A Review of Task Offloading Algorithms with Deep Reinforcement Learning.
Publication Date: 23/08/2024
Author(s): Ahmad Umar Labdo, Ajay Singh Dhabariya, Zainab Mukhtar Sani, Musa Abubakar Abbayero.
Volume/Issue: Volume 7 , Issue 3 (2024)
Abstract:
Enormous data generated by IoT devices are handled in processing and storage by edge computing, a paradigm that allows tasks to be processed outside host devices. Task offloading is the movement of tasks from IoT devices to an edge or cloud server –where resources and processing capabilities are abundant– for processing, it is an important aspect of edge computing. This paper reviewed some algorithms of task offloading and the techniques used by each algorithm. Existing algorithms focus on either latency, load, cost, energy or delay, the deep reinforcement phase of a task offloading algorithm automates and optimizes the offloading decision process, it trains agents and defines rewards. Latency-aware phase then proceeds to obtain the best offload destination in other to significantly reduce the latency.
Keywords:
Edge, Fog, Round-trip, Cloud.
