In today's data centers, precisely controlling server power consumption is an essential way to avoid system failures caused by power capacity overload or overheating due to increasingly high server density. While various power control strategies have been recently proposed, existing solutions are not scalable to control the power consumption of an entire large-scale data center, because these solutions are designed only for a single server or a rack enclosure. In a modern data center, however, power control needs to be enforced at three levels: rack enclosure, power distribution unit, and the entire data center, due to the physical and contractual power limits at each level. This paper presents SHIP, a highly scalable hierarchical power control architecture for large-scale data centers. SHIP is designed based on well-established control theory for analytical assurance of control accuracy and system stability. Empirical results on a physical testbed show that our control solution can provide precise power control, as well as power differentiations for optimized system performance and desired server priorities. In addition, our extensive simulation results based on a real trace file demonstrate the efficacy of our control solution in large-scale data centers composed of 5,415 servers.

With the number of high-density servers in data centers rapidly increasing, power control with performance optimization has become a key challenge to gain a high return on investment, by safely accommodating the maximized number of servers allowed by the limited power supply and cooling facilities in a data center. Various power control solutions have been recently proposed for high-density servers and different components in a server to avoid system failures due to power overload or overheating. Existing solutions, unfortunately, either rely only on the processor for server power control, with the assumption that it is the only major power consumer, or limit power only for a single component, such as main memory. As a result, the synergy between the processor and main memory is impaired by uncoordinated power adaptations, resulting in degraded overall system performance. In this paper, we propose a novel power control solution that can precisely limit the peak power consumption of a server below a desired budget. Our solution adapts the power states of both the processor and memory in a coordinated manner, based on their power demands, to achieve optimized system performance. Our solution also features a control algorithm that is designed rigorously based on advanced feedback control theory for guaranteed control accuracy and system stability. Compared with two state-of-the-art server power control solutions, experimental results show that our solution, on average, achieves up to 23% better performance than one baseline for CPU-intensive benchmarks and doubles the performance of the other baseline when the power budget is tight.

In this paper, we undertake the problem of server consolidation in virtualized data centers from the perspective of approximation algorithms. We formulate server consolidation as a stochastic bin packing problem, where the server capacity and an allowed server overflow probability p are given, and the objective is to assign VMs to as few physical servers as possible, and the probability that the aggregated load of a physical server exceeds the server capacity is at most p.

Optimizing the performance of a multi-core microprocessor within a power budget has recently received a lot of attention. However, most existing solutions are centralized and cannot scale well with the rapidly increasing level of core integration. While a few recent studies propose power control algorithms for many-core architectures, those solutions assume that the workload of every core is independent and therefore cannot effectively allocate power based on thread criticality to accelerate multi-threaded parallel applications, which are expected to be the primary workloads of many-core architectures. This paper presents a scalable power control solution for many-core microprocessors that is specifically designed to handle realistic workloads, i.e., a mixed group of single-threaded and multi-threaded applications. Our solution features a three-layer design. First, we adopt control theory to precisely control the power of the entire chip to its chip-level budget by adjusting the aggregated frequency of all the cores on the chip. Second, we dynamically group cores running the same applications and then partition the chip-level aggregated frequency quota among different groups for optimized overall microprocessor performance. Finally, we partition the group-level frequency quota among the cores in each group based on the measured thread criticality for shorter application completion time. As a result, our solution can optimize the microprocessor performance while precisely limiting the chip-level power consumption below the desired budget. Empirical results on a 12-core hardware testbed show that our control solution can provide precise power control, as well as 17% and 11% better application performance than two state-of-the-art solutions, on average, for mixed PARSEC and SPEC benchmarks. Furthermore, our extensive simulation results for 32, 64, and 128 cores, as well as overhead analysis for up to 4,096 cores, demonstrate that our solution is highly scalable to many-core architectures.

The demand for high performance information dissemination is increasing in many applications, such as e-commerce and security alerting systems. These applications usually require that the desired information be matched between numerous sources and sinks based on established subscriptions in a timely manner while a maximized system throughput be achieved to find more matched results. Existing work primarily focuses on only one of the two requirements, either timeliness or throughput. This can lead to an unnecessarily underutilized system or poor guarantees on matching delays. In this paper, we propose an integrated solution that controls both the matching delay and CPU utilization in information dissemination systems to achieve bounded matching delay for high-priority information and maximized system throughput in an example information dissemination system. In addition, we design an admission control scheme to meet the timeliness requirements for selected low-priority information. Our solution is based on optimal control theory for guaranteed control accuracy and system stability. Empirical results on a hardware testbed demonstrate that our controllers can meet the timeliness requirements while achieving maximized system throughput.

