摘要 : Industrial systems usually draw huge energy to run various machines. The amount of energy requirement has again increased due to the automation of the industrial plants to make them Industry 4.0 compliant. As a result, demand of e... 展开 Industrial systems usually draw huge energy to run various machines. The amount of energy requirement has again increased due to the automation of the industrial plants to make them Industry 4.0 compliant. As a result, demand of energy is on the rise in almost all manufacturing and industrial plants. The necessity of critical and smart manufacturing processes in Industry 4.0 and its increased energy requirements force us to look for energy efficient techniques for running the deployed computing systems, which are often embedded and integrated within larger machines and have to function under time constraints. Computational efficiency of these real-time embedded systems (RTESs) depends solely on the timely completion of tasks. Task execution with less energy consumption within critical timing constraints is a challenging issue for the designers of RTESs. Thus, task scheduling in these systems require sophisticated energy efficient mechanisms. However, energy efficiency and timeliness are two mutually contradictory objectives, since the former is achieved only with a significant compromise of the later. In this paper, we propose a novel approach, based on the popular multi-objective evolutionary algorithm, Non-dominated sorting genetic algorithm-II, to solve this problem. Moreover, in RTESs, precise prediction of timing constraints is difficult before runtime which causes a form of imprecision or uncertainty in the system. Therefore, we use type-2 fuzzy sets (T2 FSs) to model the timing constraints in RTESs and introduce novel algorithms for membership function generation and calculation of fuzzy earliness. Numerical as well as real-life examples are included to demonstrate our proposed technique. 收起