针对电压可调处理器的低功耗设计策略

在便携式系统的低功耗设计中，动态电源管理（Dynamic Power Management，DPM）和动态电压调节（Dynamic Voltage Scaling，DVS）已经成为比较通用的技术，并且很多实验数据表明DVS省电性能比DPM更为优越。本文针对电压可调的处理器，在理论证明的基础上提出了一种能够跟踪工作负载需求变化，在保证给定任务组中所有任务性能的同时实现系统能耗最优化的电压调节策略EOVSP（Energy Optimal Voltage Scaling Policy）。实验结果也表明，该策略在满足系统性能要求的前提下具有比一般DPM策略更好的省电性能。     

Dynamic Power Optimization Targeting User Delays in Interactive Systems

Power has become a major concern for mobile computing systems such as laptops and handhelds, on which a significant fraction of software usage is interactive instead of compute-intensive. For interactive systems, an analysis shows that more than 90 percent of system energy and time is spent waiting for user input. Such idle periods provide vast opportunities for dynamic power management (DPM) and voltage scaling (DVS) techniques to reduce system energy. In this work, we propose to utilize user interface information to predict user delays based on human-computer interaction history and theories from the field of psychology. We show that such a delay prediction can be combined with DPM/DVS for aggressive power optimization. We verify the effectiveness of our methodologies with usage traces collected on a personal digital assistant (PDA) and a system power model based on accurate measurements. Experiments show that using predicted user delays for DPM/DVS achieves an average of 21.9 percent system energy reduction with little sacrifice in user productivity or satisfaction     

基于MSR模型的动态功耗管理策略

系统级动态功耗管理(Dynamic Power Management,DPM)策略根据系统状态和负载,动态地调整系统配置,从而能够有效降低系统功耗.传统的DPM策略仅从设备的角度考察工作负载状况,忽略了工作负载的应用特征.本文从任务的角度分析负载,提出新颖的多请求源(Multiple Service Requesters,MSR)系统级功耗管理的模型,以及基于该模型的自适应超时策略(Multiple-Service-Requester-Based Timeout Policy,MSRBTP).实验表明,与传统DPM策略相比较,在非平稳的应用环境下,MSRBTP策略具有更好更稳定的节能效果.     

一种数字信号处理器的动态功耗管理方案

动态功耗管理是一种系统级低功耗设计技术，降低功耗的思路是根据系统当前负载动态调整时钟频率或者关闭时钟。文章以数字信号处理器为模型，提出了一种系统属性可调节的动态功耗管理方案，它支持通过软硬件配合对功耗进行灵活的动态管理，其管理策略采用了适应性预测算法，并引入非确定性因子。实验结果表明，该方案可以大大降低数字信号处理器的功耗。     

Hierarchical power management of a system with autonomously power-managed components using reinforcement learning

This paper presents a hierarchical dynamic power management (DPM) framework based on reinforcement learning (RL) technique, which aims at power savings in a computer system with multiple I/O devices running a number of heterogeneous applications. The proposed framework interacts with the CPU scheduler to perform effective application-level scheduling, thereby enabling further power savings. Moreover, it considers non-stationary workloads and differentiates between the service request generation rates of various software application. The online adaptive DPM technique consists of two layers: component-level local power manager and system-level global power manager. The component-level PM policy is pre-specified and fixed whereas the system-level PM employs temporal difference learning on semi-Markov decision process as the model-free RL technique, and it is specifically optimized for a heterogeneous application pool. Experiments show that the proposed approach considerably enhances power savings while maintaining good performance levels. In comparison with other reference systems, the proposed RL-based DPM approach, further enhances power savings, performs well under various workloads, can simultaneously consider power and performance, and achieves wide and deep power-performance tradeoff curves. Experiments conducted with multiple service providers confirm that up to 63% maximum energy saving per service provider can be achieved.     

PBALT动态电源管理策略

在嵌入式和便携式系统的低功耗设计中，动态电源管理（Dynamic Power Management，DPM）是一个非常重要的技术。DPM本质上是一种“在线”问题，因为PM（Power Management）策略必须在系统所有输入信息可用之前就能够对系统资源的使用情况做出正确的判断。本文在对自适应学习树（Adaptive Learning Tree，ALT）不足之处进行分析的基础上，提出了一种新颖的DPM策略——PBALT（Probability-Based ALT）。实验结果表明，PBALT具有很强的稳定性；而且在对空闲时段的预测准确性方面，PBALT比ALT具有更高的命中率。     

