Energy‐efficient workload allocation in fog‐cloud based services of intelligent transportation systems using a learning classifier system

Abstract

Nowadays, renewable energies have been considered as one of the important sources of energy supply in delaysensitive 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.

Stock exchange trading optimization algorithm: a human-inspired method for global optimization

“…Some human-inspired algorithms are harmony search (HS) [50], imperialist competitive algorithm (ICA) [51], teaching-learning-based optimization (TLBO) [52], league championship algorithm (LCA) [53], class topper optimization (CTO) [54], presidential election algorithm (PEA) [11], sine-cosine algorithm (SCA) [55], socio evolution & learning optimization algorithm (SELO) [56], team game algorithm (TGA) [57], ludo game-based swarm intelligence (LGSI) [58], heap-based optimizer (HBO) [15], coronavirus optimization algorithm (CVOA) [59], political optimizer (PO) [14], and Lévy flight distribution (LFD) [4]. Some algorithms are inspired by machine learning, reinforcement learning, and learning classifier systems [60][61][62]. For example, ActivO is an ensemble machine learning-based optimization algorithm [63].…”

“…Optimization plays a crucial role in various domains, like industrial applications, business, engineering, social science, and transportation [1][2][3]. A lot of problems in science and engineering are generally constraint or unconstraint optimization problems.…”

Optimized Economic Loading of Distribution Transformers Using Minimum Energy Loss Computing

“…As a future application of the proposed approach, it can be used for future smart cities where high-performance energy systems in cooperation with many other technologies must be accessible, for example, IT infrastructure [26][27][28], wireless sensor systems [29], intelligent transport systems [30][31][32], industrial developments and cyber-physical systems [33-38], and monitoring systems [39-42].…”

Enabling and Leveraging AI in the Intelligent Edge: A Review of Current Trends and Future Directions

“…Another approach considers the energy efficiency of workload deployment in fog-cloud IoV applications [157]. The algorithm uses a Learning Classifier System (specifically XCS, genetic-based machine learning), optimizing for energy use and workload delay, taking into account battery status of battery powered nodes.…”