The expense of power cost in server farms has driven the recent power-aware development in both industry and academia. At the same time, a Service Level Agreement (SLA) of service performance between a customer and a service provider is demanded to meet the customer satisfaction. This paper investigates the queueing-theoretical power-saving design strategy for server farms under a given SLA, which in particular is measured in a certain level percentile of the job response time. We consider server farms with servers that are equipped with the capabilities of Dynamic Voltage Scaling (DVFS) and Dynamic Power Management (DPM). We adopt an M/G/1/PS server model, where the job service time distribution is assumed heavy-tailed, as discovered and validated by previous research. We propose a design strategy called Power Tail to minimize the power consumption under the given SLA. Our data confirms that the proposed Power Tail strategy indeed provides statistical guarantee in comparison with existing dynamic DVFS approaches and significantly outperforms the intuitive load-balancing strategy.

To provide satisfactory customer experience, modern server clusters like Amazon usually set Service Level Agreement (SLA) as guaranteeing a certain percentile (i.e. 99%) of the customer requests to have a response time within a threshold (i.e. 1s). One way to meet the SLA constraint is to serve the customer requests with sufficient computing capacity based on the worst case workload estimation in the server cluster. However, this may cause unnecessary power consumption in the server cluster due to over-provision of the computing capacity especially when the workload is highly dynamic. In this paper, we propose an adaptive computing capacity allocation scheme referred to as TailCon. TailCon aims at minimizing the power consumption in the server cluster while satisfying the SLA constraint by adjusting the number of active servers and the CPU frequencies of the turn on machines online. In TailCon, we analyze the distribution of the request response time dynamically and leverage the measured request response time to estimate the workload intensity in the server cluster, which is used as a continuous feedback to find the proper provision of the computing capacity online based on optimization techniques. We conduct both the emulation using the real-word HTTP traces and the experiments to evaluate the performance of TailCon. The experimental results demonstrate the effectiveness of TailCon scheme in enforcing the SLA constraint while saving the power consumption.

Reducing the power consumption while maintaining the response time constraint has been an important goal in server system design. One of the techniques widely explored in the literature to achieve this goal is Dynamic Voltage Scaling (DVS). However, DVS is not efficient in modern systems where the overall power consumption includes a large portion of static power consumption. In this paper, we aim to reduce the static power consumption by Dynamic Power Management (DPM) with sleep model in addition to DVS. We propose a smart PowerSleep power-saving scheme, where a procrastination technique is adopted to carefully aggregate jobs to reduce the overhead of transitions in and out of the sleep mode. We also observe that PowerSleep might not always be a good choice due to the mode transition overhead when the server utilization is high, where instead we use PowerIdle power-saving scheme with DVS only. By modeling the system with M/G/1/PS queuing model and further extensions, we present how to minimize the mean power consumption of the server under the given mean response time constraint for both power-saving schemes. Simulation results show that our smart PowerSleep scheme significantly outperforms the simple power saving scheme which adopts sleep mode.

Thermal management becomes a prominent issue in system design for both server systems and embedded systems. A system could fail if the peak temperature exceeds its thermal constraint. This research studies thermal-constrained scheduling for frame-based real-time tasks on a dynamic voltage/speed scaling system. Our objective is to design speed schedulers for real-time tasks by utilizing dynamic voltage/speed scaling to meet both timing and thermal constraints. Two approaches are proposed: One is based on the minimization of the response time under the thermal constraint, and the other is based on the minimization of the temperature under the timing constraint. We present detailed schedulability analysis for both proposed approaches. Our data show that our proposed proactive approaches outperform existing reactive ones.

As the power density of modern electronic circuits increases dramatically, systems are prone to overheating. Thermal management has become a prominent issue in system design. This paper explores thermal-aware scheduling for sporadic real-time tasks to minimize the peak temperature in a homogeneous multicore system, in which heat might transfer among some cores. By deriving an ideally preferred speed for each core, we propose global scheduling algorithms which can exploit the flexibility of multicore platforms at low temperature. Compared with load-balancing strategies, the proposed algorithms can significantly reduce the peak temperature by up to 30degC to 70degC for simulated platforms.

