Machine Learning for Cloud Management

Cloud computing offers subscription-based on-demand services, and it has emerged as the backbone of the computing industry. It has enabled us to share resources among multiple users through virtualization, which creates a virtual instance of a computer system running in an abstracted hardware layer. Unlike early distributed computing models, it offers virtually limitless computing resources through its large scale cloud data centers. It has gained wide popularity over the past few years, with an ever-increasing infrastructure, a number of users, and the amount of hosted data. The large and complex workloads hosted on these data centers introduce many challenges, including resource utilization, power consumption, scalability, and operational cost. Therefore, an effective resource management scheme is essential to achieve operational efficiency with improved elasticity. Machine learning enabled solutions are the best fit to address these issues as they can analyze and learn from the data. Moreover, it brings automation to the solutions, which is an essential factor in dealing with large distributed systems in the cloud paradigm. Machine Learning for Cloud Management explores cloud resource management through predictive modelling and virtual machine placement. The predictive approaches are developed using regression-based time series analysis and neural network models. The neural network-based models are primarily trained using evolutionary algorithms, and efficient virtual machine placement schemes are developed using multi-objective genetic algorithms. Key Features: The first book to set out a range of machine learning methods for efficient resource management in a large distributed network of clouds. Predictive analytics is an integral part of efficient cloud resource management, and this book gives a future research direction to researchers in this domain. It is written by leading international researchers. The book is ideal for researchers who are working in the domain of cloud computing.

List of FiguresList of TablesPrefaceAuthor BiosAbbreviations Introduction1.1 CLOUD COMPUTING1.2 CLOUD MANAGEMENT1.2.1 Workload Forecasting1.2.2 Load Balancing1.3 MACHINE LEARNING1.3.1 Artificial Neural Network1.3.2 Metaheuristic Optimization Algorithms1.3.3 Time Series Analysis1.4 WORKLOAD TRACES1.5 EXPERIMENTAL SETUP & EVALUATION METRICS1.6 STATISTICAL TESTS1.6.1 Wilcoxon Signed-Rank Test1.6.2 Friedman Test1.6.3 Finner Test Time Series Models2.1 AUTOREGRESSION2.2 MOVING AVERAGE2.3 AUTOREGRESSIVE MOVING AVERAGE2.4 AUTOREGRESSIVE INTEGRATED MOVING AVERAGE2.5 EXPONENTIAL SMOOTHING2.6 EXPERIMENTAL ANALYSIS2.6.1 Forecast Evaluation2.6.2 Statistical Analysis Error Preventive Time Series Models3.1 ERROR PREVENTION SCHEME3.2 PREDICTIONS IN ERROR RANGE3.3 MAGNITUDE OF PREDICTIONS3.4 ERROR PREVENTIVE TIME SERIES MODELS3.4.1 Error Preventive Autoregressive Moving Average3.4.2 Error Preventive Auto Regressive Integrated Moving Average3.4.3 Error Preventive Exponential Smoothing3.5 PERFORMANCE EVALUATION3.5.1 Comparative Analysis3.5.2 Statistical Analysis Metaheuristic Optimization Algorithms4.1 SWARM INTELLIGENCE ALGORITHMS IN PREDICTIVE MODEL4.1.1 Particle Swarm Optimization4.1.2 Firefly Search Algorithm4.2 EVOLUTIONARY ALGORITHMS IN PREDICTIVE MODEL4.2.1 Genetic Algorithm4.2.2 Differential Evolution4.3 NATURE INSPIRED ALGORITHMS IN PREDICTIVE MODEL4.3.1 Harmony Search4.3.2 Teaching Learning Based Optimization4.4 PHYSICS INSPIRED ALGORITHMS IN PREDICTIVE MODEL4.4.1 Gravitational Search Algorithm4.4.2 Blackhole Algorithm4.5 STATISTICAL PERFORMANCE ASSESSMENT Evolutionary Neural Networks5.1 NEURAL NETWORK PREDICTION FRAMEWORK DESIGN5.2 NETWORK LEARNING5.3 RECOMBINATION OPERATOR STRATEGY LEARNING5.3.1 Mutation Operator5.3.1.1 DE/current to best/15.3.1.2 DE/best/15.3.1.3 DE/rand/15.3.2 Crossover Operator5.3.2.1 Ring Crossover5.3.2.2 Heuristic Crossover5.3.2.3 Uniform Crossover5.3.3 Operator Learning Process5.4 ALGORITHMS AND ANALYSIS5.5 FORECAST ASSESSMENT5.5.1 Short Term Forecast5.5.2 Long Term Forecast5.6 COMPARATIVE ANALYSIS Self Directed Learning6.1 NON-DIRECTED LEARNING BASED FRAMEWORK6.1.1 Non-Directed Learning6.2 SELF-DIRECTED LEARNING BASED FRAMEWORK6.2.1 Self Directed Learning6.2.2 Cluster Based Learning6.2.3 Complexity analysis6.3 FORECAST ASSESSMENT6.3.1 Short Term Forecast6.3.1.1 Web Server Workloads6.3.1.2 Cloud Workloads6.4 LONG TERM FORECAST6.4.0.1 Web Server Workloads6.4.0.2 Cloud Workloads6.5 COMPARATIVE & STATISTICAL ANALYSIS Ensemble Learning7.1 EXTREME LEARNING MACHINE7.2 WORKLOAD DECOMPOSITION PREDICTIVE FRAMEWORK7.2.1 Framework Design7.3 ELM ENSEMBLE PREDICTIVE FRAMEWORK7.3.1 Ensemble Learning7.3.2 Expert Architecture Learning7.3.3 Expert Weight Allocation7.4 SHORT TERM FORECAST EVALUATION7.5 LONG TERM FORECAST EVALUATION7.6 COMPARATIVE ANALYSIS Load Balancing8.1 MULTI-OBJECTIVE OPTIMIZATION8.2 RESOURCE EFFICIENT LOAD BALANCING FRAMEWORK8.3 SECURE AND ENERGY AWARE LOAD BALANCING FRAMEWORK8.3.1 Side Channel Attacks8.3.2 Ternary Objective VM Placement8.4 SIMULATION SETUP8.5 HOMOGENEOUS VM PLACEMENT ANALYSIS8.6 HETEROGENEOUS VM PLACEMENT ANALYSIS BibliographyIndex

