scholarly journals Power and Performance Evaluation of Memory-Intensive Applications

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4089
Author(s):  
Kaiqiang Zhang ◽  
Dongyang Ou ◽  
Congfeng Jiang ◽  
Yeliang Qiu ◽  
Longchuan Yan
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Power Consumption ◽  
Job Scheduling ◽  
Memory System ◽  
Processor Core ◽  
Memory Efficiency ◽  
And Performance ◽  
Reasonable Use ◽  
Server System

In terms of power and energy consumption, DRAMs play a key role in a modern server system as well as processors. Although power-aware scheduling is based on the proportion of energy between DRAM and other components, when running memory-intensive applications, the energy consumption of the whole server system will be significantly affected by the non-energy proportion of DRAM. Furthermore, modern servers usually use NUMA architecture to replace the original SMP architecture to increase its memory bandwidth. It is of great significance to study the energy efficiency of these two different memory architectures. Therefore, in order to explore the power consumption characteristics of servers under memory-intensive workload, this paper evaluates the power consumption and performance of memory-intensive applications in different generations of real rack servers. Through analysis, we find that: (1) Workload intensity and concurrent execution threads affects server power consumption, but a fully utilized memory system may not necessarily bring good energy efficiency indicators. (2) Even if the memory system is not fully utilized, the memory capacity of each processor core has a significant impact on application performance and server power consumption. (3) When running memory-intensive applications, memory utilization is not always a good indicator of server power consumption. (4) The reasonable use of the NUMA architecture will improve the memory energy efficiency significantly. The experimental results show that reasonable use of NUMA architecture can improve memory efficiency by 16% compared with SMP architecture, while unreasonable use of NUMA architecture reduces memory efficiency by 13%. The findings we present in this paper provide useful insights and guidance for system designers and data center operators to help them in energy-efficiency-aware job scheduling and energy conservation.

scholarly journals Fuzzy-Based Thermal Management Scheme for 3D Chip Multicores with Stacked Caches

Electronics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 346 ◽  
Author(s):  
Lili Shen ◽  
Ning Wu ◽  
Gaizhen Yan
Keyword(s):  
Power Consumption ◽  
Thermal Management ◽  
System Performance ◽  
Control Policy ◽  
Three Dimension ◽  
Processor Core ◽  
Management Scheme ◽  
And Performance ◽  
On Chip ◽  
Silicon Vias

By using through-silicon-vias (TSV), three dimension integration technology can stack large memory on the top of cores as a last-level on-chip cache (LLC) to reduce off-chip memory access and enhance system performance. However, the integration of more on-chip caches increases chip power density, which might lead to temperature-related issues in power consumption, reliability, cooling cost, and performance. An effective thermal management scheme is required to ensure the performance and reliability of the system. In this study, a fuzzy-based thermal management scheme (FBTM) is proposed that simultaneously considers cores and stacked caches. The proposed method combines a dynamic cache reconfiguration scheme with a fuzzy-based control policy in a temperature-aware manner. The dynamic cache reconfiguration scheme determines the size of the cache for the processor core according to the application that reaches a substantial amount of power consumption savings. The fuzzy-based control policy is used to change the frequency level of the processor core based on dynamic cache reconfiguration, a process which can further improve the system performance. Experiments show that, compared with other thermal management schemes, the proposed FBTM can achieve, on average, 3 degrees of reduction in temperature and a 41% reduction of leakage energy.

scholarly journals Optimizing Power Consumption of Freight Railroad Bearings Using Laboratory Experimental Data

2020 ◽  
Author(s):  
Carlos E. Lopez ◽  
Constantine Tarawneh ◽  
Arturo Fuentes ◽  
Harry Siegal
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Power Consumption ◽  
Optimal Operating ◽  
Speed Condition ◽  
Load Train ◽  
Train Speed ◽  
Railroad Bearings ◽  
Railroad Bearing ◽  
The University

