.
Therefore, a dynamic method has been proposed, which can be used to make decisions according to the conditions at any time, especially when the topology changes in the network. The proposed method has advantages such as dynamic selection of access points according to network conditions, direct feedback on the efficiency of the network and shared channel, intelligence and learning towards changes to select points, interaction with similar agents in nodes, and reducing the probability of congestion at each access point. Also, with the increase in user traffic, which leads to congested conditions and the possibility of congestion in nodes and access points, this method helps more in terms of load balancing and reducing the level of congestion. So that its difference with compared methods that use more stable techniques such as fuzzy method increases significantly.
According to the obtained results, this method has been able to improve the efficiency of the local network by more than 10% compared to the previous methods such as the fuzzy method and more than 30% compared to the SSS selection policy in high traffic load conditions.