Instruction Scheduling for Low Power

Reducing energy consumption has become an important issue in designing hardware and software systems in recent years. Although low power hardware components are critical for reducing energy consumption, the switching activity, which is the main source of dynamic power dissipation in electronic systems, is largely determined by the software running on these systems.In this paper, we present and evaluate several instruction scheduling algorithms that reorder a given sequence of instructions taking into account the energy considerations. We first compare a performance-oriented scheduling technique with three energy-oriented instruction scheduling algorithms from both performance (execution cycles of the resulting schedules) and energy consumption points of view. Then, we propose three scheduling algorithms that consider energy and performance at the same time. Our experimentation with these scheduling techniques shows that the best scheduling from the performance perspective is not necessarily the best scheduling from the energy perspective. Further, scheduling techniques that consider both energy and performance simultaneously are found to be desirable, that is, these techniques are quite successful in reducing energy consumption and their performance (in terms of execution cycles) is comparable to that of a pure performance-oriented scheduling. We also illuminate the inherent approximations and difficulties in building energy models for enabling energy-aware instruction scheduling and explore alternative options using cycle-accurate energy simulator. The simulation results show that the energy-oriented scheduling reduces energy consumption by up to 30% compared to the performance-oriented scheduling.     

Specification and analysis of power-managed systems

Dynamic power management encompasses several techniques for reducing energy dissipation in electronic systems by selective slowdown or shutdown of components. We present a theoretical framework for explaining and classifying different approaches to power management. Within this framework, we model power-manageable components, workloads, and controllers as discrete-event systems (DESs). The structure of these DESs is specified in terms of physical states (representing operation modes) and events (triggering state transitions), while system behavior is specified in terms of next-event and next-state functions. In particular, nondeterministic next-event and next-state functions are modeled by conditional probability distributions, according to generalized semi-Markov processes (GSMPs). The modeling framework provides a general denotational model for system specification and a rigorous execution semantics that enables event-driven simulation. We introduce a modeling framework, built on top of MathWork's Simulink, supporting the specification and execution of our model. In particular, we present templates for the Simulink simulator to execute GSMP models, and we describe how to use such templates for specifying, analyzing, and optimizing dynamic power-managed systems. Finally, we demonstrate the expressive power and versatility of the proposed approach by using the modeling framework and the simulator for the analysis of representative real-life case studies, including the Intel Xscale processor architecture, a multitasking real-time system, and a sensor network.     

Multidimensional Adaptive Power Management for Low-Power Operation of Wireless Devices

Currently, wireless circuits are designed to meet minimum quality-of-service requirements under worst case wireless link conditions (interference, noise, multipath effects), leading to high power consumption when the channel is not worst case. In this work, we develop a multidimensional adaptive power management approach that optimally trades-off power versus performance across temporally changing operating conditions by concurrently tuning control parameters in the RF and digital baseband components of the wireless receiver. Simulation and hardware results indicate significant power savings in the receiver using the proposed approach while maintaining the system bit error rate specification.      

Uncertainty-Aware Dynamic Power Management in Partially Observable Domains

This paper tackles the problem of dynamic power management (DPM) in nanoscale CMOS design technologies that are typically affected by increasing levels of process and temperature variations and fluctuations due to the randomness in the behavior of silicon structure. This uncertainty undermines the accuracy and effectiveness of traditional DPM approaches. This paper presents a stochastic framework to improve the accuracy of decision making during dynamic power management, while considering manufacturing process and/or environment induced uncertainties. More precisely, variability and uncertainty at the system level are captured by a partially observable semi-Markov decision process with interval-based definition of states while the policy optimization problem is formulated as a mathematical program based on this model. Experimental results with a RISC processor in 65-nm technology demonstrate the effectiveness of the technique and show that the proposed uncertainty-aware power management technique ensures system-wide energy savings under statistical circuit parameter variations.      

Dynamic channel allocation in interference-limited cellular systemswith uneven traffic distribution

Most recently proposed wireless dynamic channel allocation methods have used carrier-to-interference (C/I) information to increase the system performance. Power control is viewed as essential for interference-limited systems. However, the performance of such systems under an imbalance of load among cells, as may occur often in microcells, is largely unknown. Here, we study a typical interference-limited dynamic channel allocation policy. Calls are accepted if a channel can be assigned that will provide a minimum C/I, and power control and intracell handoffs are used to maintain this level. We focus on the relationship between system performance and the amount of imbalance in load among neighboring cells. Previous studies for systems that do not use C/I information have found that dynamic channel allocation (DCA) outperforms fixed channel allocation (FCA) in all but heavily loaded systems with little load imbalance. We present two principal new results. First, we find that with use of C/I information, the difference in performance between FCA and DCA (in terms of throughput or blocking probability) is increasing with load imbalance. DCA was found to be more effective in congestion control at the cost of a slightly lower call quality. Second, we find that use of power control to maintain a minimum C/I results in two equilibrium average power levels for both DCA and FCA, with DCA using a higher average power than FCA, and that while DCA's power is increasing with load imbalance, FCA's average power is decreasing with load imbalance     

