scholarly journals On the impact of sampling frequency on software energy measurements

Author(s):  
Rubén Saborido ◽  
Venera Arnaoudova ◽  
Giovanni Beltrame ◽  
Foutse Khomh ◽  
Giuliano Antoniol

Energy consumption is a major concern when developing and evolving mobile applications and researchers are investigating ways to reduce energy consumption. We conjecture that these studies are at the border between hardware and software and we must be careful on how the energy consumption is measured. To the best of our knowledge, no previous work investigates how much energy and power consumption is due to high frequency events missed when sampling at low frequencies such as 10 kHz and verified the error at the precision of method level. In this paper, we propose an approach for accurate measurements of the energy consumption of mobile applications. We apply the proposed approach to assess the energy consumption of 21 mobile, closed source, applications and four open source Android applications. We show that by sampling at 10 kHz one may expect a median error of 8%, however, such error may be as high as 50%.

Author(s):  
Rubén Saborido ◽  
Venera Venera Arnaoudova ◽  
Giovanni Beltrame ◽  
Foutse Khomh ◽  
Giuliano Antoniol

Energy consumption is a major concern when developing and evolving mobile applications. The user wishes to access fast and powerful mobile applications, which is usually in contrast to optimized battery life and heat generation. The software engineering community have acknowledged the relevance of the problem and researchers are investigating ways to reduce energy consumption, for example by examining which library, device configuration, and applications parameters should be used to promote long battery life. We conjecture that these studies are at the border between hardware and software and we must be careful on how the energy consumption is measured and how the energy consumption is attributed to methods and libraries.To the best of our knowledge, no previous work investigates how much energy and power consumption is due to high frequency events missed when sampling at low frequencies such as 10 kHz and verified the error at the precision of method level. Low frequency sampling is a rough approximation that hinders the understanding of fine grain details: the real picture of energy consumption as well as the root causes are missed. This has profound implications on the choice of methods to evolve or components to replace.In this paper, we propose an approach for accurate measurements of the energy consumption of mobile applications. We apply the proposed approach to assess the energy consumption of 21 mobile, closed source, applications and four open source Android applications.We show that by sampling at 10 kHz one may expect a median error of 8%, however, such error may be as high as 50% for short fast executing methods. Finally, we revisit a previous approach that estimates the energy consumption of methods based on execution time and found that it can miss as much as 84% of the energy, with a median of 30%.


2015 ◽  
Author(s):  
Rubén Saborido ◽  
Venera Venera Arnaoudova ◽  
Giovanni Beltrame ◽  
Foutse Khomh ◽  
Giuliano Antoniol

Energy consumption is a major concern when developing and evolving mobile applications. The user wishes to access fast and powerful mobile applications, which is usually in contrast to optimized battery life and heat generation. The software engineering community have acknowledged the relevance of the problem and researchers are investigating ways to reduce energy consumption, for example by examining which library, device configuration, and applications parameters should be used to promote long battery life. We conjecture that these studies are at the border between hardware and software and we must be careful on how the energy consumption is measured and how the energy consumption is attributed to methods and libraries.To the best of our knowledge, no previous work investigates how much energy and power consumption is due to high frequency events missed when sampling at low frequencies such as 10 kHz and verified the error at the precision of method level. Low frequency sampling is a rough approximation that hinders the understanding of fine grain details: the real picture of energy consumption as well as the root causes are missed. This has profound implications on the choice of methods to evolve or components to replace.In this paper, we propose an approach for accurate measurements of the energy consumption of mobile applications. We apply the proposed approach to assess the energy consumption of 21 mobile, closed source, applications and four open source Android applications.We show that by sampling at 10 kHz one may expect a median error of 8%, however, such error may be as high as 50% for short fast executing methods. Finally, we revisit a previous approach that estimates the energy consumption of methods based on execution time and found that it can miss as much as 84% of the energy, with a median of 30%.


2021 ◽  
Author(s):  
Sara Damyar

Building envelope retrofits is one of the options available to reduce energy consumption of postwar MURBs in Toronto. This study evaluates the impact of building envelope retrofits that meet current standards on energy consumption of a Toronto postwar MURB; utilizing eQUEST energy simulation software. Further upgrades also take place to evaluate how the impact of building envelope retrofits on energy use can be increased and optimized for all assemblies of building envelope and airtightness. Moreover, the retrofit strategies are ranked based on cost and energy-saving effectiveness. The results of the analysis reveal that building envelope retrofit based on OBC-2012 standards can reduce the energy consumption by up to 44%. Furthermore, the optimal RSI values of all building envelope components were found to be equal or less than code requirements which outcomes significant energy savings. Lastly, the ranking of the strategies helps to identify the best option according to the priorities of a project.


2020 ◽  
Vol 12 (14) ◽  
pp. 5729 ◽  
Author(s):  
Ayman Ragab ◽  
Ahmed Abdelrady

Energy consumption for cooling purposes has increased significantly in recent years, mainly due to population growth, urbanization, and climate change consequences. The situation can be mitigated by passive climate solutions to reduce energy consumption in buildings. This study investigated the effectiveness of the green roof concept in reducing energy demand for cooling in different climatic regions. The impact of several types of green roofing of varying thermal conductivity and soil depth on energy consumption for cooling school buildings in Egypt was examined. In a co-simulation approach, the efficiency of the proposed green roof types was evaluated using the Design-Builder software, and a cost analysis was performed for the best options. The results showed that the proposed green roof types saved between 31.61 and 39.74% of energy, on average. A green roof featuring a roof soil depth of 0.1 m and 0.9 W/m-K thermal conductivity exhibited higher efficiency in reducing energy than the other options tested. The decrease in air temperature due to green roofs in hot arid areas, which exceeded an average of 4 °C, was greater than that in other regions that were not as hot. In conclusion, green roofs were shown to be efficient in reducing energy consumption as compared with traditional roofs, especially in hot arid climates.


