Game Theory based Resource Identification Scheme for Wireless Sensor Networks

Abstract

In modern world of sensing and distributive systems, traditional Wireless Sensor Networks (WSN) has to deal with new challenges, such as multiple application requirements, dynamic and heterogeneous networks. Senor nodes in WSN are resource constrained in terms of energy, communication range, bandwidth, processing delay and memory. Numerous solutions are proposed to optimize the performance and to increase the lifetime of WSN by introducing new resource management principles. Effective and intelligent resource management in WSN involves in resource identification, resource scheduling, and resource utilization. This paper proposes a Bayesian Game Model (BGM) approach to efficiently identify the best node with the maximum resource in WSN for data transmission, considering energy, bandwidth, and computational delay. The scheme operates as follows: (1) Sensor nodes information such as residual energy, available bandwidth, and node ID, etc., is gathered (2) Energy and bandwidth of each node are used to generate the payoff matrix (3) Implementation of node identification scheme is based on payoff matrix, utilities assigned, strategies and reputation of each node (4) Find Bayesian Nash Equilibrium condition using Starring algorithm (5) Solving the Bayesian Nash Equilibrium using Law of Total Probability and identifying the best node with maximum resources (6) Adding/Subtracting reward (reputation factor) to winner/looser node. Simulation results show that the performance of the proposed Bayesian game model approach for resource identification in WSN is better as compared with the Efficient Neighbour Discovery Scheme for Mobile WSN (ENDWSN). The results indicate that the proposed scheme has up to 12% more resource identification accuracy rate, 10% increase in the average number of efficient resources discovered and 8% less computational delay as compared to ENDWSN.

Artificial Intelligence-Enabled Game-Based Learning and Quality of Experience: A Novel and Secure Framework (B-AIQoE)

“…The technology stimulates outside and real-time data analysis, which is usually related to the domain of machine learning (ML). AI is sub-divided into two parts, ML and deep learning (DL) [2,3]. ML, on the other hand, is divided into three sub-domains: (i) supervised learning, (ii) unsupervised learning, and (iii) semi-supervised learning.…”