Sojung Lee

Eunsu Kim

Jongwon Han

Jeongmin Seo

Taeyeoun Kim

Suhyun Jeon

Pildo Yoon

Joonpyo Hong

Yonghwa Lee

Suyoung Ahn

The AI/Cloud-Native System Architecture Research Group at Korea University focuses on artificial intelligence and cloud-native system architecture.

고려대학교 인공지능/클라우드 네이티브 시스템 아키텍처 연구 그룹은 인공지능 및 클라우드 네이티브 시스템 아키텍처를 연구한다.

To cope with increasing energy consumption in mobile devices, the mobile cloud offloading has received considerable attention from its ability to offload processing tasks of mobile devices to cloud servers, and previous studies have focused on single type tasks in fixed network environments. However, real network environments are spatio-temporally varying, and typical mobile devices have not only various types of tasks, e.g., network traffic, cloud offloadable/nonoffloadable workloads but also capabilities of CPU frequency scaling and network interface selection between WiFi and cellular. In this paper, we first jointly consider the following three dynamic problems in real mobile environments: 1) cloud offloading policy, i.e., determining to use local CPU resources or cloud resources; 2) allocation of tasks to transmit through networks and to process in local CPU; and 3) CPU clock speed and network interface controls …

DREAM: Dynamic Resource and Task Allocation for Energy Minimization in Mobile Cloud Systems

Most existing content caching designs require accurate estimation of content popularity, which can be challenging in the dynamic mobile network environment. Moreover, emerging hierarchical network architecture enables us to enhance the content caching performance by opportunistically exploiting both cloud-centric and edge-centric caching. In this paper, we propose a hybrid content caching design that does not require the knowledge of content popularity. Specifically, our design optimizes the content caching locations, which can be original content servers, central cloud units (CUs) and base stations (BSs) where the design objective is to support as high average requested content data rates as possible subject to the finite service latency. We fulfill this design by employing the Lyapunov optimization approach to tackle an NP-hard caching control problem with the tight coupling between CU caching and BS …

Hybrid content caching in 5G wireless networks: Cloud versus edge caching

Mobile code offloading (MCO) is a technology that offloads computing tasks from mobile devices to remote servers managed by code offload service providers (CSPs). Nowadays, it is recommended that the remote servers be placed on the edge of the network to support modern applications, e.g., augmented reality, which demand stringent and ultralow latency or high bandwidth. To date, previous studies have independently addressed code offloading policy in mobile devices and pricing/server provisioning policies in the CSP; moreover, the system models for both user side and CSP side have not adequately reflected their practical aspects. This paper designs a practical model for the both sides and takes account of them in an integrated MCO framework simultaneously. By leveraging Lyapunov drift-plus-penalty technique, we propose code offloading, local CPU clock frequency, and network interface selection …

Dual-side optimization for cost-delay tradeoff in mobile edge computing

For 5G and 6G communications, satellites are drawing great attention for global coverage extension and 3-D mobility enhancement. With advancements of satellite hardware, functional satellites are expected to be applied for 6G Internet of Things (IoT) services. In particular, because IoT service has a relatively low computational burden, it is more feasible for satellite edge computing (SatEC) with limited power, making IoT supportable SatEC one of the economically feasible applications for future satellite networks. In this article, an architecture of IoT supportable SatEC is analyzed, and the corresponding network slice scheduling is proposed. First, a multiobjective optimization problem for IoT supportable SatEC is formulated with respect to latency, computational power, and transmission power attenuation. The problem is solved for the satellite offloading rate and altitude by using a heuristic algorithm in low time …

Satellite edge computing architecture and network slice scheduling for IoT support

