Smart and fuzzy approach based on CSP for cloud resources allocation

ABSTRACT

In this study, we proposed a resource allocation approach that aims at fulfilling two main objectives. First, it equilibrates between the different cloud infrastructure particularities including load balancing, so it enhances the performance of infrastructure. Second, our approach provides a solution for the customer needs through shortening the execution time and reducing payments of the requested resources that have a dynamic nature. This paper suggests a new hybrid resources allocation approach based on three methods: multiagent system (MAS), distributed constraints satisfaction problems (DCSP), and the fuzzy logic (FL). The MAS represents the physical infrastructure. It provides an efficient management of the resources in the distribution and the heterogeneity of this infrastructure. DCSP, on the other hand, works side by side with MAS to maintain resources allocation policies in datacenters, while the FL is used to facilitate the representation of the dynamic resource values into linguistic terms (low, medium, high  …) and helps the system to determine the best solution according to the criteria of customer requests. The experimental results show the efficiency of our approach in terms of load balancing, energy consumption cost, execution time, and the rate payment gain of customers.

KEYWORDS:

• Cloud computing
• distributed constraints satisfaction problems
• fuzzy logic
• multiagent system
• resources allocation

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Abdallah Almutawakel

Almutawakel Abdallah graduated from the Department of Computer Science University of Mohamed Khider Biskra, Biskra (Algeria) in 2010. He received a Magister degree from the same university in 2015. Currently, he is a PhD student at the same university. He is a member of the LINFI laboratory at the Department of Computer Science, University of Mohamed Khider Biskra, Biskra (Algeria). His research interests concern cloud computing, Internet of things, and optimization techniques.

Okba Kazar

Okba Kazar obtained his magister degree in 1997 from the Constantine University (Algeria) by working on artificial intelligence field. He obtained his PhD degree from the same university in 2005. He is member of editorial board of some Journals. He published more than 230 papers in international journals and communication in international conference. He participate as a session chair in international conferences, and he also published a book ‘ Manual d’Intelligence artificielle ’ of five chapters. His main research field is artificial intelligence, and he is interested in the multiagents systems and their applications, PHM in medical and industrial fields, ERP, advanced information systems, Web services, semantic Web, bigdata, Internet of things, and cloud computing.

Actually, Okba KAZAR is a full professor at computer science department of Biskra University and director of intelligent computer science laboratory (LINFI).

Mouadh Bali

Mouadh Bali obtained the Engineer and Master Science degrees in computer science from both the University of Biskra and University of Bejaia (Algeria), in 2010 and 2016, respectively. He is currently working toward the Ph.D. degree at the University of Bejaia. In 2016, he joined the Computer Science Department, University of El-Oued (Algeria). His current research activities include cloud computing, Internet of things, and optimization techniques.

Houcine Belouaar

Houcine Belouaar obtained the engineering diploma in 1996 from Annaba University (Algeria), obtained his magister in computer science in networks and multimedia information systems in 2011 from Ouargla university (Algeria) and his PhD degree in 2019 from Biskra University (Algeria). He is a teacher in the Computer Science Department of Biskra University. Currently, he is currently working on Web services and fuzzy logic. He is interested in intelligent environment, Internet of things, cloud computing, and multiagent systems.

Abdelbasset Barkat

Abdelbasset Barkat obtains his magister degree in 2012 from Biskra University (Algeria) about building ontology from text. He received his PhD in Computer science at the University of Biskra – Algeria (2018). He is an associate professor at the Department of computer science, University of M’sila. His research interests include issues related to the cloud computing, web service, multiagent systems, and optimization.