2016 ◽  
Vol 17 (4) ◽  
pp. 451-470 ◽  
Author(s):  
Nicole Sintov ◽  
Ellen Dux ◽  
Agassi Tran ◽  
Michael Orosz

Purpose The purpose of this paper was to evaluate the impact of a competition-based intervention combining high-resolution electricity feedback, incentives, information and prompts on college dormitory residents’ energy consumption and participation in demand response events. The authors also investigated changes in individual-level pro-environmental behaviors and examined psychosocial correlates of behavior change. Design/methodology/approach Residents of 39 suites in a freshman residence hall competed against one another to reduce energy consumption and win prizes as part of a three-week competition. Feedback was provided in near real-time at the suite-level via an interactive touch-screen kiosk. Participants also completed baseline and follow-up surveys. Findings Electricity use among all suites was approximately 6.4 per cent lower during the competition period compared to baseline, a significant reduction. Additionally, participants reported engaging in various pro-environmental behaviors significantly more frequently during the competition relative to baseline. Changes in pro-environmental behavior were associated with changes in level of group identification and perceived social norms. Practical implications In three weeks, dormitory residents saved 3,158 kWh of electricity compared to baseline – the equivalent of more than 3,470 pounds of carbon dioxide emissions. The findings provide evidence that real-time feedback, combined with incentives, information and prompts, can motivate on-campus residents to reduce energy consumption. Originality/value The authors contribute to a limited body of evidence supporting the effectiveness of dorm energy competitions in motivating college students to save energy. In addition, the authors identified individual-level behavioral and psychosocial changes made during such an intervention. University residential life planners may also use the results of this research to inform student programming.


2010 ◽  
Vol 26 (4) ◽  
pp. 473-483 ◽  
Author(s):  
Clément Carpentier ◽  
Josep M. Font-Llagunes ◽  
József Kövecses

The impulsive dynamics associated with the impact of the crutch with the ground is an important topic of research, since this is known to be the main cause of energy loss during crutch gait. In this article, a four-segmental 2D model based on anthropometric body segment parameters is used to analyze various dynamics aspects of such impact. For this purpose, a novel formulation based on the decomposition of the tangent space of the biomechanical system to two subspaces associated with the constrained and admissible motions is developed. Detailed numerical analysis is presented to discuss the effects of body configuration and crutch length on the kinetic energy redistribution, velocity change and impulsive contact forces generated. The conclusions reached via this analysis give guidelines for optimal crutch selection or crutch-use teaching that can be applied to injured subjects. For instance, to reduce energy consumption which leads to a reduction of muscular fatigue.


2021 ◽  
Author(s):  
Sara Damyar

Building envelope retrofits is one of the options available to reduce energy consumption of postwar MURBs in Toronto. This study evaluates the impact of building envelope retrofits that meet current standards on energy consumption of a Toronto postwar MURB; utilizing eQUEST energy simulation software. Further upgrades also take place to evaluate how the impact of building envelope retrofits on energy use can be increased and optimized for all assemblies of building envelope and airtightness. Moreover, the retrofit strategies are ranked based on cost and energy-saving effectiveness. The results of the analysis reveal that building envelope retrofit based on OBC-2012 standards can reduce the energy consumption by up to 44%. Furthermore, the optimal RSI values of all building envelope components were found to be equal or less than code requirements which outcomes significant energy savings. Lastly, the ranking of the strategies helps to identify the best option according to the priorities of a project.


Energies ◽  
2019 ◽  
Vol 12 (9) ◽  
pp. 1677 ◽  
Author(s):  
Samuel Domínguez-Amarillo ◽  
Jesica Fernández-Agüera ◽  
Miguel Ángel Campano ◽  
Ignacio Acosta

Spain’s high winter weather-associated death count, the second largest in Europe, can be attributed primarily to the low construction standards of its social housing, particularly the stock built prior to the entry into effect of the earliest statutory provisions on envelope quality. Hence, improving building envelopes to both reduce energy consumption and raise occupant comfort levels is important. Air leakage is one of the factors with the greatest impact on indoor comfort and domestic energy consumption. This study explores the sensitivity of energy consumption to that parameter in a series of types of social housing built between 1950 and 1979 in five Mediterranean climate zones. Demand in a total of 53 housing units located in 21 developments was simulated to that end. The findings show that air permeability has a significant effect on wintertime demand in the sample studied. Although the impact is greater in the more severe climates where it is estimated to be over 10 kWh/m2, it may also affect energy consumption in mild climates.


2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Yilian Zhou ◽  
Ligang He ◽  
Bin Wang ◽  
Yi Su ◽  
Hao Chen

Offloading computation from mobile to remote cloud servers is a promising way to reduce energy consumption and improve the performance of mobile applications. However, a great challenge arises as automatic integration of powerful computing resources in remote cloud infrastructure and the portability of mobile devices. In this paper, we develop a Java annotation-based offloading framework, called MCAF, for android mobile devices. This framework is designed and committed to simplifying the development of android applications enabled with the offload capability. All the developers need to do is to import the SDK library of our MCAF and annotate the computation-intensive methods. MCAF can automatically extract the annotated source code and generate the code that will be run in the Cloud. Moreover, the codes of making the offloading decisions are automatically inserted into the original source code. We also conducted the real experiments to show the applicability of our MCAF.


Sign in / Sign up

Export Citation Format

Share Document