Energy-delay tradeoffs in smartphone applications have been studied independently in dynamic voltage and frequency scaling (DVFS) problem and network interface selection problem. We optimize the two problems jointly to quantify how much energy can be saved further and propose a scheme called SpeedControl which jointly manages application scheduling, CPU speed control and wireless interface selection. The scheme is shown to be near-optimal in that it tends to minimize energy consumption for given delay constraints. This paper is the first to reveal energy-delay tradeoffs in a holistic view considering multiple wireless interfaces, DVFS and multitasking in smartphone. We perform real measurements on WiFi/3G coverage and throughput, power consumption of CPU and WiFi/3G interfaces, and CPU workloads. Trace-driven simulations based on the measurements demonstrate that SpeedControl can …

Dynamic Speed Scaling for Energy Minimization in Delay-Tolerant Smartphone Applications

Recently, as plug-in hybrid electric vehicles (PHEVs) take center stage for the eco-friendly and cost-effective transportation, commercial PHEV charging stations will be widely prevalent in the future. However, previous studies in the fields of the management of PHEV charging stations have not synthetically taken practical charging systems into account. In this paper, we study the profit-optimal management of a PHEV charging station under the realistic environment addressing not only various types of vehicles but waiting time guarantee for PHEV customers as well. This paper is first to jointly take into account pricing for charging services, scheduling of reserved vehicles to PHEV chargers, dropping of reserved vehicles, and management of the energy storage in a unified framework that contains key features of a practical PHEV charging station. Based on this framework, we develop an algorithm to find the parameters …

Dynamic Pricing, Scheduling and Energy Management for Profit Maximization in PHEV Charging Stations

Greening effect in interference management (IM), a way of enhancing spectrum sharing via intelligent transmit power control, can be achieved by the fact that as BSs moderately reduce their transmit powers, the performance degradation decreases slower than linearly, yet a considerable overall energy saving is expected due to transmit powers' exerting influence on operational power. This paper investigates the impact of different spatial and/or temporal power sharing policies for a given system-wide power budget in IM schemes. We develop an optimization-theoretic IM framework on cellular network greening, from which we first develop four IM schemes governed by different power sharing: no sharing, only temporal sharing, only spatial sharing, and both spatial and temporal sharing. Through extensive simulations, including a real BS deployment in Manchester city, United Kingdom, we obtain the following …

Greening effect of spatio-temporal power sharing policies in cellular networks with energy constraints

The advent of elastic Content Delivery Networks (CDNs) enable Content Providers (CPs) to lease cache capacity on demand and at different cloud and edge locations in order to enhance the quality of their services. This article addresses key challenges in this context, namely how to invest an available budget in cache space in order to match spatio-temporal fluctuations of demand, wireless environment and storage prices. Specifically, we jointly consider dynamic cache rental, content placement, and request-cache association in wireless scenarios in order to provide just-in-time CDN services. The goal is to maximize the an aggregate utility metric for the CP that captures both service benefits due to caching and fairness in servicing different end users. We leverage the Lyapunov drift-minus-benefit technique and Jensen's inequality to transform our infinite horizon problem into hour-by-hour subproblems which can …

Elastic femtocaching: Scale, cache, and route

More network operators have recently provided content delivery network (CDN) services, where traffic engineering techniques, such as the base station (BS) association, are jointly employed with content delivery. This deployment attempts to reduce the network operating cost and enhance the quality of service (QoS) of end users. Toward this end, we study the BS association and file caching problem considering the spatial diversity of the file popularity and the realistic time-scale separation between the file caching and the BS association decisions in this paper. Our design aims to minimize the file delivery latency and operating power consumption in the cellular networks, where the tradeoff between these conflicting objectives is controlled by a single parameter. The short time-scale BS association problem is solved by using the convex optimization technique for a given file caching solution. However, the long time …

Two time-scale edge caching and BS association for power-delay tradeoff in multi-cell networks

In this paper, we study dynamic bandwidth slicing and resource allocation problems to support a mixture of IoT (Internet of Things) and video streaming services. By employing Lyapunov optimization method with time-scale separation approach, we develop algorithms for long time-scale bandwidth slicing, and short time-scale IoT device scheduling, power allocation (for IoT service) and quality decision (for video streaming service). We show through simulations that proposed dynamic bandwidth slicing and resource allocation algorithms outperform the static bandwidth slicing and resource allocation policies in terms of average total cost and average total delay.