Thermal constraints have limited the performance improvement of modern computing systems in recent years. As a system could fail if the peak temperature exceeds its thermal constraint, overheating should be avoided while designing a system. Moreover, higher temperature also leads to higher leakage power consumption. This paper explores dynamic thermal management to minimize the energy consumption for a specified computing demand under the thermal constraint. We develop energy-efficient speed scheduling schemes for frame-based real-time tasks under thermal constraints. Experimental results reveal the effectiveness of the proposed scheme in terms of energy consumption in comparison with the reactive schemes in the literature.

In this paper, we study temperature-constrained real-time systems, where real-time guarantees must be met without exceeding safe temperature levels within the processor. We give a short review on temperature issues in processors and describe how speed control can be used to trade-off task delays against processor temperature. In this paper, we describe how traditional worst-case execution scenarios do not apply in temperature-constrained situations. As example, we adopt a simple reactive speed control technique. We show how this simple reactive scheme can improve the processor utilization compared with any constant-speed scheme.

In this paper, we study temperature-constrained hard real-time systems, where real-time guarantees must be met without exceeding safe temperature levels within the processor. Dynamic speed scaling is one of the major techniques to manage power so as to maintain safe temperature levels. As example, we adopt a simple reactive speed control technique in our work. We design a methodology to perform delay analysis for general task arrivals under reactive speed control with first-in-first-out (FIFO) scheduling and static-priority (SP) scheduling. As a special case, we obtain a close-form delay formula for the leaky-bucket task arrival model. Our data show how simple reactive speed control can decrease the delay of tasks compared with any constant-speed scheme

In this paper, we address issues in implementing voice over IP (VoIP) services in packet switching networks. VoIP has been identified as a critical real-time application in the network QoS research community and has been implemented in commercial products. To provide competent quality of service for VoIP systems comparable to traditional PSTN systems, a call admission control (CAC) mechanism has to be introduced to prevent packet loss and over-queuing. Several well-designed CAC mechanisms, such as the site-utilization-based CAC-and the link-utilization-based CAC mechanisms have been in place. However, the existing commercial VoIP systems have not been able to adequately apply and support these CAC mechanisms and, hence, have been unable to provide QoS guarantees to voice over IP networks. We have designed and implemented a QoS-provisioning system that can be seamlessly integrated with the existing VoIP systems to overcome their weakness in offering QoS guarantees. A practical implementation of our QoS-provisioning system has been realized.

We address privacy-preserving classification problem in a distributed system. Randomization has been the approach proposed to preserve privacy in such scenario. However, this approach is now proven to be insecure as it has been discovered that some privacy intrusion techniques can be used to reconstruct private information from the randomized data tuples. We introduce an algebraic-technique-based scheme. Compared to the randomization approach, our new scheme can build classifiers more accurately but disclose less private information. Furthermore, our new scheme can be readily integrated as a middleware with existing systems.

Component technology has become a central focus of software engineering in research and development. Reusability is a key factor that contributes to its success. The reuse of components can lead to a shortening of software development cycles and savings in software development costs. However, existing component models provide no support for real-time services and some real-time extensions of component models lack of consideration for reusability of components in providing real-time services. In this work, we develop a real-time component-based system that maintains the reusability of components.

We study the delay performance of policed traffic to provide real-time guarantees over wireless networks. A number of models have been presented in the literature to describe wireless (radio or optical) networks in terms of the wireless channel and the underlying error control mechanisms. We describe a general framework to incorporate such models into delay guarantee computations for real-time traffic. Static-priority scheduling is considered, and two different admission control mechanisms are used to achieve the trade-off between resource utilization and admission overhead.

Distributed denial of service (DDoS) attacks are currently major threats to communication in the Internet. A secure overlay services (SOS) architecture has been proposed to provide reliable communication between clients and a target under DDoS attacks. The SOS architecture employs a set of overlay nodes arranged in three hierarchical layers that controls access to the target. Although the architecture is novel and works well under simple congestion based attacks, we observe that it is vulnerable under more intelligent attacks. We generalize the SOS architecture by introducing more flexibility in layering to the original architecture. We define two intelligent DDoS attack models and develop an analytical approach to study the impacts of the number of layers, number of neighbors per node and the node distribution per layer on the system performance under these two attack models. Our data clearly demonstrate that performance is indeed sensitive to the design features and the different design features interact with each other to impact overall system performance.

