Design and Comparison of Reward Functions in Reinforcement Learning for Energy Management of Sensor Nodes

TL;DR

This paper investigates how different reward functions in reinforcement learning affect energy management in sensor nodes, proposing new functions that balance energy consumption and performance, leading to improved adaptation and reduced learning time.

Contribution

It explores five reward functions for energy management in sensor nodes and introduces two novel functions that improve performance balancing and learning efficiency.

Findings

Reward functions significantly influence energy consumption outcomes.

Proposed reward functions adapt node performance based on battery level.

New functions reduce learning time and improve energy-performance trade-offs.

Abstract

Interest in remote monitoring has grown thanks to recent advancements in Internet-of-Things (IoT) paradigms. New applications have emerged, using small devices called sensor nodes capable of collecting data from the environment and processing it. However, more and more data are processed and transmitted with longer operational periods. At the same, the battery technologies have not improved fast enough to cope with these increasing needs. This makes the energy consumption issue increasingly challenging and thus, miniaturized energy harvesting devices have emerged to complement traditional energy sources. Nevertheless, the harvested energy fluctuates significantly during the node operation, increasing uncertainty in actually available energy resources. Recently, approaches in energy management have been developed, in particular using reinforcement learning approaches. However, in reinforcement learning, the algorithm's performance relies greatly on the reward function. In this paper, we present two contributions. First, we explore five different reward functions to identify the most suitable variables to use in such functions to obtain the desired behaviour. Experiments were conducted using the Q-learning algorithm to adjust the energy consumption depending on the energy harvested. Results with the five reward functions illustrate how the choice thereof impacts the energy consumption of the node. Secondly, we propose two additional reward functions able to find the compromise between energy consumption and a node performance using a non-fixed balancing parameter. Our simulation results show that the proposed reward functions adjust the node's performance depending on the battery level and reduce the learning time.