Dynamic network slicing and resource allocation for heterogeneous wireless services

The electronic tongue (E-tongue) system has emerged as a significant innovation, aiming to replicate the complexity of human taste perception. In spite of the advancements in E-tongue technologies, two primary challenges remain to be addressed. First, evaluating the actual taste is complex due to interactions between taste and substances, such as synergistic and suppressive effects. Second, ensuring reliable outcomes in dynamic conditions, particularly when faced with high deviation error data, presents a significant challenge. The present study introduces a bioinspired artificial E-tongue system that mimics the gustatory system by integrating multiple arrays of taste sensors to emulate taste buds in the human tongue and incorporating a customized deep-learning algorithm for taste interpretation. The developed E-tongue system is capable of detecting four distinct tastes in a single drop of dietary compounds …

Taste Bud-Inspired Single-Drop Multitaste Sensing for Comprehensive Flavor Analysis with Deep Learning Algorithms

As the advanced satellite network can provide extremely diverse data to various types of users, it is of vital importance to achieve data security using encryption over satellite channels. However, since the avalanche effect makes encryption techniques vulnerable to bit errors in the wireless channel, a more powerful encryption technique is required for data confidentiality. In addition, an efficient method for exchanging encryption keys between receivers and transmitters should be capable of managing a large scale of satellites in the network. In this article, we propose a novel superencryption method of joint encryption and channel coding, cipher feedback-advanced encryption standard (CFB-AES)-TURBO, which combines AES in the upper layer and turbo coding as bulk encryption in the physical layer. Because we introduce turbo coding in the CFB mode with AES for each block, our scheme can accomplish dual goals of …

Cross-Layer Encryption of CFB-AES-TURBO for Advanced Satellite Data Transmission Security

Recently, applications using artificial intelligence (AI) technique in mobile devices such as augmented reality have been extensively pervasive. The hardware specifications of mobile devices, dynamic service demands, stochastic network states, and characteristics of DNN (Deep Neural Network) models affect the quality of experience (QoE) of such applications. In this paper, we propose CutEdge , that leverages a virtual queue-based Lyapunov optimization framework to jointly optimize DNN model partitioning between a mobile device and a mobile edge computing (MEC) server and processing/networking resources in a mobile device with respect to internal/external system dynamics. Specifically, CutEdge makes decisions of (i) the partition point of DNN model between the mobile device and MEC server, (ii) GPU clock frequency, and (iii) transmission rates in a mobile device, simultaneously. Then, we theoretically …

Cutting-edge inference: Dynamic DNN model partitioning and resource scaling for mobile AI

For beyond-5G and 6G communications, the satellite-terrestrial integrated network (STIN) is expected to provide diverse services with global coverage. The first step in implementing a successful STIN is to make the satellite network capable of functioning seamlessly with its terrestrial counterpart. However, as satellites rotate around Earth at very high speeds and are connected over very long wireless links, it is almost impossible to use terrestrial schemes without modification.

Satellite network slice planning: Architecture, performance analysis, and open issues

A fundamental question in the study of location-based mobile sensing is how much energy can be saved while still guaranteeing the reliable localization accuracy. In this paper, we analyze key features of human proximity and find a motivation which implies that the energy-efficient and accurate localization is possible by sharing the locations of nearby mobile devices. From the location-based collaborative sensing idea, we formulate an optimization problem which aims to minimize the total number of location measurements for a given fairness criterion. Then, we propose a practical and distributed location sharing (DLS) protocol and an optimal parameter control algorithm (OWD) which makes the DLS protocol attain an asymptotic optimal performance. Via extensive simulations under various environments including real mobility traces, we verify that the proposed DLS+OWD policy significantly reduces the average …

Proximity-Aware Location-Based Collaborative Sensing for Energy-Efficient Mobile Devices

