Accurate Energy Modelling on the Cortex-M0 Processor for Profiling and Static Analysis
2
Citation
14
Reference
10
Related Paper
Citation Trend
Abstract:
Energy modelling can enable energy-aware software development and assist the developer in meeting an application's energy budget. Although many energy models for embedded processors exist, most do not account for processor-specific config-urations, neither are they suitable for static energy consumption estimation. This paper introduces a set of comprehensive energy models for Arm's Cortex-M0 processor, ready to support energy-aware development of edge computing applications using either profiling- or static-analysis-based energy consumption estimation. We use a commercially representative physical platform together with a custom modified Instruction Set Simulator to obtain the physical data and system state markers used to generate the models. The models account for different processor configurations which all have a significant impact on the execution time and energy consumption of edge computing applications. Unlike existing works, which target a very limited set of applications, all developed models are generated and validated using a very wide range of benchmarks from a variety of emerging IoT application areas, including machine learning and have a prediction error of less than 5%.Keywords:
Profiling (computer programming)
Energy Modeling
ARM architecture
Optimizing the energy efficiency of mobile applications can greatly increase user satisfaction. However, developers lack viable techniques for estimating the energy consumption of their applications. This paper proposes a new approach that is both lightweight in terms of its developer requirements and provides fine-grained estimates of energy consumption at the code level. It achieves this using a novel combination of program analysis and per-instruction energy modeling. In evaluation, our approach is able to estimate energy consumption to within 10% of the ground truth for a set of mobile applications from the Google Play store. Additionally, it provides useful and meaningful feedback to developers that helps them to understand application energy consumption behavior.
Energy Modeling
Consumption
Code (set theory)
Cite
Citations (234)
Profiling (computer programming)
Cite
Citations (7)
The energy consumption problem in data centers is becoming increasingly severe, and energy consumption models can reveal the relationship between data center energy consumption and its corresponding factors, which is crucial for reducing energy consumption. Containerization is the current mainstream trend in data centers. Therefore, this paper proposes energy consumption models for physical hosts, containers, and containerized applications. First, we constructe a physical host energy consumption model based on polynomial regression with lasso. Then, by analyzing the resource utilization, we propose a simple and accurate method for modeling the container energy consumption. Finally, based on the container energy consumption model, we propose a method for constructing a parameter-based energy consumption models for containerized applications. The experimental results show that our modeling methods are valid. The advantages of our modeling method are that it can analyze data center energy consumption from different levels, such as physical hosts, containers, and applications, and it has the advantages of simplicity, high accuracy, ease of implementation.
Data center
Energy Modeling
Consumption
Cite
Citations (0)
Profiling (computer programming)
Merge (version control)
Dependence analysis
Cite
Citations (7)
Optimizing the energy efficiency of mobile applications can greatly increase user satisfaction. However, developers lack viable techniques for estimating the energy consumption of their applications. This paper proposes a new approach that is both lightweight in terms of its developer requirements and provides fine-grained estimates of energy consumption at the code level. It achieves this using a novel combination of program analysis and per-instruction energy modeling. In evaluation, our approach is able to estimate energy consumption to within 10% of the ground truth for a set of mobile applications from the Google Play store. Additionally, it provides useful and meaningful feedback to developers that helps them to understand application energy consumption behavior.
Energy Modeling
Consumption
Code (set theory)
Cite
Citations (158)
Energy modelling can enable energy-aware software development and assist the developer in meeting an application's energy budget. Although many energy models for embedded processors exist, most do not account for processor-specific config-urations, neither are they suitable for static energy consumption estimation. This paper introduces a set of comprehensive energy models for Arm's Cortex-M0 processor, ready to support energy-aware development of edge computing applications using either profiling- or static-analysis-based energy consumption estimation. We use a commercially representative physical platform together with a custom modified Instruction Set Simulator to obtain the physical data and system state markers used to generate the models. The models account for different processor configurations which all have a significant impact on the execution time and energy consumption of edge computing applications. Unlike existing works, which target a very limited set of applications, all developed models are generated and validated using a very wide range of benchmarks from a variety of emerging IoT application areas, including machine learning and have a prediction error of less than 5%.
Profiling (computer programming)
Energy Modeling
ARM architecture
Cite
Citations (2)
The advent of larger machine learning (ML) models have improved state-of-the-art (SOTA) performance in various modeling tasks, ranging from computer vision to natural language. As ML models continue increasing in size, so does their respective energy consumption and computational requirements. However, the methods for tracking, reporting, and comparing energy consumption remain limited. We present EnergyVis, an interactive energy consumption tracker for ML models. Consisting of multiple coordinated views, EnergyVis enables researchers to interactively track, visualize and compare model energy consumption across key energy consumption and carbon footprint metrics (kWh and CO2), helping users explore alternative deployment locations and hardware that may reduce carbon footprints. EnergyVis aims to raise awareness concerning computational sustainability by interactively highlighting excessive energy usage during model training; and by providing alternative training options to reduce energy usage.
Carbon Footprint
Footprint
Energy Modeling
Consumption
Tracking (education)
Cite
Citations (11)
Safely meeting Worst Case Energy Consumption (WCEC) criteria requires accurate energy modeling of software. We investigate the impact of instruction operand values upon energy consumption in cacheless embedded processors. Existing instruction-level energy models typically use measurements from random input data, providing estimates unsuitable for safe WCEC analysis.
Operand
Energy Modeling
Energy accounting
Consumption
Cite
Citations (20)
Actual energy consumption in buildings is typically different from predictions during the design phase. While differences in occupant energy usage characteristics play an important role in this variation, actual energy estimation software do not account for this factor. This paper proposes a new approach for energy estimation in buildings using a combination of traditional energy calculation software along with agent-based simulation modeling. First, the difference in energy consumption levels for different types of occupancy energy usage characteristics is identified by building energy models adapted for each type of behavior. Then, an agent-based simulation model simulates the influence that people with different behaviors have on each other, resulting in potential changes in energy usage characteristics over time. By combining these two methods, more customized energy studies can be performed resulting in more accurate energy consumption estimates.
Occupancy
Energy accounting
Energy Modeling
Simulation software
Cite
Citations (25)
Abstract Various energy simulation tools are used to predict energy consumption in buildings at different stages from design to post-occupancy and maintenance. The inaccuracy and insufficiency of inputs used for building energy simulation (BES) often cause a discrepancy between the predicted and actual energy consumption. Inaccurate energy consumption estimations affect the accomplishment of the sustainability goals and reduction of energy consumption and CO 2 emissions in buildings. The review of the existing literature suggests that the potential causes of the aforementioned uncertainty in building energy predictions are divided into 2 categories: human error (in design, construction, energy modelling, etc.) and the inaccuracy and insufficiency of inputs in BES. This research proposes the way forward for BES tools to improve their accuracy by enhancing the precision of various energy simulation inputs, integration of real-time data and use of machine learning and other emerging technologies.
Occupancy
Energy Modeling
Consumption
Energy accounting
Cite
Citations (0)