Self-Learning Power Control in Wireless Sensor Networks

Abstract

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay.

Intelligence at the Edge of Complex Networks: The Case of Cognitive Transmission Power Control

“…Assuming to use two alkaline AA batteries of 3000mAh @1.5V for each node corresponding to a total energy of 32400 Joule, the nodes in which the CQL-TPC is implemented can transmit for a longer period before batteries depletion. We have estimated that the lifetime of the nodes increases of several days (i.e., 14-23), without any sleeping techniques, and few months (i.e., [9][10][11][12][13][14][15][16][17] if the deep sleep mode is enabled during the idle periods. Moreover, the energy consumed by the CQL-TPC in the learning and convergence phases does not affect the battery capacity in the long term since such estimated average value of about 2 Joule and 0.38 Joule with deep sleep disabled and enabled, can be considered as a negligible value compared to the total batteries energy.…”

“…It is therefore realistic to conceive that intelligent processes should start at the network periphery, leading to new forms of decentralized machine learning. Decentralized learning opens several new avenues when it comes to cognitive wireless communications, as it allows wireless devices to directly spot communication patterns without incurring any communication overheads with base stations or other centralized points [9]. In-node learning has significant potential to evolve current communication standards towards predictionbased communications at the physical, MAC and network layers, and enabling cross-layer communication protocols for high-density, low-power, massive-scale systems.…”

“…Chincoli et al [9] have carried out exemplary work on learning-based resource management in wireless sensor networks, showing how reinforcement learning may be used in small sensors to tackle the combined problems of energy and spectrum efficiency. Q-learning can indeed be deployed in low-spec devices to iteratively predict the channel conditions through trial-and-error methods that are more viable than other optimization algorithms (Sections IV and V).…”

Edge IoT Networking

“…However, since sensors are tied up with life span due to the battery lifetime and energy, this cause a critical hurdle for such type of communication to be more spread and utilized in communication and networking [5]. Therefore, various techniques were proposed in literature to address the issues related to power consumption and life span of WSN such as [6] [7] [8]. On the other hand, WSN has faced some issues and limitations on communicating with servers and cloud due to the sensitivity of data which is intolerable of low data rate and high latency [9].…”

AN-Aided Secure Beamforming in Power-Splitting-Enabled SWIPT MIMO Heterogeneous Wireless Sensor Networks

“…Unfortunately, because SN are battery-powered, the working lifetime of the entire WSNs is limited by energy consumption due to the energy restriction at SN [4]. In order to overcome these limitation, there are many investigations on enabling technologies for energy sustainablility in WSNs [5].…”