Reliable Scheduling Algorithm for Space Debris Monitoring Resources Using Adaptive Multipopulation Differential Evolutionary Optimization With Reinforcement Learning

Article Computer Science, Hardware & Architecture

Task scheduling, resource provisioning, and load balancing on scientific workflows using parallel SARSA reinforcement learning agents and genetic algorithm

Ali Asghari et al.

Summary: Cloud computing is a popular distributed environment with resource management being a major challenge for scientific workflows. This study utilizes state-action-reward-state-action learning and genetic algorithm to manage cloud resources, achieving the goals of reducing makespan, enhancing resource utilization, and improving load balancing.

JOURNAL OF SUPERCOMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

An improved adaptive genetic algorithm based on DV-Hop for locating nodes in wireless sensor networks

Aijia Ouyang et al.

Summary: This study introduces an improved adaptive genetic algorithm (IAGA) to address the localization problem of unknown nodes in wireless sensor networks (WSN), and experimental results demonstrate its superiority, indicating the potential of meta-heuristic algorithms in this issue.

NEUROCOMPUTING (2021)

Add to Collection

Article Robotics

Low-cost and high-performance visual guidance and navigation system for space debris removal

Shinichi Kimura et al.

Summary: A highly intelligent visual guidance navigation system was developed in this study to autonomously identify target space debris and realize a controlled rendezvous maneuver. The system integrates autonomous control software technologies and commercial off-the-shelf (COTS) devices, demonstrating orbital performance during an Astroscale demonstration mission. Collaboration with the Tokyo University of Science led to the development of a visual guidance and navigation system for space debris removal.

ADVANCED ROBOTICS (2021)

Add to Collection

Article Computer Science, Software Engineering

Polynomial analogy-based software development effort estimation using combined particle swarm optimization and simulated annealing

Zahra Shahpar et al.

Summary: Effort estimation for software projects is crucial for their success or failure. The proposed polynomial version of analogy-based estimation (PABE) method optimizes controllable parameters and utilizes a polynomial equation for effort estimation. Experimental results show the superiority of the PABE model in terms of accuracy and efficiency compared to other techniques.

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence