Abstract. In this paper, we present transmission power control algorithms, based on soft computing techniques, for reducing the energy consumption in wireless sensor network, without affecting its throughput. Two algorithms are designed, one using Artificial Neural Network (ANN) and the other using Fuzzy Logic Control (FLC). The algorithms show marked improvement in performance when compared to the conventional Medium Access Control protocol standard IEEE 802.15.4. We also show the effects of optimizing the proposed methods further using Genetic Algorithm
Abstract:In battery-operated wireless sensor networks, the quality of service requirements such as throughput and energy efficiency must be stringently maintained while the least amount of energy is consumed. Since a major portion of energy is spent by the transceiver operations, transmission power control (TPC) in the medium access control (MAC) layer can bring about considerable energy efficiency. Since TPC algorithms will have a direct impact on the received signal strength index (RSSI) at the receiver, RSSI is the primary input parameter for any TPC algorithm. The objective of the proposed work is to decide on the exact value of transmission power required for the next transmission that will ensure an RSSI just above the threshold level at the receiver. Since this involves estimation of RSSI for the next transmission, we propose three state estimation techniques, namely Kalman filter (KF), extended KF (EKF), and unscented KF (UKF) to predict the RSSI accurately. This predicted value is used as an input for an artificial neural network (ANN)-based TPC algorithm. The effectiveness of the estimation techniques is verified by the prediction error. The accuracy of prediction is reflected in the TPC algorithm in terms of reduced power utilization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.