Power and energy management for server systems

This survey shows that heterogeneous server clusters can be made more efficient by conserving power and energy while exploiting information from the service level, such as request priorities established by service-level agreements.     

A density-based topology optimization methodology for thermal energy storage systems

Structural and Multidisciplinary Optimization - As many renewable energy resources are prone to an intermittent production of energy and the electric energy demand varies on daily and seasonal...     

Fuzzy logic-based coordinated control method for multi-type battery energy storage systems

In order to take full advantage of the complementary nature of multi-type energy storage and maximally increase the capability of tracking the scheduled wind power output, a charging–discharging control strategy for a battery energy storage system (BESS) comprising many control coefficients is established, and a power distribution method employing fuzzy control principles to optimize the multi-type BESS is proposed, so as to reduce the error of day-ahead short-term wind power prediction. A simulation analysis, taking a typical wind farm output as an actual data sample, showed that the proposed fuzzy logic control method for the multi-type BESS is uniquely flexible and adaptable in achieving the control effect of improving the capability of tracking the scheduled wind power output.     

Dismountable media management in tertiary storage systems

We describe an adaptive algorithm for tertiary storage media mount management. This predictive longest next reference mount management algorithm attempts to approximate the optimal page replacement policy, OPT     

Smart Sankey picturization for energy management systems in India

AI & SOCIETY - India’s energy demand is predicted to rise by 135% within a span of 20 years. Coping up with surging energy demands requires several reforms in both renewable and...     

Minimizing residential electrical energy costs using microcomputer energy management systems

Load dependent or time dependent pricing structures provide electrical utilities with a means to use their existing capacities more effectively. Assuming that some type of load or time dependent price structure will be implemented by most utilities in the near future, it is worthwhile to assess the use of microcomputer energy control systems for minimizing residential electrical energy costs. This paper discusses the development of an optimizing energy management algorithm to reduce the cost of electricity under either a time-of-use or demand dependent price structure. A computer model which simulates the electrical demand and energy needs of a typical residence was developed to test the effectiveness of the optimizing algorithms. The results are presented for a period of 30 days for each season and price structure, under varying demand profiles. For a customer with an all-electric home using 2000 kWh each month, a savings of $140 a year is very realistic.     

Reliability-conscious energy management for fixed-priority real-time embedded systems with weakly hard QoS-constraint

Aggressive scaling in technology size has dramatically increased the power density and degraded the reliability of real-time embedded systems. In this paper, we study the problem of reliability-conscious energy minimization for scheduling fixed-priority real-time embedded systems with weakly hard QoS-constraint. The weakly hard QoS-constraint is modeled with (m, k)-constraint, which requires that at least m out of any k consecutive jobs of a task meet their deadlines. We first propose a technique that can balance the static and dynamic energy consumption for real-time jobs with better speed determination than the classical strategies during their feasible intervals. Then based on it, we propose an adaptive fixed-priority scheduling scheme to reduce the energy consumption for the system while preserving its reliability. Through extensive simulations, our experiment results demonstrate that the proposed techniques can significantly outperform the previous research in energy performance while satisfying the weakly hard QoS-constraint under the reliability requirement.     

A reliable power management scheme for consistent hashing based distributed key value storage systems

Distributed key value storage systems are among the most important types of distributed storage systems currently deployed in data centers. Nowadays, enterprise data centers are facing growing pressure in reducing their power consumption. In this paper, we propose GreenCHT, a reliable power management scheme for consistent hashing based distributed key value storage systems. It consists of a multi-tier replication scheme, a reliable distributed log store, and a predictive power mode scheduler (PMS). Instead of randomly placing replicas of each object on a number of nodes in the consistent hash ring, we arrange the replicas of objects on nonoverlapping tiers of nodes in the ring. This allows the system to fall in various power modes by powering down subsets of servers while not violating data availability. The predictive PMS predicts workloads and adapts to load fluctuation. It cooperates with the multi-tier replication strategy to provide power proportionality for the system. To ensure that the reliability of the system is maintained when replicas are powered down, we distribute the writes to standby replicas to active servers, which ensures failure tolerance of the system. GreenCHT is implemented based on Sheepdog, a distributed key value storage system that uses consistent hashing as an underlying distributed hash table. By replaying 12 typical real workload traces collected from Microsoft, the evaluation results show that GreenCHT can provide significant power savings while maintaining a desired performance. We observe that GreenCHT can reduce power consumption by up to 35%–61%.     

