Secure VM Live Migration For Energy-Efficient Cloud Computing Data Centers

Data centre inefficiency is a widespread and growing concern. Soaring costs and ever-increasing environmental footprint are impacting the corporate investment landscape, threatening profitability, and inviting regulatory scrutiny.Several governmental, industrial, and academic surveys indicate that the energy utilized by computing and communication units within a data center contributes to a considerable slice of the data center operational costs. Apart from high operating costs, a major problem caused by the growing energyconsumption is high CO2emissions, which contribute to the global warming. More and more customers have started to considerthe "green" aspect in selecting products and services. Besides the environmentalconcern, businesses have begun to face risks caused by being non-environmentfriendly. The reduction of CO2footprints is an important problem that has to beaddressed in order to facilitate further advancements in computing systems.Recent advances in hardware technologies including low-power processors,solid state drives, and energy-efficient monitors have alleviated the energy consumptionissue to a certain degree, and a series of software approaches have significantlycontributed to the improvement of energy efficiency.Most of the current state-of-the-art research on energy efficiency has predominantly focused on achieving energy efficiency through virtual machine consolidation. Other power saving solutions focused on making the data center hardware components power efficient. Technologies, such as Dynamic Voltage and Frequency Scaling (DVFS), and Dynamic Power Management (DPM)were extensively studied and widely deployed. Because the aforementioned techniques rely on power-down and power-off methodologies, the efficiency of these techniques is at best limited. In fact, an idle server may consume about2/3of the peak load.However most of the methods explored previously by other researchers have security vulnerabilities and low energy saving.This thesis addresses the high energy consumption problem by minimizingthe peak power required to feed a completely utilizedsystem. The thesis achievesthis through workload consolidation onto a set of servers and powering off servers that become idle after consolidation. The main idea is to reduce power wastage by idle servers that do not have any workload. This thesis presents an efficient method of server consolidation through virtual machine migration among server farms.Thethesis makes major contributions by providing a comprehensive consolidation strategy using secure VM live migration. It discusses efficient ways of deploying virtual machines to servers and migrating virtual machines among servers clusters based on sever workload utilization using dynamic round-robin algorithm. The ultimate result of the method is the reduction of the number of physical machines used since the number of physical machines used greatly affects the overall power consumption. The thesis further discusses known security threats to VM’s during live migration and presents mitigation strategies to the threats. The methods discussed in the thesis preserves privacy and integrity of protected contents by making sure that memory pages of secure processes are kept inaccessible from other processes and operating system kernel during migration. The methods presented eliminate security vulnerabilities faced during live migration.To evaluate the methods discussed in the thesis, the thesis uses CloudSim framework which provides basic models and entities to validate and evaluate energy-conscious provisioning of techniques/algorithms. The thesis has made a number of extensions to Framework to enable it to simulate efficient energy-conscious provisioning policies at resource, and VM level in a secure way. It does this by extending its classes to include additional power model object for managing power consumption on a per Cloud host basis. To support modelling and simulation of different power consumption models and power management techniques such as Dynamic Voltage and Frequency Scaling (DVFS), the thesis provides an abstract implementation to handle this. This capability enables the creation of energy-conscious provisioning policies that require real-time knowledge of power consumption by Cloud system components. Furthermore, it enables accounting of total energy consumed by the system during the simulation period. To make sure that VM is protected against attacks, the thesis extended the CloudSim classes and implements the security module in it. It is the main class, which is responsible for managing event queues and controlling step by step (sequential) execution of simulation events. Every event that is generated by the CloudSim entity at run-time is stored in the queue called future events. These events are sorted by their time parameter and inserted into the queue. Next, the events that are scheduled on each step of the simulation are removed from the future events queue and transferred to the deferred event queue. Following this, an event processing method and the security module is invoked for each entity, which chooses events from the deferred event queue and performs appropriate actions.This thesisalso does significant contributions by doing extensive investigation on various power-aware VM provisioning schemes like DVFS and DNS. For this purposes, thethesis presents an optimal power aware provisioning scheme based on comparative evaluation on existing schemes on various data centre architectures. The thesis has made a number of extensions to CloudSim framework to enable it to simulate efficient energy-conscious provisioning policies at resource, and VM level in a secure way. It does this by extending the Cloudsim’s core classes to include an additional Power Model object for managing power consumption on a per Cloud host basis. This a significant contribution since this modification enables the framework to simulate different power consumption models and power management techniques such as Dynamic Voltage and Frequency Scaling (DVFS)From the results the thesis presents, it is observed thatvirtual machine migration using Dynamic Round robin algorithm for server consolidation is an extremely feasible solution to reduce energy consumption in a data centre without compromising on security.