Proceedings of the 2017 Workshop on Adaptive Resource Management and Scheduling for Cloud Computing

Abstract

In the emerging Big Data era, where we must deal with large amounts of structured and unstructured data which may not fit traditional relational databases and may arrive at high speeds requiring fast processing, we need powerful platforms and infrastructures as support. Extracting valuable information from raw data is especially difficult considering the velocity of growing data from year to year and the fact that 80% of data is unstructured. In addition, data sources are heterogeneous (various sensors, users with different profiles, etc.) and are located in different situations or contexts. Cloud Computing, which concerns large-scale interconnected systems with the main purpose of aggregating and efficiently exploiting the power of large scale distributed resources, represents one viable solution. Cloud systems are highly dynamic systems where user requests must be met following Service Level Agreements. When ubiquitous systems on the edge of the network interact with Cloud systems new algorithms for events and tasks scheduling, and new methods for resource management should be designed in order to increase the performance of such systems and to mitigate the network bottleneck caused by their control constraints and the Big Data they generate. It becomes obvious that efficient and adaptive resource management and task scheduling play a vital role in cases where one is concerned with the optimized use of cloud resources for meeting specific application objectives in the context of Big Data driven by ubiquitous systems. The adaptive methods used in this context are oriented towards: self-stabilizing, self-organizing and autonomic systems; dynamic, adaptive and machine learning based distributed algorithms; and fault tolerance, reliability, availability of distributed systems. The main goal of the workshop is to explore new directions and approaches for reasoning about resource management in future cloud and hybrid cloud-on-edge systems based on adaptive methods, and to encourage the submission of ongoing work, as well as position papers and case studies of existing verification projects. Also, the workshop offers a forum for both academics and practitioners to share their experience and identify new and emerging trends in this area. Following the success of last years' editions of ARMS-CC held in Chicago (2016), Donostia - San Sebastian (2015) and Paris (2014), the third edition of ARMS-CC workshop aims at providing a venue for researchers, engineers, and practitioners involved in the development of new resource management methods, scheduling algorithms, and middleware tools for Cloud Computing. The goal is to provide an interactive and friendly yet professional forum for original research contributions describing novel ideas, groundbreaking results or quantified system experiences, in the context of PODC Symposium. This volume contains the papers presented at ARMS-CC 2017 held on July 28, 2017 in Washington, DC, USA, in conjunction with PODC 2017 (ACM Symposium on Principles of Distributed Computing). There were 11 submissions. Each submission was reviewed by three program committee members. The committee decided to accept 4 papers to be published in ACM DL Proceedings and to be presented during the workshop (36% acceptance rate). The ARMS-CC workshop was organized with the support of the following projects: DataWay - Real-time Data Processing Platform for Smart Cities: Making sense of Big Data (PN-II-RU-TE-2014-4-2731) and Data4Water: Excellence in Smart Data and Services for Supporting Water Management (H2020-TWINN-2015, CSA-690900).