TECoSA Seminar – Learning Optimal Edge Processing with Offloading and Energy Harvesting

We aim to bring you a TECoSA Seminar on the first Thursday of each month during term-time.  All are welcome to attend and we look forward to some lively discussions. Members can accept the Outlook invitations, non-members can email tecosa-admin@kth.se to register.

Our guest speaker for November is Francesco De Pellegrini, Professor of networking and AI at the University of Avignon, France.  The seminar will take place via Zoom (https://kth-se.zoom.us/j/66857695267).

ABSTRACT:  Modern portable devices can execute increasingly sophisticated AI models on sensed data. The complexity of such processing tasks is data-dependent and has relevant energy cost. This work develops an Age of Information markovian model for a system where multiple battery-operated devices perform data processing and energy harvesting in parallel. Part of their computational burden is offloaded to an edge server which polls devices at given rate. The structural properties of an optimal policy for a single device-server system are derived. They permit to define a new model-free reinforcement learning method specialized for monotone policies, namely Ordered Q-Learning, providing a fast procedure to learn the optimal policy. The method is oblivious to the devices’ battery capacities, the cost and the value of data batch processing and to the dynamics of the energy harvesting process. Finally, the polling strategy of the server is optimized by combining this policy improvement technique with stochastic approximation methods. Extensive numerical results provide insight into the system properties and demonstrate that the proposed learning algorithms outperform existing baselines.

BIO: Francesco De Pellegrini received the MSc 2000, and the Ph.D. 2004, in Information Engineering at the University of Padova, Italy. He is currently full professor at the University of Avignon, where he teaches networking and artificial intelligence  He has published 100+ papers in major conferences and journals of computer science, networking and control theory. He applies algorithms on graphs, stochastic and control, and game theory for the design and perfomance evaluation of wireless and wired networked systems. He has co-authored two best papers, published in WiOPT 2014 and at NetGCoop 2016. His current H-index (Google) is 30 with 7000+ citations. He is anassociated editor for TNSE. He has been general co-chair of IEEE NETGCOOP 2012 and IEEE WIOPT2022, and TPC Co-Chair of IEEE NETGCOOP 2014, IEEE WIOPT 2018 and ITC 2021.