Sudhakar Ganti

Dynamic Resource Allocation in Computing Clouds Using Distributed Multiple Criteria Decision Analysis

In computing clouds, it is desirable to avoid wasting resources as a result of under-utilization and to avoid lengthy response times as a result of over-utilization. In this paper, we propose a new approach for dynamic autonomous resource management in computing clouds. The main contribution of this work is two-fold. First, we adopt a distributed architecture where resource management is decomposed into independent tasks, each of which is performed by Autonomous Node Agents that are tightly coupled with the physical machines in a data center. Second, the Autonomous Node Agents carry out configurations in parallel through Multiple Criteria Decision Analysis using the PROMETHEE method. Simulation results show that the proposed approach is promising in terms of scalability, feasibility and flexibility.

Towards an Efficient Reservation Algorithm for Distributed Reservation Protocols

With the proliferation of wireless technologies and the convenience they offer, transporting Quality-of-Service (QoS) demanding traffic such as compressed video over wireless links becomes a trend and a challenging issue. Among many factors, Media Access Control (MAC) protocols play an important role in the network stack to ensure the QoS provisioning for multimedia applications and the efficient utilization of wireless channels. Various contention-based or contention-free MAC protocols have been proposed to solve these problems. In this paper, we model, analyze with an existing framework, and evaluate two reservation algorithms, subframe-fit and isozone-fit, proposed for distributed reservation protocols exampled by WiMedia UWB MAC. The models have been validated by extensive simulations using ns-2 and an MPEG-4 traffic generator. We further improve the system performance by introducing cross-isozone allocation and on-demand compaction to isozone-fit, and discuss how to leverage both contention-based and contention-free MAC protocols.

Distributed Reservation Algorithms for Video Streaming over UWB-Based Home Networks

UItra-wideband (UWB) is a new wireless technology that transfers data over shorter distances with higher data rates and lower transmission power. WiMedia Alliances Media Access Control (MAC) protocols for UWB-based wireless personal area networks have become an international standard. The Distributed Reservation Protocol (DRP) is part of this standard that reserves the wireless channel on a slot-by-slot basis for different flows. Knowing that one of the most common use of DRP is to transport multimedia traffic, we propose distributed reservation algorithms for UWB-based home networks according to the video streaming traffic specification and quality-of-service requirement. The proposed algorithms also take the WiMedia UWB MAC policies into account. We analyze and validate the reservation algorithms and policies with a tiered overflow model, and evaluate and compare their performance with Network Simulator (NS-2) and a MPEG-4 video traffic generator. We further discuss the ways of improving video streaming quality and system resource utilization in UWB-based home networks.

Resource optimization algorithms for virtual private networks using the hose model

Virtual private networks (VPNs) provide a secure and reliable communication between customer sites over a shared network. With increase in number and size of VPNs, service providers need efficient provisioning techniques that adapt to customer demands. The recently proposed hose model for VPN alleviates the scalability problem of the pipe model by reserving for aggregate ingress and egress bandwidths instead of between every pair of VPN endpoints. Existing studies on quality of service guarantees in the hose model either deal only with bandwidth requirements or regard the delay limit as the main objective ignoring the bandwidth cost. In this work we propose a new approach to enhance the hose model to guarantee delay limits between endpoints while optimizing the provisioning cost. We connect VPN endpoints using a tree structure and our algorithm attempts to optimize the total bandwidth reserved on edges of the VPN tree. Further, we introduce a fast and efficient algorithm in finding the shared VPN tree to reduce the total provisioning cost compared to the results proposed in previous works. Our proposed approach takes into account the user preferences in meeting the delay limits and provisioning cost to find the optimal solution of resource allocation problem. Our simulation results indicate that the VPN trees constructed by our proposed algorithm meet maximum end-to-end delay limits while reducing the bandwidth requirements as compared to previously proposed algorithms.

Distributed Layer-3 E-Mail Classification for Spam Control

This paper proposes a distributed layer-3 e-mail classification for spam control. E-mail packets are inferred in transit and tagged with an intra-packet spam score to indicate whether the packet forms a legitimate or spam e-mail. During e-mail packet reassembly, tags for an e-mail are aggregated to give an inter-packet spam score. The naive Bayes inference technique is used to evaluate the performance of the proposed approach compared to the full e-mail classification approach. Our simulation results show that the proposed approach exhibits a comparable spam precision (and confidence) to the full e-mail classification approach. Spam recall increases from 63% to 85% depending to the maximum transmission unit size, approaching the 87% of the full e-mail classification. For 67% spam-to-legitimate ratio, we obtain reduction of end serverss workload by 42% to 57% (across all maximum transmission unit sizes tested) of the total e-mail traffic. Thus, the proposed approach can complement existing anti-spam systems by pre-processing e-mail packets on upstream nodes. Layer-3 e-mail processing requires reduced processing complexity as compared to layer-7 processing and is viable for high throughput hardware-based implementations