Abstract Based on projected freight truck fuel efficiency, freight railroad and equipment suppliers need to identify, evaluate and implement technologies and/or operating practices to maintain traditional railroad economic competitiveness. The railway industry uses systems that record the total energy efficiency of a train but not energy efficiency or consumption by components. Lowering the energy consumption of certain train components will result in an increase in its overall energy efficiency, which will yield cost benefits for all the stakeholders. One component of interest is the railroad bearing whose power consumption varies depending on several factors that include railcar load, train speed, condition of bearing whether it is healthy or defective, and type of defect. Being able to quantify the bearing power consumption, as a function of the variables mentioned earlier, would make it possible to obtain optimal operating condition ranges that minimize energy consumption and maximize train energy efficiency. Several theoretical studies were performed to estimate the power consumption within railroad bearings, but those studies lacked experimental validation. For almost a decade now, the University Transportation Center for Railway Safety (UTCRS) at the University of Texas Rio Grande Valley (UTRGV) has been collecting power consumption data for railroad bearings under various loads, speeds, ambient temperatures, and bearing condition. The objective of this ongoing study is to use the experimentally acquired power consumption to come up with a correlation that can be used to quantify the bearing power consumption as a function of load, speed, ambient temperature, and bearing condition. Once obtained, the model can then be used to determine optimal operating practices that maximize the railroad bearing energy efficiency. In addition, the developed model will provide insight into possible areas of improvement for the next generation of energy efficient railroad bearings. This paper will discuss ongoing work including experimental setup and findings of energy consumption of bearings as function of railcar load, train speed, condition of bearing whether it is healthy or defective, and type of defect. Findings of energy consumption are converted into approximations of diesel gallons to quantify the effect of nominal energy consumption of the bearings and show economic value and environmental impact.

scholarly journals ENERGY RETROFITS FOR IMPROVING ENERGY EFFICIENCY IN BUILDINGS: A REVIEW OF HVAC AND LIGHTING SYSTEMS

2021 ◽  
Author(s):  
M.R. Amjath ◽  
◽  
H. Chandanie ◽  
S.D.I.A. Amarasinghe ◽  
◽  
...  
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Energy Use ◽  
Implementation Process ◽  
Energy Performance ◽  
Existing Buildings ◽  
Energy Auditing ◽  
Lighting Systems ◽  
Effective Decision Making ◽  
And Performance

It has been observed that inefficient buildings consume three to five times more energy than efficient buildings. Subsequently, improving the Energy Efficiency (EE) of existing buildings, which account for a significant portion of the energy consumption of the building sector, has become a top priority. Also, Heating, Ventilation, and Air Conditioning (HVAC) and lighting systems typically account for three-quarters of a building's energy consumption. Hence, focus on the energy efficiency improvements associated with these subsystems is entailed to optimise the energy use of buildings in comparison to other energy consumers. Energy Retrofit (ER) is defined as the main approach in improving the energy efficiency of buildings to achieve energy reduction goals. Nevertheless, there is a general lack of awareness regarding ER. Thus, the purpose of this article is to bridge this research gap by critically reviewing the applicable literature on ER. The paper first analysed the role of retrofits in buildings concerning optimising energy performance. The paper also discusses the implementation process of ER, which includes five steps viz. pre-retrofit survey, energy auditing, and performance assessment, identification of suitable and feasible retrofit options, site implementation and commissioning, and validation and verification. Further, different types of ER applicable to HVAC and lighting systems are discussed. In their endeavor to enhance the EE of existing buildings, practitioners could apply the findings of this study, as a basis to understand the available ER types and as a measure to gauge the efficiency of existing buildings, which will facilitate effective decision-making.

scholarly journals THE EFFECT OF DATA-REUSE TRANSFORMATIONS ON MULTIMEDIA APPLICATIONS FOR APPLICATION SPECIFIC PROCESSORS

2014 ◽  
pp. 102-109
Author(s):  
N. Vassiliadis ◽  
A. Chormoviti ◽  
N. Kavvadias ◽  
S. Nikolaidis
Keyword(s):  
Energy Consumption ◽  
Power Consumption ◽  
Multimedia Applications ◽  
Data Reuse ◽  
Instruction Set ◽  
Specific Instruction ◽  
Data Transfers ◽  
And Performance ◽  
And Storage ◽  
Application Specific

