Dynamic power management (DPM) refers to strategies which selectively change the operational states of a device during runtime to reduce the power consumption based on the past usage pattern, the current workload, and the given performance constraint. The power management problem becomes more challenging when the workload exhibits nonstationary behavior which may degrade the performance of any single or static DPM policy.This article presents a reinforcement learning (RL)-based DPM technique for optimal selection of timeout values in the different device states. Each timeout period determines how long the device will remain in a particular state before the transition decision is taken. The timeout selection is based on workload estimates derived from a Multilayer Artificial Neural Network (ML-ANN) and an objective function given by weighted performance and power parameters. Our DPM approach is further able to adapt the powerperformance weights online to meet user-specified power and performance constraints, respectively. We have completely implemented our DPM algorithm on our embedded traffic surveillance platform and performed long-term experiments using real traffic data to demonstrate the effectiveness of the DPM. Our results show that the proposed learning algorithm not only adequately explores the power-performance trade-off with nonstationary workload but can also successfully perform online adjustment of the trade-off parameter in order to meet the user-specified constraint. ACM Reference Format: U. A. Khan and B. Rinner. 2014. Online learning of timeout policies for dynamic power management. ACM Trans. Embedd. Comput.
The technological advancements in wireless communication and miniaturization of sensor nodes have resulted in the development of Wireless Medical Sensor Networks (WMSNs) which can be effectively used for remote patient monitoring. Remote patient monitoring is one such application of wireless sensor networks which is becoming increasingly prevalent in healthcare. The healthcare applications of the WMSNs are delay-sensitive and require timely delivery of patient-critical data. However, the frequent exchange of critical data packets results in higher delays, collisions, packet drop, and re-transmissions. Consequently, it brings a detrimental impact on the performance of the WMSNs. In addition, the implanted biomedical sensor nodes produce electromagnetic radiations, pose a serious threat of damaging sensitive tissues in the human body. Protecting tissue damage requires thermal-aware routing protocols. However, most of the thermal-aware routing protocols developed for the WBSNs primarily focused on minimizing temperature, while overlooking the energy conservation goal and optimization of route selection. In this paper, we propose a weighted, QoS-based, energy and temperature-aware routing protocol, referred to as (WETRP), for the WMSNs that utilizes a composite routing metric by keeping in view temperature, remaining node energy, and link-delay estimation during route selection decisions. The simulation results presented in the paper demonstrates the efficacy of the proposed scheme in terms of preventing temperature rise, dealing with hotspot nodes, and maximizing network's lifetime. INDEX TERMS Wireless body sensor network, routing protocols, QoS, energy efficiency, temperature, hotspot nodes.
Wireless Body Sensor Networks (WBSNs) are becoming increasing popular in a number of healthcare applications. A particular requirement of WBSNs in a healthcare system is the transmission of time-sensitive and critical data, captured by heterogeneous biosensors, to a base station while considering the constraints of reliability, throughput, delay and link quality. However, the simultaneous communication among various biosensors also raises the possibility of congestion on nodes or transmission links. Consequently, the likelihood of a number of untoward situations increases, such as disruption (high delays), packet losses, retransmissions, bandwidth exhaustion, and insufficient buffer space. The significant level of interference in the network leads to a higher number of collisions and retransmissions. The selection of an optimized route to cope with these issues and satisfy the QoS requirements of a WBSN has not been well-studied in the relevant literature. In this regard, we propose a multi-constraint, Intra-BAN, QoS-Aware Routing Protocol (referred to as MIQoS-RP) which introduces an improved, multi-facet routing metric to optimize the route selection while satisfying the aforementioned constraints. The performance of the proposed protocol is evaluated in terms of average end-to-end delay, throughput and packet drop ratio. The comparison of MIQoS-RP with the existing routing protocols demonstrates its efficacy in terms of the selected criteria. The results show that the MIQoS-RP achieves improved throughput by 22%, average end-to-end delay by 29% and packet drop ratio performance by 41% as compares to existing schemes.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.