Secure proof of storage with deduplication for cloud storage systems

Explosion of multimedia content brings forth the needs of efficient resource utilization using the state of the arts cloud computing technologies such as data deduplication. In the cloud computing environments, achieving both data privacy and integrity is the challenging issue for data outsourcing service. Proof of Storage with Deduplication (POSD) is a promising solution that addresses the issue for the cloud storage systems with deduplication enabled. However, the validity of the current POSD scheme stands on the strong assumption that all clients are honest in terms of generating their keys. We present insecurity of this approach under new attack model that malicious clients exploit dishonestly manipulated keys. We also propose an improved POSD scheme to mitigate our attack.     

基于闪存的混合存储系统缓冲区管理算法

由于基于闪存的混合存储系统充分利用了闪存的高速随机读和磁盘的快速顺序写的特性,近年来已经成为了数据库管理系统的二级存储层的高效存储模式,但其I/O访问开销是一个继续提高存储性能的瓶颈.为了降低混合存储系统的I/O访问开销,提出了一种自适应缓冲区管理算法DLSB.该算法根据数据页的逻辑代价和物理代价进行自适应的数据域选择;并在选择的数据域中,比较闪存队列和磁盘队列容量的实际值与理想值来确定数据页的置换,达到了提高I/O访问效率的目的.实验结果表明,该算法有效且可行,显著降低了混合存储系统的I/O访问开销.     

An optimization-model-based interactive decision support system for regional energy management systems planning under uncertainty

In this study, an interactive decision support system (UREM-IDSS) has been developed based on an inexact optimization model (UREM, University of Regina Energy Model) to aid decision makers in planning energy management systems. Optimization modeling, scenario development, user interaction, policy analysis and visual display are seamlessly integrated into the UREM-IDSS. Uncertainties in energy-related parameters are effectively addressed through the interval linear programming (ILP) approach, improving the robustness of the UREM-IDSS for real-world applications. Thus, it can be used as an efficient tool for analyzing and visualizing impacts of energy and environmental policies, regional/community sustainable development strategies, emission reduction measures and climate change in an interactive, flexible and dynamic context. The Region of Waterloo has been selected to demonstrate the applicability and capability of the UREM-IDSS. A variety of scenarios (including a reference case) have been identified based on different energy management policies and sustainable development strategies for in-depth analysis of interactions existing among energy, socio-economy, and environment in the Region. Useful solutions for the planning of energy management systems have been generated, reflecting complex tradeoffs among energy-related, environmental and economic considerations. Results indicate that the UREM-IDSS can be successfully used for evaluating and analyzing not only the effects of an individual policy scenario, but also the variations between different scenarios compared with a reference case. Also, the UREM-IDSS can help tackle dynamic and interactive characteristics of the energy management system in the Region of Waterloo, and can address issues concerning cost-effective allocation of energy resources and services. Thus, it can be used by decision makers as an effective technique in examining and visualizing impacts of energy and environmental policies, regional/community development strategies, emission reduction measures, and climate change within an integrated and dynamic framework.     

Robust invariant sets for constrained storage systems

Several items are produced and stored into n buffers in order to supply an external demand without interruptions. We consider the classical problem of determining control laws and smallest buffer levels guaranteeing that an unknown bounded demand is always satisfied. A simple model with n decoupled integrators and n additive bounded disturbances is employed. The coupling arises from bounds on the total production capacity and on the total demand. Invariant set theory for linear and switched linear systems is exploited to compute robust positive invariant sets and controlled robust invariant sets for two commonly adopted scheduling policies. This paper provides the explicit expression of the invariant sets for any arbitrary n.     