Multimedia applications are characterized by a high number of data transfers and storage operations. Appropriate transformations can be applied at the algorithmic level to improve crucial implementation characteristics. In this paper, the effect of data-reuse transformations on power consumption and performance of multimedia applications, realized on an Application Specific Instruction set Processor (ASIP), is examined. An ASIP for multimedia applications designed based on a complete methodology is used to evaluate this effect. Results prove the efficiency of the ASIP solution and indicate benefits from the use of the data-reuse transformations in terms of energy consumption and performance. Also, preliminary results from the exploitation of instruction buffering technique to reduce the energy consumption of the ASIP are presented.

scholarly journals Smart metering application for power efficiency studies

2015 ◽  
Vol 4 (1) ◽  
pp. 78
Author(s):  
Cristian Tudoran ◽  
Stefan Albert ◽  
Dorin N. Dadarlat ◽  
Carmen Tripon ◽  
Sorin Dan Anghel
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Power Consumption ◽  
Monitoring System ◽  
Data Center ◽  
Power Efficiency ◽  
Consumption Patterns ◽  
Smart Metering ◽  
Research Teams ◽  
Energy Consumption Patterns

Improving the energy efficiency of our Institute’s data center is an ambitious challenge for our research teams. Understanding how the energy is consumed in each segment of the system becomes fundamental in order to minimize the overall energy consumed by the system itself. In this paper, we propose an experimentally–driven approach to develop a simple and accurate power consumption and temperature monitoring system. In this work we focused our attention on the monitoring, measurement of the energy consumption patterns of our data center system, at INCDTIM Cluj-Napoca, Romania.

Improving Energy-Efficiency of Scientific Computing Clusters

2012 ◽  
pp. 1916-1933
Author(s):  
Tapio Niemi ◽  
Jukka Kommeri ◽  
Ari-Pekka Hameri
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Operations Management ◽  
Scientific Computing ◽  
High Energy Physics ◽  
High Energy ◽  
Test Results ◽  
Processor Core ◽  
Processing Times ◽  
Scheduling Method

The authors applied operations management principles on scheduling and allocation to scientific computing clusters to decrease energy consumption and to increase throughput. They challenged the traditional one job per one processor core scheduling method commonly used in scientific computing with parallel processing and bottleneck management. The authors tested the effect of increased parallelism by using different test applications related to high-energy physics computing. The test results showed that at best their methods both decreased energy consumption down to 40% and increased throughput up to 100%, compared to the standard one task per CPU core method. The trade-off is that processing times of individual tasks get longer, but in scientific computing, the overall throughput and energy-efficiency are often more important.

scholarly journals Efficient energy consumption for indoor mobile robot prototype under illumination

2018 ◽  
Vol 197 ◽  
pp. 11016
Author(s):  
Seilla Angelina ◽  
Shofuro Afifah ◽  
Paramadina Susamti ◽  
Rizki Ardianto Priramadhi ◽  
Denny Darlis
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Power Consumption ◽  
Mobile Robot ◽  
Robot Navigation ◽  
Visible Light Communication ◽  
Mobile Robot Navigation ◽  
Energy Crisis ◽  
Lighting System ◽  
Large Power

In the next 20 years, energy consumption is expected to increase up to 30% and it will affect energy crisis. Energy crisis can be resolved by energy efficiency. The context of this paper is about the energy efficiency of a mobile robot in the industrial warehouse. Communications media which commonly used in mobile robot navigation such as Laser need large power consumption. In order to reduce power consumption, the system of this paper is designed to use visible light communication (VLC) for mobile robot navigation because VLC only utilize lights as the transmitter. Method of this paper is sending the data contained navigation coordinates which modulated on the lighting system, then data will be received by the photodetector and processed as mobile robot's navigation. From above system, by using 5,68-watt power on lighting system can be used to transmit navigation data with the range up to 2 meters. In the receiver side, a photodetector which uses as receiver generate maximum power 4,14 watt at 10 cm of height between transmitter and receiver while minimum generated power is 3,21 watt at 250 cm of height. The conclusion of this paper is generated power by a photodetector in navigation process mobile robot is affected by angle and distance between transmitter and receiver.