Both power and performance are important concerns for enterprise data centers. While various management strategies have been developed to effectively reduce server power consumption by transitioning hardware components to lower power states, they cannot be directly applied to today's data centers that rely on virtualization technologies. Virtual machines running on the same physical server are correlated because the state transition of any hardware component will affect the application performance of all the virtual machines. As a result, reducing power solely based on the performance level of one virtual machine may cause another to violate its performance specification. This paper proposes PARTIC, a two-layer control architecture designed based on well-established control theory. The primary control loop adopts a multi-input multi-output control approach to maintain load balancing among all virtual machines so that they can have approximately the same performance level relative to their allowed peak values. The secondary performance control loop then manipulates CPU frequency for power efficiency based on the uniform performance level achieved by the primary loop. Empirical results demonstrate that PARTIC can effectively reduce server power consumption while achieving required application-level performance for virtualized enterprise servers.

Power control is becoming a key challenge for effectively operating a modern data center. In addition to reducing operating costs, precisely controlling power consumption is an essential way to avoid system failures caused by power capacity overload or overheating due to increasing high server density. Control-theoretic techniques have recently shown a lot of promise for power management because of their better control performance and theoretical guarantees on control accuracy and system stability. However, existing work oversimplifies the problem by controlling a single server independently from others. As a result, at the enclosure level where multiple high-density servers are correlated by common workloads and share common power supplies, power cannot be shared to improve application performance. In this paper, we propose an enclosure-level power controller that shifts power among servers based on their performance needs, while controlling the total power of the enclosure to be lower than a constraint. Our controller features a rigorous design based on an optimal Multi-Input-Multi-Output (MIMO) control theory. We present detailed control problem formulation and transformation to a standard constrained least-squares problem, as well as stability analysis in the face of significant workload variations. We then conduct extensive experiments on a physical testbed to compare our controller with three state-of-the-art controllers: a heuristic-based MIMO control solution, a Single-Input-Single-Output (SISO) control solution, and an improved SISO controller with simple power shifting among servers. Our empirical results demonstrate that our controller outperforms all the three baselines by having more accurate power control and up to 11.8 percent better benchmark performance.

In today's data centers, precisely controlling server power consumption is an essential way to avoid system failures caused by power capacity overload or overheating due to increasingly high server density. While various power control strategies have been recently proposed, existing solutions are not scalable to control the power consumption of an entire large-scale data center, because these solutions are designed only for a single server or a rack enclosure. In a modern data center, however, power control needs to be enforced at three levels: rack enclosure, power distribution unit, and the entire data center, due to the physical and contractual power limits at each level. This paper presents SHIP, a highly scalable hierarchical power control architecture for large-scale data centers. SHIP is designed based on well-established control theory for analytical assurance of control accuracy and system stability. Empirical results on a physical testbed show that our control solution can provide precise power control, as well as power differentiations for optimized system performance. In addition, our extensive simulation results based on a real trace file demonstrate the efficacy of our control solution in large-scale data centers composed of thousands of servers.

Blackouts in our daily life can be disastrous with enormous economic loss. Blackouts usually occur when appropriate corrective actions are not effectively taken for an initial contingency, resulting in a cascade failure. Therefore, it is critical to complete those tasks that are running power grid computing algorithms in the energy management system (EMS) in a timely manner to avoid blackouts. This problem can be formulated as guaranteeing end-to-end deadlines in a distributed real-time embedded (DRE) system. However, existing work in power grid computing runs those tasks in an open-loop manner, which leads to poor guarantees on timeliness thus a high probability of blackouts. Furthermore, existing feedback scheduling algorithms in DRE systems cannot be directly adopted to handle with significantly different timescales of power grid computing tasks. In this paper, we propose a hierarchical control solution to guarantee the deadlines of those tasks in EMS by grouping them based on their characteristics. Our solution is based on well-established control theory for guaranteed control accuracy and system stability. Simulation results based on a realistic workload configuration demonstrate that our solution can guarantee timeliness for power grid computing and hence help to avoid blackouts.