一种云存储系统中重复数据删除机制

基于现有重复数据删除策略,提出了一种基于负载均衡的C/S双端延迟重复数据删除方法.利用基于类型的数据分块方法将数据块分成若干块;利用MD5提取指纹值,与客户端本地的索引表对比指纹,若相同则用指针取代该数据块,具有数据块指纹和数据类型的索引表一同发送至控制器;控制器在收到客户端的请求后,首先根据自己实时监控得到的各服务器的当前状态来选择最佳目标存储节点;服务器端根据数据类型查询不同的索引表以缩小查找范围.对提出的方法的重复数据删除率进行了实验验证,结果表明该机制具有较好的性能表现.     

Sensitivity analysis for multi-variable models: Methodology and application for the economics of energy management systems

A method has been developed enabling analysts to measure the sensitivity of model outcome for a large number of variables. Variables are classified as direct or indirect based on their relationship to the model output. The method involves building an interface between the indirect variables and the direct ones and modifying a basic model before measuring the sensitivity of the model for a given variable. Sensitivity is measured through the computation of the model value; each time a variable is assigned a new value between predetermined limits. The method was formulated analytically and a computer program written to facilitate using the models for survey purposes as well as sensitivity analysis depending on the application.     

Designing storage management schemes for block-structured languages

Continuing the work presented in an earlier paper, we explain the design of the runtime storage management scheme for the Portable Programming Language (PPL). The design method uses three basic ideas-the use of reduced type-expressions, the classification of the components of an object according to the way their sizes vary, and the handling of stored objects as tree structures. It is illustrated by using it to derive a storage management scheme for the Portable Programming Language, and storage management schemes appropriate to Algol 68 and Ada that compare favourably with those already described in the literature.     

Portable electronic storage systems

Notebook, palmtop, and pen-based computers have unique storage requirements. In addition to a rapid growth in capacity to support emerging multimedia applications, portable systems require small, removable media; high shock resistance; thermal resilience; and light-weight, unique form factors dictated by ergonomic constraints and choices. It is argued that storage is the critical enabling technology for many new multimedia applications and addressing its rapidly increasing requirements is key to bringing forward this new technology     

Evaluation of thermal energy storage and recovery for an electrical energy mediator system

Energy storage both electrical and thermal is a rapidly emerging field of interest toward the development of more sustainable energy systems. The inherent inefficiencies associate with electrical storage can be partially overcome when thermal storage that collects and storage the waste thermal energy for alternative uses is integrated. Consequently, thermal energy storage systems are an enabling technology that will allow increased energy efficiency of a community, permit load levelling to reduce peak electricity demand. In order to facilitate a technology evaluation, a sizing strategy is developed for a phase change material (PCM) thermal storage system that determines system requirements under given thermal energy capture and recovery cycles. The sizing process utilizes a simplified one-dimensional heat transfer model that estimates melt times for a phase change material thickness without detailed geometry information. This melt time estimate allows the proportion of phase change material to fluid routing materials to be calculated, giving an estimate of material cost for the thermal storage cell to determine economic feasibility. The model is compared to both experimental data and computational fluid dynamics models in order to determine its limitations. Through a specific example of hydrogen based distributed electrical energy mediator system, the utility of the sizing model in determining the estimated cost of thermal energy storage is demonstrated.     

Survivable information storage systems

As society increasingly relies on digitally stored and accessed information, supporting the availability, integrity and confidentiality of this information is crucial. We need systems in which users can securely store critical information, ensuring that it persists, is continuously accessible, cannot be destroyed and is kept confidential. A survivable storage system would provide these guarantees over time and despite malicious compromises of storage node subsets. The PASIS architecture flexibly and efficiently combines proven technologies (decentralized storage system technologies, data redundancy and encoding, and dynamic self-maintenance) for constructing information storage systems whose availability, confidentiality and integrity policies can survive component failures and malicious attacks