Reducing power consumption of smart device by proper management of Wakelocks

Patil, Pratiksha S.; Doshi, Jinalkumar; Ambawade, Dayanand

doi:10.1109/iadcc.2015.7154832

“…Previous work has been done to measure and model the energy consumed by various phone components such as the CPU [ 18 , 19 , 20 , 21 , 22 ], memory [ 18 , 23 ], WiFi NIC [ 18 , 19 , 20 , 21 , 24 ], display screen [ 24 ], GPS sensor [ 2 , 11 ], Bluetooth module [ 25 , 26 , 27 ], cellular module [ 25 ], and so on.…”

Section: Related Workmentioning

confidence: 99%

“…Because a phone in the basic state runs no applications, keeps Bluetooth/GSM/3G radios disabled and camera/microphone/speakers off, the energy consumed by the other components (e.g., sensors, cameras, Bluetooth modules and cellular modules) is zero and not involved in our model. Compared to our work, the work mentioned in Section 2.2 does not aim to model the energy of the phone in the basic state, and the models are for different phone components [ 2 , 11 , 25 , 26 , 27 ] or for individual components [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ], rather than the entire phone.…”

Section: Related Workmentioning

confidence: 99%

Energy Modeling of IoT Mobile Terminals on WiFi Environmental Impacts †

Sun

¹

,

Chen

²

,

Tang

³

et al. 2018

Sensors

View full text Add to dashboard Cite

With the popularity of various IoT mobile terminals such as mobile phones and sensors, the energy problems of IoT mobile terminals have attracted increasingly more attention. In this paper, we explore the impacts of some important factors of WiFi environments on the energy consumption of mobile phones, which are typical IoT end devices. The factors involve the WiFi signal strength under good signal conditions, the type and the amount of protocol packets that are initiated by WiFi APs (Access Points) to maintain basic network communication with the phones. Controlled experiments are conducted to quantitatively study the phone energy impacts by the above WiFi environmental factors. To describe such impacts, we construct a time-based signal strength-aware energy model and packet type/amount-aware energy models. The models constructed in the paper corroborate the following user experience on phone energy consumption: (1) a phone’s energy is drawn faster under higher WiFi signal strengths than under lower ones even in normal signal conditions; (2) phones consume energy faster in a public WiFi network than in a private one even in the basic phone state. The energy modeling methods proposed in the paper enable ordinary developers to analyze phone energy draw conveniently by utilizing inexpensive power meters as measurement tools. The modeling methods are general and are able to be used for phones of any type and any platform.

show abstract

“…Pathak et al [43] observed that 70% of energy bugs are the result of wake lock related problems. This is no wonder that much research [44,6,35,8,53,46] has been conducted to characterize, detect, and minimize no sleep bugs so that the developers can optimize their code.…”

Section: Energy Optimization and Guidelinesmentioning

confidence: 99%

Did I make a mistake? Finding the impact of code change on energy regression

Chowdhury

¹

,

Gil

²

,

Romansky

³

et al. 2017

Preprint

View full text Add to dashboard Cite

Software energy consumption is a performance related non-functional requirement that complicates building software on mobile devices today. Energy hogging applications are a liability to both the end-user and software developer. Measuring software energy consumption is non-trivial, requiring both equipment and expertise, yet many researchers have found that software energy consumption can be modelled. Prior works have hinted that with more energy measurement data one can make more accurate energy models but this data was expensive to extract because it required energy measurement of running test cases (rare) or time consuming manually written tests. We address these concerns by automatically generating test cases to drive applications undergoing energy measurement. Automatic test generation allows a model to be continuously improved in a model building process whereby applications are extracted, tests are generated, energy is measured and combined with instrumentation to train a grander big-data model of software energy consumption. This continuous process has allowed the authors to generate and extract measurements from hundreds of applications in order to build accurate energy models capable of predicting the energy consumption of applications without end-user energy measurement. We clearly show that models built from more applications reduce energy modelling error.

show abstract

“…Pathak et al [43] observed that 70% of energy bugs are the result of wake lock related problems. This is no wonder that much research [44,6,35,8,53,46] has been conducted to characterize, detect, and minimize no sleep bugs so that the developers can optimize their code.…”

Section: Energy Optimization and Guidelinesmentioning

confidence: 99%

GreenScaler: Automatically training software energy model with big data

Chowdhury¹,

Gil²,

Romansky³

et al. 2016

Preprint

0

View full text Add to dashboard Cite

Software energy consumption is a performance related non-functional requirement that complicates building software on mobile devices today. Energy hogging applications are a liability to both the end-user and software developer. Measuring software energy consumption is non-trivial, requiring both equipment and expertise, yet many researchers have found that software energy consumption can be modelled. Prior works have hinted that with more energy measurement data one can make more accurate energy models but this data was expensive to extract because it required energy measurement of running test cases (rare) or time consuming manually written tests. We address these concerns by automatically generating test cases to drive applications undergoing energy measurement. Automatic test generation allows a model to be continuously improved in a model building process whereby applications are extracted, tests are generated, energy is measured and combined with instrumentation to train a grander big-data model of software energy consumption. This continuous process has allowed the authors to generate and extract measurements from hundreds of applications in order to build accurate energy models capable of predicting the energy consumption of applications without end-user energy measurement. We clearly show that models built from more applications reduce energy modelling error.

show abstract

Reducing power consumption of smart device by proper management of Wakelocks

Cited by 12 publications

References 6 publications

Energy Modeling of IoT Mobile Terminals on WiFi Environmental Impacts †

Energy Modeling of IoT Mobile Terminals on WiFi Environmental Impacts †

Did I make a mistake? Finding the impact of code change on energy regression

GreenScaler: Automatically training software energy model with big data

Contact Info

Product

Resources

About