The demand for high performance information dissemination is increasing in many applications, such as e-commerce and security alerting systems. These applications usually require that the desired information be matched between sources and sinks based on established subscriptions in a timely manner while a maximal system throughput be achieved to find more matched results. Existing work primarily focuses on only one of the two requirements, either timeliness or throughput. This can lead to an unnecessarily underutilized system or poor guarantees on matching delays. In this paper, we propose an integrated solution that controls both the matching delay and CPU utilization in information dissemination systems to achieve bounded matching delay for high-priority information and maximized system throughput in an example information dissemination system. Our solution is based on optimal control theory for guaranteed control accuracy and system stability. Empirical results on a physical testbed demonstrate that our controllers can guarantee the timeliness requirements while achieving maximized system throughput.

Power control is becoming a key challenge for effectively operating a modern data center. In addition to reducing operation costs, precisely controlling power consumption is an essential way to avoid system failures caused by power capacity overload or overheating due to increasing high-density. Control-theoretic techniques have recently shown a lot of promise on power management thanks to their better control performance and theoretical guarantees on control accuracy and system stability. However, existing work over-simplifies the problem by controlling a single server independently from others. As a result, at the cluster level where multiple servers are correlated by common workloads and share common power supplies, power cannot be shared to improve application performance. In this paper, we propose a cluster-level power controller that shifts power among servers based on their performance needs, while controlling the total power of the cluster to be lower than a constraint. Our controller features a rigorous design based on an optimal multi-input-multi-output control theory. Empirical results demonstrate that our controller outperforms two state-of-the-art controllers, by having better application performance and more accurate power control.

Power control is becoming a key challenge for effectively operating a modern data center. In addition to reducing operation costs, precisely controlling power consumption is an essential way to avoid system failures caused by power capacity overload or overheating due to increasing high- density. Control-theoretic techniques have recently shown a lot of promise on power management thanks to their better control performance and theoretical guarantees on control accuracy and system stability. However, existing work oversimplifies the problem by controlling a single server independently from others. As a result, at the cluster level where multiple servers are correlated by common workloads and share common power supplies, power cannot be shared to improve application performance. In this paper, we propose a cluster-level power controller that shifts power among servers based on their performance needs, while controlling the total power of the cluster to be lower than a constraint. Our controller features a rigorous design based on an optimal multi-input-multi-output control theory. Empirical results demonstrate that our controller outperforms a state-of-the-art controller, by having better application performance and more accurate power control.

Real-time information dissemination is of increasing importance to our society. Existing work mainly focuses on delivering information from sources to sinks in a timely manner based on established subscriptions, with the assumption that those subscriptions are persistent. However, the bottleneck of many real-time information dissemination systems is actually the matching process to continuously reevaluate such subscriptions between numerous sources and numerous sinks, in response to dynamically varying information attributes at runtime. In this paper, we propose a feedback controller to adaptively meet the response time constraints on metadata matching in an example information dissemination system. Our controller features a rigorous design based on well-established feedback control theory for guaranteed control accuracy and system stability. Empirical results on a physical test-bed demonstrate that our controller outperforms both an open-loop solution and a typical heuristic solution, by having more accurate control and better system quality of service.

Both power and performance are important concerns for enterprise data centers. While various management strategies have been developed to effectively reduce server power consumption by transitioning hardware components to lower-power states, they cannot be directly applied to today's data centers that rely on virtualization technologies. Virtual machines running on the same physical server are correlated, because the state transition of any hardware component will affect the application performance of all the virtual machines. As a result, reducing power solely based on the performance level of one virtual machine may cause another to violate its performance specification. This paper proposes a two-layer control architecture based on well-established control theory. The primary control loop adopts a multi-input-multi-output control approach to maintain load balancing among all virtual machines so that they can have approximately the same performance level relative to their allowed peak values. The secondary performance control loop then manipulates CPU frequency for power efficiency based on the uniform performance level achieved by the primary loop. Empirical results demonstrate that our control solution can effectively reduce server power consumption while achieving required application-level performance for virtualized enterprise servers.

Real-time image transmission is crucial to an emerging class of distributed embedded systems operating in open network environments. Examples include avionics mission re-planning over Link-16, security systems based on wireless camera networks, and online collaboration using camera phones. Meeting image transmission deadlines is a key challenge in such systems due to unpredictable network conditions. In this paper, we present CAMRIT, a Control-based Adaptive Middleware framework for Real-time Image Transmission in distributed real-time embedded systems. CAMRIT features a distributed feedback control loop that meets image transmission deadlines by dynamically adjusting the quality of image tiles. We derive an analytic model that captures the dynamics of a distributed middleware architecture. A control theoretic methodology is applied to systematically design a control algorithm with analytic assurance of system stability and performance, despite uncertainties in network bandwidth. Experimental results demonstrate that CAMRIT can provide robust real-time guarantees for a representative application scenario.