A High-Throughput Energy-Efficient Passive Optical Network with Multiple Planes

Datacenter applications impose heavy demands on bandwidth and generate different communication patterns. Supporting such traffic demands leads to networks built with exorbitant facility costs and formidable power consumption if conventional design is followed. In this thesis, we propose a novel high-throughput datacenter network that leverages passive optical technologies to efficiently support communications with mixed traffic patterns. Our network enables a dynamic traffic allocation that caters to diverse communication. Specifically, our proposed network consists of two optical planes, each optimized for specific traffic patterns. We compare the proposed network with its counterparts and highlight its benefits in terms of facility costs and power consumption. To avoid collisions, a high-efficiency distributed protocol is designed to dynamically distribute traffic. Moreover, we formulate the scheduling process as a programming problem and design three greedy heuristic algorithms. Finally, simulation results show our scheme outperforms the previous POXN in terms of throughput and mean packet delay.