My current research interests are in the physical layer design aspects for the next generation wireless communication systems. In my recent efforts, I have focused on the design of energy harvesting (EH) communications systems, application of machine learning and artificial intelligence to the design of wireless communication systems, and resource allocation in wireless networks.
The advent of energy harvesting (EH) technology represents a paradigm shift in the design of communication systems, by enabling the nodes to harvest energy from environmental source, e.g., the sun, the wind, heat, and etc. This presents a tantalizing possibility of perpetual operation. However, typically the harvested energy is sporadic and random in nature. The fundamental energy conservation principle mandates that, at any time instant, the amount of energy an EH node can use is limited by the energy available in its battery. This call for development of new energy management schemes. Our research efforts in this direction are summarized here.
The next generation wireless networks will heavily rely on machine learning and artificial intelligence for optimizing their performance. The data-driven optimization techniques, such as deep learning and reinforcement learning, could be used to solve the problems for which accurate mathematical models are not available, or the problems which are intractable to solve, even numerically. Our recent contributions in this direction can be found here.