Tradeoffs in cross platform solutions for mobile assistive technology

With the increasing popularity and wide penetration of mobile smart devices, the advanced capabilities of mobile phones and tablets are being incorporated into assistive technologies. These technologies are crucial for assisting the elderly and people with disabilities in order for them to live independently. There are a myriad ways of designing and developing mobile assistive applications today, each comes with its pros and cons. In this paper we investigate the tradeoffs to be considered when trying to build a “one-size-fits-all” cross platform solution to the existing assistive technology. We outline the design decisions with respect to cross-platform issues, performance, development costs, maintenance overhead, and so on. These design and implementation decisions are the outcome of our two prototype implementations: (i) the development of a cross-mobile application that helps users effectively navigate the outdoor public transit system; and (ii) the development of an application that monitors a users movement and detects certain abnormal behaviors such as falling. We also further investigate the system level concerns such as the performance and efficiency of data storage. We found that it is still challenging to develop a truly “one-size-fits-all” application with todays mobile techniques. However, this is an important first step towards platform independence of assistive technologies.

VM Placement Algorithms for Hierarchical Cloud Infrastructure

A hierarchical cloud infrastructure involving cloud, cluster, and node controllers is the most preferred deployment architecture by the cloud providers since it helps them to achieve the desired scalability and geographical distribution. In this architecture, the cloud controller indirectly controls a large number of node controllers through a few cluster controllers. A Virtual Machine (VM) placement algorithm, therefore, should provide for intelligent cluster selection before node selection. To the best of our knowledge, there is no VM placement algorithm available that has addressed this issue. In this paper, we propose a new VM placement algorithm that intelligently selects the appropriate cluster, and then a node inside the cluster. We use multi-criteria-decision-analysis (MCDA) technique for this purpose. Simulation results have confirmed the superior performance of our algorithm.

Towards software-adaptive green computing based on server power consumption

With the proliferation of virtualization and cloud comput- ing, optimizing the power usage effectiveness of enterprise data centers has become a laudable goal and a critical re- quirement in IT operations all over the world. While a sig- nificant body of research exists to measure, monitor, and control the greenness level of hardware components, signif- icant research efforts are needed to relate hardware energy consumption to energy consumption due to program exe- cution. In this paper we report on our investigations to characterize power consumption profiles for different types of compute and memory intensive software applications. In particular, we focus on studying the effects of CPU loads on the power consumption of compute servers by monitoring rack power consumption in a data center. We conducted a series of experiments with a variety of processes of differ- ent complexity to understand and characterize the effect on power consumption. Combining processes of varying com- plexity with varying resource allocations produces different energy consumption levels. The challenge is to optimize pro- cess orchestration based on a power consumption framework to accrue energy savings. Our ultimate goal is to develop smart adaptive green computing techniques, such as adap- tive job scheduling and resource provisioning, to reduce over- all power consumption in data centers or clouds.

Resource Optimization to Provision a Virtual Private Network Using the Hose Model

Virtual private networks (VPN) provide a secure and reliable communication between customer sites over a shared network. With increase in number and size of VPNs, providers need efficient provisioning techniques that adapt to customer demands. The recently proposed hose model for VPN alleviates the scalability problem of the pipe model by reserving for its aggregate ingress and egress bandwidth instead of between every pair of VPN endpoints. Existing studies on quality of service guarantees in the hose model either deal only with bandwidth requirements or regard the delay requirement as the main objective ignoring the bandwidth cost. In this work we propose a new approach to enhance the hose model to guarantee delay requirements between endpoints while optimizing the provisioning bandwidth cost. We connect VPN endpoints using a tree structure and our algorithm attempts to optimize the total bandwidth reserved on edges of the VPN tree. Our proposed approach takes into account the user preferences in meeting the delay requirements and provisioning cost to find the optimal solution of resource allocation problem. Our experimental results indicate that the VPN trees constructed by our proposed algorithm meet minimum delay requirements while reducing the bandwidth requirements as compared to previously proposed algorithms.

Adaptive routing in mobile ad hoc networks based on decision aid approach

In this paper, we propose a new approach to the problem of adaptive routing in small scale Mobile Ad Hoc Networks (MANET). The proposed approach focuses on leveraging the already existing routing algorithms in real-time through switching from one routing algorithm to another as the conditions change. The contribution of this work is three-fold: (1) nodes use a Multiple Criteria Decision Analysis method called PROMETHEE to make local decisions, (2) the final decision is evaluated as an aggregation of all the local decisions in the MANET through weighted voting, and (3) the network-wide decision process is carried out through a hybrid method that aims to benefit from the advantages of centralized and distributed methods, while limiting their disadvantages. The analyses based on the results extracted from simulations underline that the proposed approach produces stable configurations with minimal interruptions. Furthermore, the completion of global adaptation cycles are performed an order of magnitude faster in comparison to the results outlined in the previous work. These results indicate that the proposed solution is a promising alternative to the existing solutions, and forms a strong basis for further research on larger scale MANETs.