AFED-EF An Energy-efficient VM Allocation Algorithm for IoT Applications in a Cloud Data Center

Abstract : Cloud Data Centers (CDCs) have become a vital computing infrastructure for enterprises. However, CDCs consume substantial energy due to the increased demand for computing power, especially for the Internet of Things (IoT) applications. Although a great deal of research in green resource allocation algorithms have been proposed to reduce the energy consumption of the CDCs, existing approaches mostly focus on minimizing the number of active Physical Machines (PMs) and rarely address the issue of load fluctuation and energy efficiency of the Virtual Machine (VM) provisions jointly. Moreover, existing approaches lack mechanisms to consider and redirect the incoming traffics to appropriate resources to optimize the Quality of Services (QoSs) provided by the CDCs. We propose a novel adaptive energy-aware VM allocation and deployment mechanism called AFED-EF for IoT applications to handle these problems. The proposed algorithm can efficiently handle the fluctuation of load and has good performance during the VM allocation and placement. We carried out extensive experimental analysis using a real-world workload based on more than a thousand PlanetLab VMs. The experimental results illustrate that AFED-EF outperforms other energy-aware algorithms in energy consumption, Service Level Agreements (SLA) violation, and energy efficiency.

 EXISTING SYSTEM :

 ? Existing algorithms typically consider a particular subset of VM characteristics that is relevant to optimize the main goal, and keep the rest of metrics either unchanged or under a predefined threshold. ? Every time slot, the VM allocation method re-allocates the existing VMs, migrating them if needed to the minimum number of servers such that highly data-correlated VMs are placed together, while highly CPU-load correlated VMs are placed apart. ? In addition, an energy-efficient management based on existing CPU-load correlation to achieve more energy and cost savings is missing from these works. ? The Datacenter Energy Controller is based on a state-of-the-art CPU-load correlation-aware VM allocation scheme due to the existence of high CPU variability in applications’ patterns.

 DISADVANTAGE :

 ? This stage is treated as multi-dimensional vector bin packing problem (MVBPP) and the MVBPP based heuristics virtual resource allocation algorithm (HVRAA) is proposed to solve it. ? The rapid growth in mobile devices and the storage needs due to the adoption of cloud data networking are creating huge data traffic due to the emerging issues of data centers and also digital content, media and technology. ? Energy issues are supposed to be critical and also needs to be managed properly in some environment where mobile cloud computing is involved. ? The vital challenge is balancing between system performance and power consumption by reducing energy consumption without prejudicial impact on the performance and quality of services delivered.

 PROPOSED SYSTEM :

 • The proposed technique exploits the holistic knowledge of VMs characteristics to tackle the challenges of operational cost (i.e., electricity bill) optimization and energyperformance trade-offs. • The proposed algorithm optimizes the operational costs, data center energy consumption, network traffic and response time while maximizing the renewable energy and battery usage. • The proposed algorithm dynamically determines which method among the heuristic and the ML is to be used at each time. • The proposed hyper-heuristic relies on the long-term periodicity of the workloads being executed, and learns the performance of the methods over time.

 ADVANTAGE :

 ? High performance has always been the most critical concern in cloud data centers, which comes at the cost of energy consumption. ? The key challenge is to balance between system performance and the power consumption. ? As the energy availability decreases and energy cost proportionally increases, the need for shifting the focus for utilizing data center resource management to optimize energy performance while maintaining service performance is becoming a necessity. ? The customers would not pay or may switch to other similar service providers if either quality of service or expected performance level is not achievable.