ARTICLE IN PRESS JID: CAEE [m3Gsc;February 28, 2018;11:42] Computers and Electrical Engineering 000 (2018) 1–15 Contents lists available at ScienceDirect Computers and Electrical Engineering journal homepage: www.elsevier.com/locate/compeleceng An Integer Linear Programming model and Adaptive Genetic Algorithm approach to minimize energy consumption of Cloud computing data centers  Huda Ibrahim, Raafat O. Aburukba * , Khaled El-Fakih Department of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, UAE a r t i c l e i n f o Article history: Received 30 June 2017 Revised 17 February 2018 Accepted 19 February 2018 Available online xxx Keywords: Cloud computing Task scheduling Optimization Integer Linear Programming Energy consumption Genetic algorithm Cloud data centers a b s t r a c t Cloud computing infrastructures are designed to support the accessibility and availability of various services to consumers over the Internet. Data centers hosting Cloud applications consume massive amount of power, contributing to high carbon footprints to the envi- ronment. Hence, solutions are needed to minimize the energy consumption. This paper focuses on the development of a dynamic task scheduling algorithm by proposing an In- teger Linear Programming (ILP) model that minimizes the energy consumption in a Cloud data center. Furthermore, an Adaptive Genetic Algorithm (GA) is proposed to reflect the dynamic nature of the Cloud environment and to provide a near optimal scheduling so- lution that minimizes the energy consumption. The proposed adaptive GA is validated by simulating the Cloud infrastructure and conducting a set of performance and quality evalu- ation study in this environment. The results demonstrate that the proposed solution offers performance gains with regards to response time and in reducing energy consumption. © 2018 Elsevier Ltd. All rights reserved. 1. Introduction Cloud computing has been emerging as a successful paradigm for providing computing services to consumers. The avail- ability of low cost computers, servers, storage devices, and high capacity networks motivated Cloud providers to expose underutilized resources as a utility to consumers over the Internet in a pay as you go manner. Those Cloud providers ensure the ultimate use of the delivered services while guaranteeing high quality of service and customer satisfaction. The work in [1] showed that up to 20% savings can be achieved on the energy consumptions of data centers. These savings lead to an additional 30% saving on cooling energy requirements. Cloud computing makes use of the virtualization technology to achieve better resource utilization and gives the ability to dynamically consolidate Virtual Machines (VM) and live VM migration over the compute resources. Some techniques such as demand projection, heat management and temperature-aware allocation, dynamic power management by shutting servers down when they are not in use, Dynamic Voltage and Frequency Scaling (DVFS) to minimize the power level of physical compute resources, load balancing and task scheduling were reported in the literature to minimize the energy consumption in Cloud environments [2,3]. This work focuses on the allocation of Cloud consumers’ requests to the capable resources within the Cloud data cen- ter at a specific time, where the consumers’ requirements are met and the overall power consumption over time is mini-  Reviews processed and recommended for publication to the Editor-in-Chief by Associate Editor Dr. Hong Shen. * Corresponding author. E-mail address: raburukba@aus.edu (R.O. Aburukba). https://doi.org/10.1016/j.compeleceng.2018.02.028 0045-7906/© 2018 Elsevier Ltd. All rights reserved. Please cite this article as: H. Ibrahim et al., An Integer Linear Programming model and Adaptive Genetic Algorithm ap- proach to minimize energy consumption of Cloud computing data centers, Computers and Electrical Engineering (2018), https://doi.org/10.1016/j.compeleceng.2018.02.028