Saving Energy in QoS Networked Data Centers

One of the major challenges that cloud providers face is minimizing power consumption of their data centers. To this point, majority of current research focuses on energy efficient management of resources in the Infrastructure as a Service model using virtualization and through virtual machine consolidation. However, current virtualized data centers are not designed for supporting communication–computing intensive real-time applications, such as, info-mobility applications, real-time video co-decoding. In fact, imposing hard-limits on the overall per-job delay forces the overall networked computing infrastructure to adapt quickly its resource utilization to the (possibly, unpredictable and abrupt) time fluctuations of the offered workload. Jointly, a promising approach for making networked data centers more energy-efficient is the use of traffic engineering-based method to dynamically adapt the number of active servers to match the current workload. Therefore, it is desirable to develop a flexible and robust resource allocation algorithm that automatically adapts to time-varying workload and pays close attention to the consumed energy in computing and communication in virtualized networked data centers (VNetDCs). In this thesis, we propose three new dynamic and adaptive energy-aware algorithms scheduling policies that model and manage VNetDCs. Our focuses are to propose i) admission control of the offered input traffic; ii) balanced control and dispatching of the admitted workload; iii) dynamic reconfiguration and consolidation of the Dynamic Voltage and Frequency Scaling (DVFS)-enabled Virtual Machines (VMs) instantiated onto the parallel computing platform; and, iv) rate control of the traffic injected into the TCP/IP mobile connection. Necessary and sufficient conditions for the feasibility and optimality of the proposed schedulers are also provided in closed-form. Specifically, the first approach, called VNetDC, the optimal minimum-energy scheduler for the joint adaptive load balancing and provisioning of the computing-plus-communication resources. VNetDC platforms have been considered which operate under hard real-time constraints. VNetDC has capability to adapt to the time-varying statistical features of the offered workload without requiring any a priori assumption and/or knowledge about the statistics of the processed data. Green-NetDC is the second scheduling policy that is a flexible and robust resource allocation algorithm that automatically adapts to time-varying workload and pays close attention to the consumed energy in computing and communication in VNetDCs. GreenNetDC not only ensures users the Quality of Service (through Service Level Agreements) but also achieves maximum energy saving and attains green cloud computing goals in a fully distributed fashion by utilizing the DVFS-based CPU frequencies. Finally, the last algorithm tested an efficient dynamic resource provisioning scheduler which applied in Networked Data Centers (NetDCs). This method is connected to (possibly, mobile) clients through TCP/IP-based vehicular backbones The salient features of this algorithm is that: i) It is adaptive and admits distributed scalable implementation; ii) It is capable to provide hard QoS guarantees, in terms of minimum/maximum instantaneous rate of the traffic delivered to the client, instantaneous goodput and total processing delay; and, iii) It explicitly accounts for the dynamic interaction between computing and networking resources, in order to maximize the resulting energy efficiency. Actual performance of the proposed scheduler in the presence of :i) client mobility; ii)wireless fading; iii)reconfiguration and two-thresholds consolidation costs of the underlying networked computing platform; and, iv)abrupt changes of the transport quality of the available TCP/IP mobile connection, is numerically tested and compared against the corresponding ones of some state-of-the-art static schedulers, under both synthetically generated and measured real-world workload traces.