In this paper, we propose and analyze a methodology for providing absolute differentiated services for real-time applications. We develop a method that can be used to derive delay bounds without specific information on flow population. With this new method, we are able to successfully employ a utilization-based admission control approach for flow admission. This approach does not require explicit delay computation at admission time and, hence, is scalable to large systems. We assume the underlying network to use static-priority schedulers. We design and analyze several priority assignment algorithms and investigate their ability to achieve higher utilization bounds. Traditionally, schedulers in differentiated services networks assign priorities on a class-by-class basis, with the same priority for each class on each router. In this paper, we show that relaxing this requirement, that is, allowing different routers to assign different priorities to classes, achieves significantly higher utilization bounds.

We propose an approach to analyze the resilience to failures of structured P2P systems. The approach is Markov-chain based, and can be applied to systems with relatively stable size and uniformly distributed nodes. We apply our method to several well-known structured P2P systems. We find that finger neighbors and special neighbors have different influences on the resilience features of P2P systems. More particularly, finger neighbors have significant influence on the average path length while special neighbors influence the hit ratio. Following the above observation, we propose to add some finger neighbor(s) to nodes of the CAN (content-addressable network) system which originally have no such finger neighbor(s). We use the small-world phenomenon to form the CAN-small-world (CAN-SW) system. We then apply the proposed Markov-chain based approach to analyze its resilience. We find that the performance of the system under failures or not, has been improved significantly, particularly, in terms of the average path length.

We address the issues related to aggregation of anycast groups for scalable anycast routing. Anycast is a new network service that allows a sender to access anyone in a group that shares the same anycast address. Anycast has numerous potential applications. However, it also introduces new issues. One of the issues is that the size of the anycast routing tables is significantly increased The main goals of this study are to reduce the size of routing tables and to improve network end-to-end performance. Particularly, we propose three group-aggregation algorithms with different objectives: (1) group-aggregation for minimizing the routing table size, (2) group-aggregation for balancing interface load, and (3) integrated group-aggregation. These algorithms take full advantages of the anycast semantics. Our evaluation results show that our group-aggregation algorithms can efficiently reduce the size of routing tables by 90% while achieving high network performance in terms of the average end-to-end delay.

In this paper, we propose and analyze a methodology for providing statistical guarantees within the diffserv model in a network, that uses static-priority schedulers. We extend the previous work on statistical delay analysis and develop a method that can be used to derive delay bounds without specific information on flow population. With this new method, we are able to successfully employ a utilization-based admission control approach for flow admission. This approach does not require explicit delay computation at admission time and hence is scalable to large systems. We systematically analyze the performance of our approaches in terms of system utilization. As expected, our experimental data show that statistical services can achieve much higher utilization than deterministic services.

We propose and analyze a methodology for providing absolute differentiated services for real-time applications in networks that use static-priority schedulers. We extend previous work on worst-case delay analysis and develop a method that can be used to derive delay bounds without specific information on flow population. With this new method, we are able to successfully employ a utilization-based admission control approach for flow admission. This approach does not require explicit delay computation at admission time and hence is scalable to large systems. We assume the underlying network to use static-priority schedulers. We design and analyze several priority assignment algorithms, and investigate their ability to achieve higher utilization bounds. Traditionally, schedulers in differentiated services networks assign priorities on a class-by-class basis, with the same priority for each class on each router. We show that relaxing this requirement, that is, allowing different routers to assign different priorities to classes, achieves significantly higher utilization bounds.

We propose and analyze a methodology for providing absolute differentiated services with statistical performance guarantees for real-time applications in networks that use class-based (as opposed to flow-aware) static priority schedulers. We develop a method that can be used to derive statistical delay guarantees in a flow-unaware fashion. Traditionally, both deterministic and statistical delay analysis methods either depend on schedulers that keep per-flow state information, or require detailed information about flow population at delay analysis time. The fact that no such information is needed for delay analysis allows us to perform deadline tests during system (re-)configuration time. We are so able to reduce the runtime admission control to a simple utilization test. No explicit delay computation is necessary at admission time, making this approach scalable to large systems.