Jitendra Kumar is an assistant professor in machine learning at the National Institute of Technology Tiruchirappalli, Tamilnadu, India. He obtained his doctorate in 2019 from the National Institute of Technology Kurukshetra, Haryana, India. He is also a recipient of the Director’s medal for the first rank in the University examination at Dayalbagh Educational Institute, Agra, Uttar Pradesh in 2011. He has experience of three years in academia. He has published several research papers in international journals and conferences of high repute, including IEEE Transactions on Parallel and Distributed Systems, Information Sciences, Future Generation Computer Systems, Neurocomputing, Soft Computing, Cluster Computing, IEEE-FUZZ, etc. He has also obtained the best paper awards in two international conferences. His research interests are machine learning, cloud computing, healthcare, parallel algorithms, and optimization. He is also a review board member of several journals, including IEEE Transactions on Computers, IEEE Transactions on Parallel and Distributed Systems, IEEE Access, Journal and Parallel Distributed Computing, and more. Ashutosh Kumar Singh is an esteemed researcher and academician in the domain of Electrical and Computer engineering. Currently, he is working as a Professor; Department of Computer Applications; National Institute of Technology; Kurukshetra, India. He has more than 20 years research, teaching and administrative experience in various University systems of the India, UK, Australia and Malaysia. Dr. Singh obtained his Ph. D. degree in Electronics Engineering from Indian Institute of Technology-BHU, India; Post Doc from Department of Computer Science, University of Bristol, United Kingdom and Charted Engineer from United Kingdom. He is the recipient of Japan Society for the Promotion of Science (JSPS) fellowship for visit in University of Tokyo and other universities of Japan. His research area includes Verification, Synthesis, Design and Testing of Digital Circuits, Predictive Data Analytics, Data Security in Cloud, Web Technology. He has more than 250 publications till now which includes peer reviewed journals, books, conferences, book chapters and news magazines in these areas. He has co-authored eight books including ‘‘Web Spam Detection Application using Neural Network’’, ‘‘Digital Systems Fundamentals’’ and ‘‘Computer System Organization & Architecture’’. Prof. Singh has worked as principal investigator/investigator for six sponsored research projects and was a key member on a project from EPSRC (United Kingdom) entitled ’’Logic Verification and Synthesis in New Framework’’. Anand Mohan has nearly 44 years of experience in teaching and research and the administration and management of higher educational institutions. He is currently an institute professor in the Department of Electronics Engineering, Indian institute of Technology (BHU), Varanasi, India. Besides his present academic assignment, Prof. Mohan is a Member of the Executive Council of Banaras Hindu University and Vice-Chairman of the Board of Governors of Indian Institute of Technology (BHU), Varanasi, India. Prof. Mohan served as Director (June 2011--June 2016) of the National Institute of Technology (NIT), Kurukshetra, Haryana, India and was also Mentor Director of the National Institute of Technology, Srinagar, Uttarakhand, India. For his outstanding contributions in the field of Electronics Engineering, Prof. Mohan was conferred the ’’Lifetime Achievement Award’’ (2016) by Kamla Nehru Institute of Technology, Sultanpur, India. Rajkumar Buyya is a Redmond Barry Distinguished Professor and Director of the Cloud Computing and Distributed Systems (CLOUDS) Laboratory at the University of Melbourne, Australia. He is also serving as the founding CEO of Manjrasoft Pty Ltd., a spin-off company of the University, commercialising its innovations in Cloud Computing. He served as a Future Fellow of the Australian Research Council during 2012-2016. He serving/served as Honorary/Visiting Professor for several elite Universities including Imperial College London (UK), University of Birmingham (UK), University of Hyderabad (India), and Tsinghua University (China). He received B.E and M.E in Computer Science and Engineering from Mysore and Bangalore Universities in 1992 and 1995 respectively; and a Doctor of Philosophy (PhD) in Computer Science and Software Engineering from Monash University, Melbourne, Australia in 2002. He was awarded Dharma Ratnakara Memorial Trust Gold Medal in 1992 for his academic excellence at the University of Mysore, India. He received Richard Merwin Award from the IEEE Computer Society (USA) for excellence in academic achievement and professional efforts in 1999. He received Leadership and Service Excellence Awards from the IEEE/ACM International Conference on High Performance Computing in 2000 and 2003. He received ‘‘Research Excellence Awards’’ from the University of Melbourne for productive and quality