Internet of Things-Centric Optimized Service Provisioning in Multi-Cloud Environment

Due to the rapid growth of IoT and smart city applications the need for low-latency efficient service provisioning in distributed systems has grown substantially. Conventional cloud-centric architectures which rely on centralized processing tend to introduce significant latency that makes them ill-suited for real-time IoT workloads. This work addresses the challenge of service placement and resource allocation for IoT applications operating across multi cloud and fog computing infrastructures. Achieving satisfactory Quality of Service (QoS) requires simultaneous consideration of latency, bandwidth and resource utilization. Current single cloud and statically configured deployment strategies struggle with scalability and responsiveness in dynamic IoT scenarios. There is a clear need for adaptive intelligent frameworks capable of handling fluctuating workloads and heterogeneous resource availability. To address task placement, this work introduces a lightweight, QoS-aware service placement algorithm that evaluates latency, bandwidth, and node load in real time. Fog-layer task scheduling is handled through an enhanced weighted fair queuing (EWFQ) mechanism that incorporates user-defined priorities and live feedback signals. A weighted Q-learning algorithm (WQLA) is further introduced to refine placement decisions by learning from interactions with the deployment environment across multi-cloud and fog nodes. Simulation results confirm that the proposed approach yields reduced latency and more consistent wait times relative to heuristic and genetic baselines. Energy efficiency and service availability are also sustained under varying load conditions. The combined, adaptive framework delivers a practical and scalable method for IoT service provisioning in multi-cloud environment, advancing the groundwork for future work in context-sensitive, secure, and scalable resource management.