(54) METHOD AND APPARATUS FOR(52) US Cl. ALLOCATING MINIMUM GUARANTEED CPC......... H04W 72/082 (2013.01); H04 W 16/12 RESOURCE AMOUNT TO ACCESS POINT IN(2013.01); H04W 24/08 (2013.01); H04W WIRELESS ACCESS SYSTEM 72/0493 (2013.01)

Method and apparatus for allocating minimum guaranteed resource amount to access point in wireless access system

Massive Multi-Input Multi-Output (MIMO) and Coordinated MultiPoint (CoMP) technologies in Cloud-RAN (C-RAN) architecture become inevitable trend due to the advent of next-generation mobile applications, which are traffic-intensive, such as ultra high definition (UHD) video. In this paper, we study a joint beam activation and user scheduling problem in a 5G cellular network with massive MIMO and CoMP utilizing orthogonal random beamforming technique. This paper aims to minimize total Remote Radio Heads’ (RRHs’) energy expenditure in a dynamic C-RAN architecture while ensuring finite service time for all user traffic arrivals in the communication coverage. We leverage Lyapunov drift-plus-penalty framework to transform an original long-term average problem into a series of per-slot modified problems. Since the provided per-slot problem is combinatorial and nonlinear optimization problem, we are …

Energy and delay guaranteed joint beam and user scheduling policy in 5G CoMP networks

Demand for using cloud object storage has been increasing in order to efficiently manage a large number of binary large objects (BLOBs), including videos, photos and documents. Although many companies and institutions are currently trying to utilize public cloud object storage services such as AWS Simple Storage Service (S3), most of existing encoding systems for safe storage of data have not been optimized for current cloud object storage architecture. In this article, we propose a novel dynamic extreme erasure encoding algorithm, namely DexEncoding aiming to maximize the utility of clients where the encoding locations in the cloud storage architecture are dynamically optimized between gateway and storage servers with respect to the time-varying cloud environment. Here, the utility captures the satisfaction of clients for the speed of data storage and fairness among clients. DexEncoding efficiently resolves …

Dynamic multi-resource optimization for storage acceleration in cloud storage systems

The next generation of networks will need to support massive requests for services that have very stringent performance requirements, and their delivery involves significant computing and storage resources. Prominent examples are the mobile augmented and virtual reality services, processing of large-scale IoT data, and mobile data analytics. In order to address these arising challenges, mobile network operators need innovative solutions, and one such is the close collaboration with the cloud service providers. In this article, we propose a novel system architecture that integrates the infrastructure of Mobile Network Operator (MNO) and Cloud Service Provider (CSP), leveraging recent developments in network softwarization that allows the unified control of the network, computing, and storage resources. We envision a multi-tier architecture where the CSP and MNO exchange real-time information about their …

Collaboration of Network Operators and Cloud Providers in Software-Controlled Networks

Wireless technologies, such as WirelessHART, are being adopted in industrial wireless sensor–actuator networks (IWSAN), which are required to provide reliable quality of control (QoC). This article focuses on adaptively selecting the best network path for reliable QoC in the IWSAN. The main challenge is estimating the time-varying packet delivery ratio (PDR) of each path. The IWSAN path selection problem in a multi-armed bandit (MAB) framework is formulated. A novel algorithm criticality-aware adaptive path learning (CAPL) is proposed, which determines the criticality of each packet according to the degree of QoC degradation if it is lost. The key novelty of CAPL is that it simultaneously considers the fundamental exploration–exploitation trade-off in MAB and QoC in the IWSAN. CAPL uses low-criticality packets for exploration to measure the PDR so that it can minimize the impact of exploration on QoC …

Intelligent Computing & Networking Laboratory

교수님 소개

곽정호

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Interchangeable CPU-GPU DVFS for Encoding vs. Inference in LEO Satellite Onboard Processing

Optimal Computation Load Balancing for Integrated Service Caching and Offloading Systems in Hierarchical Cloud Architecture

Joint Millimeter-Wave Beamforming Design and Access Link Rate Assignment for Integrated Access and Backhaul Networks

연구실 보유 특허

대학별 입시끈

우리 연구실 모집