AFED-EF An Energy-efficient VM Allocation Algorithm for IoT Applications in a Cloud Data Center
ABSTARCT :
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 :
? We tackle problems and issues in managing cloud infrastructure on IaaS level, considering both computing and networking resource provisioning.
? Although many surveys and taxonomies have been presented in cloud computing and SDN contexts, each of them has been addressed a specific problem in the area.
? Network embedding problem, for example, is to map the network flows by different tenants into physical resources by virtualizing the infrastructure .
? These approaches try to collect the network data and alter the forwarding rules in clouds using SDN to solve the research problem.
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 :
? The traditional network approach raises network manageability and performance issues in a cloud data center due to its massive scale on which computing and network resources should be dynamically provisioned to adapt to the fluctuating requests from various tenants.
? A model of SDN architecture to separate a control plane from a forwarding plane, supporting dynamic forwarding rule update, per-flow bandwidth allocation, user-defined network control logic, and network performance monitoring.
? A performance model of SDN-enabled network switches capable of measuring bandwidth utilization and energy consumption.
? Performance evaluation on empirical testbed and simulation framework in comparison with the state-of-the-art baselines with real-world traces.
|