A Dynamic Thermal Management Circuit for System-On-Chip Designs

A novel fully integrated dynamic thermal management circuit for system-on-chip design is proposed. Instead of worst-case thermal management used in conventional systems, this design yields continual monitoring of thermal activity and reacts to specified conditions. With the above system, we are able to incorporate on-chip power/speed modulation and integrated multi-stage fan controllers, which allows us to achieve nominal power dissipation and ensure operation within specification. Both architecture and circuitry are optimized for modern system-on-chip designs. This design yields intricate control and optimal mangement with little system overhead and minimum hardware requirements, as well as provides the flexibility to support different thermal mangement algorithms.     

基于BQ24610的智能锂电池充电系统设计

BQ24610是TI公司推出的一教比较先进的,面向5V至28V电压输入的锂离子电池供电应用开关模武独立电池充电器IC。基于便携武分子筛制氧机的电源管理的设计需求,经过对一系列芯片原理、性能、参数设置的分析讨论,最后我们选用BQ24610芯片作为该电源管理部分的主控制芯片,结合部分外围电路,实现该设计的电源的自动选择、内部回路补偿、内部软启动、动态电源管理（DPM）、精确的充电电流与电压调节、预充电、充电终止、适配器电流调节以及充电状态监控等功能。最后把该设计制成实验板,经过反复调试,测试结果实现了预期性能指标。     

DYNAMO: A Cross-Layer Framework for End-to-End QoS and Energy Optimization in Mobile Handheld Devices

In this paper, we present the design and implementation of a cross-layer framework for evaluating power and performance tradeoffs for video streaming to mobile handheld systems. We utilize a distributed middleware layer to perform joint adaptations at all levels of system hierarchy - applications, middleware, OS, network and hardware for optimized performance and energy benefits. Our framework utilizes an intermediate server in close proximity of the mobile device to perform end-to-end adaptations such as admission control, intelligent network transmission and dynamic video transcoding. The knowledge of these adaptations are then used to drive "on-device" adaptations, which include CPU voltage scaling through OS based soft realtime scheduling, LCD backlight intensity adaptation and network card power management. We first present and evaluate each of these adaptations individually and subsequently report the performance of the joint adaptations. We have implemented our cross-layer framework (called DYNAMO) and evaluated it on Compaq iPaq running Linux using streaming video applications. Our experimental results show that such joint adaptations can result in energy savings as high as 54% over the case where no optimization are used while substantially enhancing the user experience on hand-held systems.     

A Cooperative Management Scheme for Power Efficient Implementations of Real-Time Operating Systems on Soft Processors

A cooperative management scheme for power efficient implementations of real-time operating systems on field-programmable gate-array (FPGA)-based soft processors is presented. Dedicated power management hardware peripherals are tightly coupled to a soft processor by utilizing its configurability. These hardware peripherals manage tasks and interrupts in cooperation with the soft processor, while retaining the real-time responsiveness of the operating system. More specifically, the hardware peripherals perform the following power management functionalities: (1) control the on-chip clock distribution network for driving the soft processor, its hardware peripherals, and the bus interfaces between them; (2) perform task and interrupt management responsibilities of the operating system when the soft processor is turned off; and (3) selectively wake up the soft processor and its hardware components, and put them into proper activation states based on the hardware resource requirements of the tasks under execution. The implementations of two popular real-time operating systems on a state-of-the-art FPGA device are presented. Measurements on an experimental board show that the proposed power management scheme can lead to significant power savings.     

Designing risk-management strategies for critical engineeringsystems

Effective management of the tradeoff between productivity and safety is a challenge in many industries that operate critical engineering systems such as nuclear power plants or offshore oil platforms. The objective of this paper is to link risk-management strategies to a system's safety and productivity over its lifetime. These strategies involve decisions that affect the physical system both directly and indirectly though the performance of the personnel that design, construct, or operate it. The problem is thus to link the different components of such risk-management strategies to human and system performance. In this paper, we present the basis of a decision support framework for the design and assessment of different risk-management strategies in risk-critical systems. First we discuss the inherent difficulty in balancing productivity and safety in the short and the long term and the different components of a risk-management strategy. We present a model involving both production failures and catastrophic failures as a function of strategic alternatives. This model is based on a probabilistic and dynamic risk analysis of a system, linking different aspects of risk-management strategies to specific characteristics of the physical system. We show how this model, coupled with explicit value judgments, can be used to design optimal strategies, e.g., to balance initial costs, long-term operations and maintenance costs, and the potential costs of catastrophic failures. To illustrate the concepts we use the case of the maintenance of a corporate airplane     

