Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 108, P. 611 - 625
Published: Aug. 10, 2024
Mobile Augmented Reality (MAR) applications enhance user experiences by providing realistic information about the current location through mobile devices. However, MAR are computationally intensive, leading to high energy consumption and latency issues. To address these challenges, this research presents a Hybrid Monte Carlo Tree Search (HMCTS) based task offloading scheme, combining genetic algorithm with tree search for efficient management. The proposed method uses YoloV7 object recognition aims reduce consumption, response time, migration time. Experimental results demonstrate that HMCTS approach significantly reduces 1290 kJ, time 24 ms, 0.52 outperforming existing techniques. These improvements highlight potential of enhancing performance applications. Proposed hybrid improve efficiency effectiveness in model dynamically offloads tasks edge servers, optimizing scheduling consumption.
Language: Английский