Joint Optimization of Controller Placement and Switch Assignment in SDN-based LEO Satellite Networks

TL;DR

This work tackles joint controller placement and switch assignment (CPSA) in SDN-based LEO satellite networks under dynamic topology and traffic. It formulates CPSA as an NP-hard integer nonlinear program and solves it with a prior population-based genetic algorithm that links adjacent time slots to account for migration, switch reassignment, and synchronization costs. A traffic model, queuing-delay model, and a three-term objective minimize $w_1\\Delta B^t + w_2\\Psi^t + w_3 M^t$, with extensive simulations showing improved load balancing and reduced migration and reassignment costs while maintaining competitive delays. The approach provides a practical, continuous-optimization framework for dynamic SDN control in LEO constellations and yields actionable insights on the effects of controller count and objective weights.

Abstract

Software-defined networking (SDN) based low earth orbit (LEO) satellite networks leverage the SDN's benefits of the separation of data plane and control plane, control plane programmability, and centralized control to alleviate the problem of inefficient resource management under traditional network architectures. The most fundamental issue in SDN-based LEO satellite networks is how to place controllers and assign switches. Their outcome directly affects the performance of the network. However, most existing strategies can not sensibly and dynamically adjust the controller location and controller-switch mapping according to the topology variation and traffic undulation of the LEO satellite network meanwhile. In this paper, based on the dynamic placement dynamic assignment scheme, we first formulate the controller placement and switch assignment (CPSA) problem in the LEO satellite networks, which is an integer nonlinear programming problem. Then, a prior population-based genetic algorithm is proposed to solve it. Some individuals of the final generation of the algorithm for the current time slot are used as the prior population of the next time slot, thus stringing together the algorithms of adjacent time slots for successive optimization. Finally, we obtain the near-optimal solution for each time slot. Extensive experiments demonstrate that our algorithm can adapt to the network topology changes and traffic surges, and outperform some existing CPSA strategies in the LEO satellite networks.

Figures (16)

• Figure 1: Controller placement and switch assignment strategies of two adjacent time slots.
• Figure 2: SDN-based LEO satellite networks architecture.
• Figure 3: Maximum number of Internet users per region, divided by $10^6$.
• Figure 4: An example of switch $s_n$ sending a request to controller $c_k$ and receiving a response.
• Figure 5: Continuous optimization process of the proposed algorithm.