Given billions of mobile users, the environmental impact of edge computing is significant. To address this, future applications need to execute computations on a green component which is fueled by renewable energy sources. However, because of the intermittent nature of the renewable energy sources, the carbon intensity of computing components can significantly vary with location and time of use. This poses a new challenge for edge applications – deciding when and where to run computations across consumer devices at the edge and servers in the cloud. Such scheduling decisions become more complicated with the amortization of the rising embodied emissions and stochastic runtime variance. This work proposes GreenScale, an intelligent execution scaling engine that accurately selects the carbon-optimal execution target for edge applications in different runtime environments. Our evaluation with three representative categories of applications (i.e., AI, Game, and AR/VR) demonstrate that the carbon emissions of the applications can be reduced by 35.2%, on average, with GreenScale.

Given billions of mobile users, the environmental impact of edge computing is significant. To address this, future applications need to execute computations on a green component which is fueled by renewable energy sources. However, because of the intermittent nature of the renewable energy sources, the carbon intensity of computing components can significantly vary with location and time of use. This poses a new challenge for edge applications – deciding when and where to run computations across consumer devices at the edge and servers in the cloud. Such scheduling decisions become more complicated with the amortization of the rising embodied emissions and stochastic runtime variance. This work proposes GreenScale, an intelligent execution scaling engine that accurately selects the carbon-optimal execution target for edge applications in different runtime environments. Our evaluation with three representative categories of applications (i.e., AI, Game, and AR/VR) demonstrate that the carbon emissions of the applications can be reduced by 35.2%, on average, with GreenScale.

With the widespread use of Large Language Models (LLMs), there is an increasing demand for personalized models that meet diverse needs of users. To enable private, network-independent personalization of LLMs, on-device fine-tuning is receiving much attention. However, on-device fine-tuning faces efficiency and scalability challenges as sequential execution of compute- and memory-intensive operations often under-utilizes resources. In this letter, we propose ReAx, a framework that accelerates on-device fine-tuning through resource efficient asynchronous parallel execution of memory- and compute-intensive operations. Without increasing memory usage, ReAx improves the average fine-tuning performance and energy consumption by 10.42% and 5.55%, respectively, compared to the baseline. As a positive side effect, asynchronous parameter updates induce gradient noise due to slight delays between streams, which act as a regularizer against adverse updates across mini-batches, without sacrificing accuracy.

Paulo is considered a model city due to its cultural diversity and its formation by immigrants from all over the world.Japanese immigration to Brazil began in 1908.In 1927, a Korean who lived in Japan joined a group of Japanese immigrants and came to Brazil on a missionary mission.He became known as Mita harabodi and played a fundamental role in the survival and adaptation of the first Korean immigrants in So Paulo, who began arriving unofficially in Brazil in 1959.In this context, we will study how Mita harabodis contributions marked the beginning of Korean history in Brazil, and how they influenced the development and success that the Korean community has achieved in various fields.

Thin films of gadolinium-doped ceria (GDC) nanoparticles were fabricated as electrolytes for low-temperature solid oxide fuel cells (SOFCs) by combining electrophoretic deposition (EPD) and the successive ionic layer adsorption and reaction-air spray plus (SILAR-A+) method. The Ce_1-<i>x</i>Gd<i>_x</i>O_2-<i>x</i>/2 solid solution was synthesized using hydrothermal (HY) and solid-state (SS) procedures to produce high-quality GDC nanoparticles suitable for EPD fabrication. The crystalline structure, cell parameters, and phases of the GDC products were analyzed using X-ray diffraction. Variations in oxygen vacancy concentrations in the GDC samples were achieved through the two synthetic methods. The ionic conductivities of pressed pellets from the HY, SS, and commercial G_0.2DC samples, measured at 150 °C, were 0.6 × 10^-6, 2.6 × 10^-6, and 2.9 × 10^-6 S/cm, respectively. These values were determined using electrochemical impedance spectroscopy (EIS) with a simplified equivalent circuit method. The morphologies of G_0.2DC thin films prepared via EPD and SILAR-A+ processes were characterized, with particular attention to surface cracking. Crack-free GDC thin films, approximately 730-1200 nm thick, were successfully fabricated on conductive substrates through the hybridization of EPD and SILAR-A+, followed by hydrothermal annealing. EIS and ionic conductivity (1.39 × 10^-9 S/cm) measurements of the G_0.2DC thin films with thicknesses of 733 nm were performed at 300 °C.

This paper presents a novel approach for executing the inference of a network of pre-trained deep neural networks (DNNs) on commercial-off-the-shelf devices that are deployed at the edge. The problem is to partition the computation of the DNNs between an energy-constrained and performance-limited edge device <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\mathcal{E}}$</tex-math></inline-formula>, and an energy-unconstrained, higher performance device <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\mathcal{C}}$</tex-math></inline-formula>, referred to as the <i>cloudlet</i>, with the objective of minimizing the energy consumption of <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\mathcal{E}}$</tex-math></inline-formula> subject to a deadline constraint. The proposed partitioning algorithm takes into account the performance profiles of executing DNNs on the devices, the power consumption profiles, and the variability in the delay of the wireless channel. The algorithm is demonstrated on a platform that consists of an NVIDIA Jetson Nano as the edge device <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\mathcal{E}}$</tex-math></inline-formula> and a Dell workstation with a Titan Xp GPU as the cloudlet. Experimental results show significant improvements both in terms of energy consumption of <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\mathcal{E}}$</tex-math></inline-formula> and processing delay of the application. Additionally, it is shown how the energy-optimal solution is changed when the deadline constraint is altered. Moreover, the overhead of decision-making for our proposed method is significantly lower than the state-of-the-art Integer Linear Programming (ILP) solutions.

Federated Learning (FL) is a practical approach to train deep learning models collaboratively across user-end devices, protecting user privacy by retaining raw data on-device. In FL, participating user-end devices are highly fragmented in terms of hardware and software configurations. Such fragmentation introduces a new type of data heterogeneity in FL, namely \textit{system-induced data heterogeneity}, as each device generates distinct data depending on its hardware and software configurations. In this paper, we first characterize the impact of system-induced data heterogeneity on FL model performance. We collect a dataset using heterogeneous devices with variations across vendors and performance tiers. By using this dataset, we demonstrate that \textit{system-induced data heterogeneity} negatively impacts accuracy, and deteriorates fairness and domain generalization problems in FL. To address these challenges, we propose HeteroSwitch, which adaptively adopts generalization techniques (i.e., ISP transformation and SWAD) depending on the level of bias caused by varying HW and SW configurations. In our evaluation with a realistic FL dataset (FLAIR), HeteroSwitch reduces the variance of averaged precision by 6.3\% across device types.

Federated Learning (FL) is a decentralized approach to train a DNN model without sharing the on-device training samples with a cloud server. Although FL is a practical solution to prevent the privacy leakage in DNN training, the environmental impact of FL can be significant given billions of mobile users. However, optimizing carbon emissions of FL is challenging because of its unique features such as heterogeneous carbon intensity, system/data heterogeneity, and network variability. In this paper, we propose a carbon-aware FL algorithm ---CLOVER--- which enables carbon efficient selections of participants and their respective training samples considering the aforementioned features. In our experiments with various combinations of DNN models and datasets, CLOVER improves the FL carbon efficiency by 25.0%, on average, while still guaranteeing the convergence with better accuracy.