Scalable Load Balancing scheme for wireless distributed controllers in SDDC

Abstract

In this paper, we introduce a Load Balancing (LB) system for large-scale distributed Software-Defined Networking (SDN) wireless control plane architectures. Our approach utilizes a hysteresis multiple-threshold method, employing a Continuous Time Markov Chain (CTMC) model and a control policy. This system evenly distributes excess traffic from an overloaded SDN controller (client) to lightly loaded neighboring controllers (servers). When a controller’s capacity reaches a certain threshold, indicating overload, the LB mechanism redirects incoming traffic to less burdened controllers based on a defined policy. The LB mechanism does not react immediately to load changes but rather provides scalable and dynamic capacity management, maintaining stability and ensuring efficiency. By doing so, it prevents frequent and unnecessary alterations in resource allocation. This paper extends previous work by exploring LB scenarios involving one client and up to three servers instead of configuration with one client and one server. We numerically demonstrate the effectiveness of our model through transient and steady-state analysis evaluations using performance metrics such as Average Aggregated Capacity ($AAC$), Transition Rate ($TR$) and Blocking Probability ($BP$). We particularly show how increasing the number of levels in a multi-level LB schema enhances resource allocation granularity by introducing additional layers of decision-making and distribution. Hence with more levels, the system can better distribute the workload across various tiers of servers based on their capabilities and current loads. As a result, it can achieve better resource utilization, improved performance, and enhanced scalability, ultimately leading to a more efficient and responsive LB solution.