QoS-Aware Load Balancing in the Computing Continuum via Multi-Player Bandits

As computation shifts from the cloud to the edge to reduce processing latency and network traffic, the resulting Computing Continuum (CC) creates a dynamic environment where it is challenging to meet strict Quality of Service (QoS) requirements and avoid service instance overload. Existing methods often prioritize global metrics, overlooking per-client QoS, which is crucial for latency-sensitive and reliability-critical applications. We propose QEdgeProxy, a decentralized QoS-aware load balancer that acts as a proxy between IoT devices and service instances in CC. We formulate the load balancing problem as a Multi-Player Multi-Armed Bandit (MP-MAB) with heterogeneous rewards, where each load balancer autonomously selects service instances that maximize the probability of meeting its clients' QoS targets by using Kernel Density Estimation (KDE) to estimate QoS success probabilities. It also incorporates an adaptive exploration mechanism to recover rapidly from performance shifts and non-stationary conditions. We present a Kubernetes-native QEdgeProxy implementation and evaluate it on an emulated CC testbed deployed on a K3s cluster with realistic network conditions and a latency-sensitive edge-AI workload. Results show that QEdgeProxy significantly outperforms proximity-based and reinforcement-learning baselines in per-client QoS satisfaction, while adapting effectively to load surges and instance availability changes.