Big Data and Internet of Things (IoT) are two popular technical terms in current IT industry. The computing of IoT applications data consumes more energy since it’s high velocity in real-time. The proposed methodology re-storm that addresses energy issues and response time of IoT applications data. It uses big data stream computing for re-storm against existing method storm. The ultimate goal of proposed system is to plan and develop complete strategies to improve the performance of BDSC Environment for IoT application datasets. The storm failed to address dynamic scheduling but re-storm deals with three different features, 1) Data stream graph optimization, 2) energy-efficient self-scheduling strategy, 3) Real-Time Data Stream Computing with Memory Level Dynamic Voltage and Frequency Scaling (DVFS). Proposed system handles different traffic arriving rate of streams and re-storm at multiple traffic levels for high energy efficiency, low response time. It deals at three levels, firstly, a mathematical model for high energy efficiency, low response time. Secondly, allocation of resources bearing in mind DVFS methods and existing effective optimal consolidation methods. Thirdly, online task allocation using hot swapping technique and streaming graph optimizing. Finally, the experimental results show that restorm has been improved the performance 30-40% against storm for real time data of IoT applications.

Internet of Things, Big Data Stream Computing, Hadoop Distributed File System, Virtual Machine

[1]. Neumeyer, L. and B. Robbins (2010). S4 : Distributed Stream Computing Platform. IEEE Int. Conf. on Data Mining Workshops, Washington DC, pp. 170–177, USA.
[2]. Zhuravlev, S., J.C. Saez, S. Blagodurov, A. Fedorova and M. Pranaw (2013). Survey of Energy-Cognizant Scheduling Techniques, IEEE Trans. Parall. Distr. Syst., Vol. 24, No. 7, pp. 1447–1464.
[3]. Benkhelifa, E., M. Abdel-Maguid, S. Ewenike and D. Heatley (2014). The Internet of Things: The eco-system for sustainable growth. IEEE/ACS 11th Int. Conf. on Computer Systems and Applications, Doha, pp. 836-842, Qatar.
[4]. Sharifi, M., S. Shahrivari and H. Salimi (2013). PASTA: A Power-aware Solution to Scheduling of Precedence-constrained Tasks on Heterogeneous Computing Resources, J. Computing, Vol. 95, No. 1, pp. 67–88.
[5]. Shao, H., L. Rao, Z. Wang, X. Liu, Z. Wang and K. Ren. (2014). Optimal Load Balancing and Energy Cost Management for Internet Data Centers in Deregulated Electricity Markets, IEEE Trans. Parall. Distr. Syst., Vol. 25, No. 10, pp. 2659–2669.
[6]. Wang, J.H., D. Lai, Huang and W. Shi Zheng (2013). SVStream: a Support Vector- Based Algorithm for Clustering Data Streams, IEEE Trans. Knowl. Data Eng., Vol. 25, No. 6, pp. 1410–1424.
[7]. Daoud, M.I. and N. Kharma (2011). A hybrid heuristic-genetic algorithm for task scheduling in heterogeneous processor networks, J. Parall. Distr. Comput., Vol. 71, No. 11, pp. 1518–1531.
[8]. Liu, X., N. Iftikhar and X. Xie (2014). Survey of Real-Time Processing Systems for Big Data, 18th Int. Database Engineering and Applications Symposium, New York, pp. 356–361, USA.
[9]. Xu Y., K. Li, L. He and T. K. Truong (2013). A DAG Scheduling Scheme on Heterogeneous Computing Systems using Double Molecular Structure-Based Chemical Reaction Optimization, J. Parall. Distr. Comput., Vol. 73 No. 9, pp. 1306–1322.