UDP flow entry eviction strategy using q-learning in software defined networking

Software-defined networking provides a programmable and flexible way to manage the network by separating and centralizing the control plane. The data plane entities like software-defined switches and routers use flow entries in flow tables for forwarding the packets. However, the limited switch memory restricts the number of flow entries in the flow tables. This leads to flow table overflow and flow entry reinstallation problems, which severely degrade the network performance. This requires a comprehensive policy for timely eviction of inactive flow entries to avoid overflows and optimally maintain flow tables usage. To this end, many studies have been proposed, but none of them have suggested detailed eviction strategy for UDP flows. This paper proposes a UDP flow eviction strategy which periodically updates the statistical information of UDP flows through reinforcement learning and utilizes it to evict inactive UDP flows. This eviction strategy is combined with the existing TCP flow eviction method to form an eviction system that takes into account the protocol-specific characteristics of the flow. Through three traffic-based experiments, we found that the proposed system reduces the number of overflow occurrences by 27% and flow entries reinstallation by 28%, compared to the random and FIFO policies, resulting in 15% reduction in control signaling overhead.