Nowadays, renewable energies have been considered as one of the important sources of energy supply in delay‐sensitive fog computations in intelligent transportation systems due to their cheapness and availability. This study addresses the challenges of using renewable power supplies in delay‐sensitive fogs and proposes an efficient workload allocation method based on a learning classifier system. The system dynamically learns the workload allocation policies between the cloud and the fog servers and then converges on the optimal allocation that fulfils the energy and delay requirements in the overall transportation system. Simulation results confirm that the proposed algorithm reduces the long‐term costs of the system including service delay and operating costs. Also, compared to some other techniques, when the proposed method presents the most successful solution for reducing the average delay of the workloads and converging on the minimum value as well as retaining or even increasing the battery levels of fog nodes up to 100%. The lowest cost of the delay is 5 among other available methods, whereas in the proposed method, this value approaches 4.5.
Energy‐efficient workload allocation in fog‐cloud based services of intelligent transportation systems using a learning classifier system
IET Intelligent Transport Systems ; 14 , 11 ; 1484-1490
2020-11-01
7 pages
Article (Journal)
Electronic Resource
English
processor scheduling , resource allocation , learning (artificial intelligence) , power aware computing , energy conservation , cloud computing , energy‐efficient workload allocation , fog‐cloud based services , intelligent transportation systems , learning classifier system , renewable energies , energy supply , delay‐sensitive fog computations , renewable power supplies , delay‐sensitive fogs , efficient workload allocation method , workload allocation policies , fog servers , optimal allocation , transportation system , system including service delay , average delay , fog nodes