Large, Internet based companies service user requests from multiple data centers located across the globe. These data centers often house a heterogeneous computing infrastructure and draw electricity from the local electricity market. Reducing the electricity costs of operating these data centers is a challenging problem, and in this work, we propose a novel solution which exploits both the data center heterogeneity and global electricity market diversity to reduce data center operating cost. We evaluate our solution in our test-bed that simulates a heterogeneous data center, using real-world request workload and real-world electricity prices. We show that our strategies achieve cost and energy saving of at least 21% over a naive load balancing scheme that distributes requests evenly across data centers, and outperform existing solutions which either do not exploit the electricity market diversity or do not exploit data center hardware diversity.

The Multicast/Broadcast Service (MBS) feature of mobile WiMAX network is a promising technology for providing wireless multimedia, because it allows the delivery of multimedia content to large-scale user communities in a cost-efficient manner. In this paper, we consider WiMAX networks that transmit multiple video streams encoded in scalable manner to mobile receivers using the MBS feature. We focus on two research problems in such networks: 1) maximizing the video quality and 2) minimizing energy consumption for mobile receivers. We formulate and solve the substream selection problem to maximize the video quality, which arises when multiple scalable video streams are broadcast to mobile receivers with limited resources. We show that this problem is NP-Complete, and design a polynomial time approximation algorithm to solve it. We prove that the solutions computed by our algorithm are always within a small constant factor from the optimal solutions. In addition, we extend our algorithm to reduce the energy consumption of mobile receivers. This is done by transmitting the selected substreams in bursts, which allows mobile receivers to turn off their wireless interfaces to save energy. We show how our algorithm constructs burst transmission schedules that reduce energy consumption without sacrificing the video quality. Using extensive simulation and mathematical analysis, we show that the proposed algorithm: 1) is efficient in terms of execution time, 2) achieves high radio resource utilization, 3) maximizes the received video quality, and 4) minimizes the energy consumption for mobile receivers.

Broadcasting multiple scalable video streams over wireless broadband access networks in real time is a challenging problem, because of the limited channel capacity and variable bit rate of the videos. The difficulty is further increased in the presence of receiver buffer size limitations which may introduce buffer overflow possibilities. The Multicast/Broadcast Service feature of mobile WiMAX network is a promising technology for providing wireless video broadcast services. In this article, we describe a substream selection problem which arises when multiple scalable video streams are broadcast based on the Multicast/Broadcast Service feature to a number of buffer size constrained receivers. We first show that the problem is NP-Complete and design a polynomial time approximation algorithm based on convex optimization and dynamic programming techniques. We mathematically prove that the solution obtained through our algorithm is always within a constant factor of the optimal solution. Through simulation we show that under real time requirements our algorithm provides solutions which are within 1 dB of the optimal solutions.