CoSIPR: Shared Service Orchestration with Dynamic Interest Coalitions in Edge Computing

Abstract

Resource-intensive mobile edge computing (MEC) services are often provisioned on a per-request basis, resulting in repeated activation of equivalent service instances and redundant transmission of the same category-level state over overlapping inter-station links. Existing approaches rarely integrate demand aggregation, shared-instance provisioning, and reusable multi-target state distribution into a unified orchestration workflow. This paper proposes Coalition-based Shared Instance Provisioning and Routing (CoSIPR), a shared-service orchestration framework built around dynamic interest coalitions. CoSIPR predicts user requests and mobility, projects predicted locations onto the road network, filters unreliable or infeasible requests, and groups nearby users requesting the same service category. For each coalition, a marginal-gain-based candidate-reduction method and variable neighborhood search determine the serving stations, user assignments, and shared-instance counts. The selected stations then form the target set for a load-aware routing procedure that selects an existing state source and uses path-fusion reinforcement learning (PF-RL) to construct routes that reuse path segments across multiple targets. Experiments using real-world mobility and road-network data show that CoSIPR improves service-category matching, request satisfaction, and the average number of accepted requests per instance. It also reduces aggregate state-transfer cost and limits hotspot exposure while maintaining a controlled trade-off between end-to-end delay and state-transfer cost. These results demonstrate that dynamic interest coalitions and reusable multi-target paths can improve the efficiency of shared-service orchestration in MEC.