scholarly journals Design Sleep Mode and Wakeup Method for OpenFlow Switches

2015 ◽  
pp. 10
Author(s):  
Tran Hoang Vu ◽  
Vu Cong Luc
Keyword(s):  
Energy Consumption ◽  
Power Consumption ◽  
Performance Evaluations ◽  
Total Power ◽  
Sleep Mode ◽  
Total Power Consumption ◽  
Switch Mode ◽  
Reduce Energy Consumption ◽  
Management Modes ◽  
And Performance

In  this  paper,  we  present  a  design  and  an evaluation  of  two  power  management  modes  that reduce the  energy  consumption  of OpenFlow switches. First,  we  define  two  new  low  power  modes:  SLEEP PORT  and  SLEEP  SWITCH,  which  reduce   energy consumption   in  cases  where  packets  on  port  or switches  are  absent.  Second,  we  present  a  Wake  on LAN  (WOL)  method  for  OpenFlow  Switches  to  wake up  Ethernet  ports  or  the  whole  switch  from  inactive states.  Finally,  we  describe  our  design,  experimental results and  performance evaluations. Our results show that the control SLEEP PORT mode on a switch might save  about 9.8% power consumption per  port,  and  up to about 60% of total power consumption of the switch with SLEEP  SWITCH mode.  In  addition,  we  will implement  this  method  to  Openflow  Switch  bases  on NetFPGA- 10 Gigabit in the future.

scholarly journals Evaluating of daylighting in selected office room: Case of Study

2019 ◽  
Vol 14 (1) ◽  
pp. 7-15
Author(s):  
Dolnikova Erika
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Power Consumption ◽  
Simulation Program ◽  
Natural Light ◽  
Work Space ◽  
Human Need ◽  
Healthy Work ◽  
Privacy Issues

Abstract On average, we spend 90% of our time indoor particularly at work and a healthy work space is essential to that feeling of wellbeing. In a typical building, lighting accounts for up to 40% of energy consumption. Allowing more natural light to penetrate the building and controlling both the light and heat components of power consumption, will result in significant reductions. However, using natural light doesn´t come without some issues. Glare, overheating, variability and privacy issues can all cause problems. Daylight is a basic human need, which is highlighted by the provision of transparent and translucent surfaces to all occupied spaces that we see around us. In many cases, the drive to create healthier, more occupant-conscious buildings works hand in hand with the requirement for greater energy efficiency. This article presents illumination of indoor workspace using daylight lighting. Measured values were compared with values calculated by simulation program Velux Daylight Visualizer 3.

Improving Energy-Efficiency of Scientific Computing Clusters

2013 ◽  
pp. 1-19 ◽  
Author(s):  
Tapio Niemi ◽  
Jukka Kommeri ◽  
Ari-Pekka Hameri
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Operations Management ◽  
Scientific Computing ◽  
High Energy Physics ◽  
High Energy ◽  
Test Results ◽  
Processor Core ◽  
Processing Times ◽  
Scheduling Method

The authors applied operations management principles on scheduling and allocation to scientific computing clusters to decrease energy consumption and to increase throughput. They challenged the traditional one job per one processor core scheduling method commonly used in scientific computing with parallel processing and bottleneck management. The authors tested the effect of increased parallelism by using different test applications related to high-energy physics computing. The test results showed that at best their methods both decreased energy consumption down to 40% and increased throughput up to 100%, compared to the standard one task per CPU core method. The trade-off is that processing times of individual tasks get longer, but in scientific computing, the overall throughput and energy-efficiency are often more important.

Sign in / Sign up

Export Citation Format

Share Document