کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

A Latency-Aware Hybrid Computing Architecture for Energy-Latency Optimization in Large-Scale IoT System

نویسندگان :

Amirmohammad Ahmadizad¹ Omidreza Sattari² Hossein Soleimani³

1- دانشگاه علم و صنعت ایران 2- دانشگاه علم و صنعت ایران 3- دانشگاه علم و صنعت ایران

کلمات کلیدی :

Internet of Things،edge computing،cloud computing،energy efficiency

چکیده :

Abstract— The rapid growth of Internet of Things (IoT) deployments has intensified the challenge of jointly minimizing energy consumption and latency for time-sensitive applications. This paper proposes a latency-aware hybrid IoT–Edge–Cloud computing architecture that dynamically distributes computational tasks across local devices, edge servers, and cloud resources. The proposed framework employs a lightweight and interpretable decision tree–based scheduler, enhanced with K-Means clustering and task dependency awareness, to adapt offloading decisions based on device energy levels, task characteristics, and latency constraints. A multi-tier cost model is formulated to capture the trade-offs between energy consumption and execution delay under Quality of Service (QoS) requirements. Extensive simulations conducted on a large-scale IoT network with 500 devices over 30 independent runs demonstrate that the proposed hybrid approach preserves approximately 57% of device energy while maintaining an average task latency of around 325 ms. Compared to local-only and edge-only strategies, the proposed model significantly extends network lifetime while achieving a balanced energy–latency trade-off. These results indicate that the proposed lightweight hybrid architecture is well-suited for scalable and delay-aware IoT applications.