Bayesian Statistical Modeling of System Energy Saving Effectiveness for MAC Protocols of Wireless Sensor Networks

Abstract

Summary. The wireless sensor network is a wireless network consisting of spatially distributed autonomous sensor devices which are called sensor nodes in remote setting to cooperatively monitor and control physical or environmental conditions. The lifetimes of sensor nodes depend on the energy availability with energy consumption. Due to the size limitation and remoteness of sensor devices after deployment, it is not able to resupply or recharge power. The system energy saving effectiveness is the probability that the wireless sensor network system can successfully meet an energy saving operational demand. To extend the system effectiveness in energy saving, the lifetimes of sensor nodes must be increased by making them energy efficient as possible. In this paper, we propose Bayesian statistical models for observed active and sleep times data of sensor nodes under the selected energy efficient CSMA contention-based MAC protocols in consideration of the system effectiveness in energy saving in a wireless sensor network. Accordingly, we propose Bayes estimators for the system energy saving effectiveness of the wireless sensor networks by use of the Bayesian method under the conjugate prior information.

Machine Learning in Wireless Sensor Networks: Algorithms, Strategies, and Applications

“…In this subsection, the major supervised learning algorithms are discussed in the context of WSNs. In fact, supervised learning algorithms are extensively used to solve several challenges in WSNs such as localization and objects targeting (e.g., [21], [22], [23]), event detection and query processing (e.g., [24], [25], [26], [27]), media access control (e.g., [28], [29], [30]), security and intrusion detection (e.g., [31], [32], [33], [34]), and quality of service (QoS), data integrity and fault detection (e.g., [35], [36], [37]).…”

“…1) Bayesian statistical model for MAC: Kim and Park [28] presented a contention-based MAC protocol for managing active and sleep times in WSNs. Instead of continuously sensing the medium, this scheme utilizes a Bayesian statistical model to learn when the channel can be allocated, and hence save network energy.…”

A Survey on Machine Learning-Based Performance Improvement of Wireless Networks: PHY, MAC and Network Layer

“…For example, predict the location of a mobile node using an algorithm that is trained on signal propagation characteristics (inputs) at known locations (outputs). Various challenges in wireless networks have been addressed using supervised learning such as: medium access control [30][31][32][33], routing [34], link quality estimation [35,36], node clustering in WSN [37], localization [38][39][40], adding reasoning capabilities for cognitive radios [41][42][43][44][45][46][47], etc. Supervised learning has also been extensively applied to different types of wireless networks application such as: human activity recognition [48][49][50][51][52][53], event detection [54][55][56][57][58], electricity load monitoring [59,60], security [61][62][63], etc.…”

Data-Driven Design of Intelligent Wireless Networks: An Overview and Tutorial

“…For example, predict the location of a mobile node using an algorithm that is trained on signal propagation characteristics (inputs) at known locations (outputs). Various challenges in wireless networks have been addressed using supervised learning such as: medium access control [ 29 , 42 , 43 , 44 ], routing [ 45 ], link quality estimation [ 46 , 47 ], node clustering in WSN [ 48 ], localization [ 49 , 50 , 51 ], adding reasoning capabilities for cognitive radios [ 36 , 37 , 52 , 53 , 54 , 55 , 56 ], etc . Supervised learning has also been extensively applied to different types of wireless networks application such as: human activity recognition [ 21 , 39 , 57 , 58 , 59 , 60 ], event detection [ 61 , 62 , 63 , 64 , 65 ], electricity load monitoring [ 66 , 67 ], security [ 68 , 69 , 70 ], etc .…”