UbiFOS: A Small Real‐Time Operating System for Embedded Systems

The ubiquitous flexible operating system (UbiFOS) is a real‐time operating system designed for cost‐conscious, low‐power, small to medium‐sized embedded systems such as cellular phones, MP3 players, and wearable computers. It offers efficient real‐time operating system services like multi‐task scheduling, memory management, inter‐task communication and synchronization, and timers while keeping the kernel size to just a few to tens of kilobytes. For flexibility, UbiFOS uses various task scheduling policies such as cyclic time‐slice (round‐robin), priority‐based preemption with round‐robin, priority‐based preemptive, and bitmap. When there are less than 64 tasks, bitmap scheduling is the best policy. The scheduling overhead is under 9 µs on the ARM926EJ processor. UbiFOS also provides the flexibility for user to select from several inter‐task communication techniques according to their applications. We ported UbiFOS on the ARM9‐based DVD player (20 kB), the Calm16‐based MP3 player (under 7 kB), and the ATmega128‐based ubiquitous sensor node (under 6 kB). Also, we adopted the dynamic power management (DPM) scheme. Comparative experimental results show that UbiFOS could save energy up to 30% using DPM.     

Dynamic power management in new architecture of wireless sensor networks

Dynamic power management (DPM) technology has been widely used in sensor networks. Though many specific technical challenges remain and deserve much further study, the primary factor currently limiting progress in sensor networks is not these challenges but is instead the lack of an overall sensor network architecture. In this paper, we first develop a new architecture of sensor networks. Then we modify the sleep state policy developed by Sinha and Chandrakasan in (IEEE Design Test Comput. 2001; 18 (2):62–74) and deduce that a new threshold satisfies the sleep‐state transition policy. Under this new architecture, nodes in deeper sleep states consume lower energy while asleep, but require longer delays and higher latency costs to awaken. Implementing DPM with considering the battery status and probability of event generation will reduce the energy consumption and prolong the whole lifetime of the sensor networks. We also propose a new energy‐efficient DPM, which is a modified sleep state policy and combined with optimal geographical density control (OGDC) (Wireless Ad Hoc Sensor Networks 2005; 1 (1–2):89–123) to keep a minimal number of sensor nodes in the active mode in wireless sensor networks. Implementing dynamic power management with considering the battery status, probability of event generation and OGDC will reduce the energy consumption and prolong the whole lifetime of the sensor networks. Copyright © 2008 John Wiley & Sons, Ltd.     

基于时间期望表的DPM预测策略

系统级动态功耗管理(DPM,Dynamic Power Management)策略根据系统状态和负载的变化,动态地调整系统配置,从而能够降低系统功耗.PBALT(Probability Based Adaptive Learning Tree)预测策略以预测正确率为单一评估标准,存在高预测正确率高功耗的问题.本文提出基于空闲时间期望表(IET,Idle Expectation Table)的DPM预测策略IETBP(Idle Expectation Table Based Prediction),通过对空闲时间的分布和状态的误预测能耗的分析,以空闲时间的期望作为预测依据,从而克服了PBALT所存在的问题,并降低了算法复杂度.仿真实验表明与PBALT策略相比,IETBP策略在较低预测正确率的情况下能够更有效地降低部件的功耗.     

Performance analysis of an improved dynamic power management model in wireless sensor node

The energy consumption in the wireless sensor networks is a very critical issue which attracts immediate attention for the sake of the growing demand of the billion dollar market in future. The Dynamic Power Management (DPM) technique is a way of controlling and saving the energy usage in a sensor node. Previously, researchers have proposed lifetime improving stochastic models for wireless sensor networks and limited work has been done focusing on the wireless sensor node. This paper proposes an analyser based Semi-Markov model for DPM in the event-driven sensor node. The power consumption comparison with previously proposed models without this analyser shows the analyser significant contributes to lifetime improvement. The improved model is more power efficient, presents how the DPM model observes the input event arrival and power states of the sensor node components, and then dynamically manages the power consumption of the overall system. Further, to observe the effect of event arrival, missed events, waiting time, processor utilization on the power consumption and lifetime, the proposed DPM system with the single server queuing model is developed.