Minyong Kim

Enhancing online power estimation accuracy for smartphones

This paper proposes an advanced online power estimation technique for multi-core smartphones. The proposed technique models each hardware components power behavior, considering the components power consumption characteristics. Our evaluation results show that the proposed technique has high accuracy (92.8%~97.2%) for applications in our evaluations, enough to be used in real smartphones.

Measuring Variance between Smartphone Energy Consumption and Battery Life

A case study reveals that energy savings do not always translate to longer smartphone battery life and that evaluating any savings plan must be based on battery consumption, not energy used.

Accurate GPU power estimation for mobile device power profiling

This paper not only describes the importance of GPU power estimation for smartphone power profiling, but also proposes GPU power estimation technique to enhance accuracy. The proposed technique improves the accuracy by up to 17.6%.

M-DTM: migration-based dynamic thermal management for heterogeneous mobile multi-core processors

Recently, mobile devices have employed heterogeneous multi-core processors which consist of highperformance big cores and low-power small cores. In heterogeneous mobile multi-core processors, the conventional DVFS (Dynamic Voltage and Frequency Scaling)-based DTM (Dynamic Thermal Management) is still adopted; it does not actively utilize the small cores to resolve thermal problem. In this paper, we propose M-DTM (Migration-based DTM) for heterogeneous mobile multi-core processors. In case of thermal emergency of the big cores, M-DTM migrates applications to the small cores instead of lowering the voltage and frequency of the big cores. In this way, M-DTM allows more time for the applications to run at the highest frequency of the big cores by cooling down the big cores more rapidly, compared to the conventional DTM. Through real measurement, we show that M-DTM improves performance by 10.6% and saves system-wide energy (not CPU energy) by 3.6%, on average, compared to the conventional DTM.

An online power estimation technique for multi-core smartphones with advanced display components

This paper describes an online power estimation technique for multi-core smartphones with advanced display components. The technique models each cores power as well as the non-linear power consumption characteristics of the advanced display component.

Application-aware scaling governor for wearable devices

Application characteristics include useful information that enhances power management techniques; for instance, a QoS-sensitive application does not need to be run any faster, as long as its QoS is preserved. In recently emerged wearable devices, power management techniques can easily utilize the characteristics, since the number of applications is limited and almost all applications are downloaded from one single application market. In this paper, we analyze the power savings by application-aware scaling governor that manages dynamic voltage frequency scaling (DVFS). Our real measurement results show that the application-aware scaling governor reduces system-wide energy consumption (12% on average) and enhances the performance (10% on average), compared to the conventional scaling governors in case of performance-sensitive applications. In addition, the application-aware scaling governor saves power (10% on average) without any noticeable QoS degradation in case of QoS-sensitive applications.

Enhancing Energy Efficiency of Multimedia Applications in Heterogeneous Mobile Multi-Core Processors

Recent smart devices have adopted heterogeneous multi-core processors which have high-performance big cores and low-power small cores. Unfortunately, the conventional task scheduler for heterogeneous multi-core processors does not provide appropriate amount of CPU resources for multimedia applications (whose QoS is important to users), resulting in energy waste; it often executes multimedia applications and non-multimedia applications on the same core. In this paper, we propose an advanced task scheduler for heterogeneous multi-core processors, which provides appropriate amount of CPU resources for multimedia applications. Our proposed task scheduler isolates multimedia applications from non-multimedia applications at runtime, exploiting the fact that multimedia applications have a specific thread for video/audio playback (to play video/audio, a multimedia application should use a function that generates the specific thread). Since multimedia applications usually require a smaller amount of CPU resources than non-multimedia applications due to dedicated hardware decoders, our proposed task scheduler allocates the former to the small cores and the latter to the big cores. In our experiments on an Android-based development board, our proposed task scheduler saves system-wide (not just CPU) energy consumption by 8.9 percent, on average, compared to the conventional task scheduler, preserving QoS of multimedia applications. In addition, it improves performance of non-multimedia applications by 13.7 percent, on average, compared to the conventional task scheduler.

Do You Waste Laptop Battery to Light the Room

Most widely used timeout based DPM (display power management) only turns off the display after there has been no user input for a fixed time. There have been a couple of studies (e.g. FaceOff) that try to save more energy by detecting user presence. However, the purpose of a display device is not to light the room, but to provide the graphical view to the user. Thus, the display does not need to be turned on, even when the user is present but not gazing at the display. In this article, we propose a power management scheme that uses a web cam to determine if the user is actually gazing at the display. In our evaluation result, the conventional DPMs turn off the display for 30~40% of the total time by detecting the state where user is not present. However, our proposed scheme turns off the display for nearly 50% of the total time by additionally detecting the state where the user is not gazing at the laptop. Our proposed scheme reduces average system-wide energy by 5% and 4% (up to 13%), compared to the timeout based DPM and FaceOff, respectively, with acceptable amount (0.8 per hour) of user irritation.

Display Power Management That Detects User Intent

In a proposed display power-management scheme, the laptop detects when the user is not looking at the screen, boosting low-power operation to 50 percent and increasing energy savings by up to 13 percent. With the growth of ubiquitous computing has come an increased reliance on laptops over desktops, and display power management (DPM) that prolongs battery life continues to be a critical issue in maintaining that trend.