RT info:eu-repo/semantics/conferenceObject
T1 Deep Reinforcement Learning Applied to Computation Offloading of Vehicular Applications: A Comparison
A1 Ferens Michalek, Mieszko Jan
A1 Hortelano Haro, Diego
A1 Miguel Jiménez, Ignacio de
A1 Durán Barroso, Ramón José
A1 Aguado Manzano, Juan Carlos
A1 Ruiz Pérez, Lidia
A1 Merayo Álvarez, Noemí
A1 Fernández Reguero, Patricia
A1 Lorenzo Toledo, Rubén Mateo
A1 Abril Domingo, Evaristo José
K1 Deep Reinforcement Learning
K1 Vehicular Applications
K1 Computation Offloading
K1 Edge Computing
AB An observable trend in recent years is the increasing demand for more complex services designed to be used with portable or automotive embedded devices. The problem is that these devices may lack the computational resources necessary to comply with service requirements. To solve it, cloud and edge computing, and in particular, the recent multi-access edge computing (MEC) paradigm, have been proposed. By offloading the processing of computational tasks from devices or vehicles to an external network, a larger amount of computational resources, placed in different locations, becomes accessible. However, this in turn creates the issue of deciding where each task should be executed. In this paper, we model the problem of computation offloading of vehicular applications to solve it using deep reinforcement learning (DRL) and evaluate the performance of different DRL algorithms and heuristics, showing the advantages of the former methods. Moreover, the impact of two scheduling techniques in computing nodes and two reward strategies in the DRL methods are also analyzed and discussed.
PB Institute of Electrical and Electronics Engineers (IEEE)
YR 2022
FD 2022
LK https://uvadoc.uva.es/handle/10324/62366
UL https://uvadoc.uva.es/handle/10324/62366
LA eng
NO 2022 International Balkan Conference on Communications and Networking (BalkanCom), Sarajevo, Bosnia and Herzegovina, 2022, pp. 31-35
NO Producción Científica
DS UVaDOC
RD 16-jun-2024