A Learning Theoretic Approach to Energy Harvesting Communication System Optimization

A point-to-point wireless communication system in the presence of an energy harvesting device and a rechargeable battery at the transmitter is considered. Both the energy and the data arrivals at the transmitter are modeled as Markov processes. Delay-limited communication is considered assuming that the underlying channel is block fading with memory and the channel state information is available at the transmitter. The problem of maximizing the expected total data transmitted during the transmitter's lifetime is studied under three different sets of assumptions regarding the information about the underlying stochastic processes, available at the transmitter. A learning theoretic approach is introduced, which does not consider any a priori information on the Markov processes governing the communication system. In addition, online and offline optimization problems are studied for the same setup assuming full statistical knowledge and causal information on the realizations, and non-causal knowledge in the realizations of the stochastic processes, respectively. Comparing the optimal solutions in all three frameworks the performance loss due to the lack of transmitter's information regarding the behaviors of the underlying Markov processes is identified. Numerical results are presented to corroborate our theoretical findings.