Related papers: Dora: QoE-Aware Hybrid Parallelism for Distributed…
In this work, we consider a mobile edge computing system with both ultra-reliable and low-latency communications services and delay tolerant services. We aim to minimize the normalized energy consumption, defined as the energy consumption…
The proliferation of the Internet of Things (IoT) and widespread use of devices with sensing, computing, and communication capabilities have motivated intelligent applications empowered by artificial intelligence. The classical artificial…
The Mixture of Experts (MoE) architecture has demonstrated significant advantages as it enables to increase the model capacity without a proportional increase in computation. However, the large MoE model size still introduces substantial…
This paper investigates the planning and operational processes of modern distribution networks (DNs) hosting Distributed Energy Resources (DERs). While in the past the two aspects have been distinct, a methodology is proposed in this paper…
Distributed DNN inference is becoming increasingly important as the demand for intelligent services at the network edge grows. By leveraging the power of distributed computing, edge devices can perform complicated and resource-hungry…
The deployment of ML models on edge devices is challenged by limited computational resources and energy availability. While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge…
Immersive media streaming, especially virtual reality (VR)/360-degree video streaming which is very bandwidth demanding, has become more and more popular due to the rapid growth of the multimedia and networking deployments. To better…
Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to low latency and better privacy. However, efficient deployment on these platforms is challenging due to the intensive computation and…
The Cuckoo optimization algorithm (COA) is developed for solving single-objective problems and it cannot be used for solving multi-objective problems. So the multi-objective cuckoo optimization algorithm based on data envelopment analysis…
This paper addresses the challenge of energy efficiency management faced by intelligent IoT devices in complex application environments. A novel optimization method is proposed, combining Deep Q-Network (DQN) with an edge collaboration…
Owing to the large volume of sensed data from the enormous number of IoT devices in operation today, centralized machine learning algorithms operating on such data incur an unbearable training time, and thus cannot satisfy the requirements…
Distributed Machine Learning (DML) on resource-constrained edge devices holds immense potential for real-world applications. However, achieving fast convergence in DML in these heterogeneous environments remains a significant challenge.…
Next-generation real-time compute-intensive applications, such as extended reality, multi-user gaming, and autonomous transportation, are increasingly composed of heterogeneous AI-intensive functions with diverse resource requirements and…
Distributed Stream Processing systems have become an essential part of big data processing platforms. They are characterized by the high-throughput processing of near to real-time event streams with the goal of delivering low-latency…
The introduction of device-to-device (D2D) into cellular networks poses many new challenges in the resource allocation design due to the co-channel interference caused by spectrum reuse and limited battery life of user equipments (UEs). In…
The ever-growing volume and decentralized nature of data, coupled with the need to harness it and extract knowledge, have led to the extensive use of distributed deep learning (DDL) techniques for training. These techniques rely on local…
The emergence of Mixture-of-Experts (MoE) has transformed the scaling of large language models by enabling vast model capacity through sparse activation. Yet, converting these performance gains into practical edge deployment remains…
It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…
Quality-Diversity (QD) optimization algorithms are a well-known approach to generate large collections of diverse and high-quality solutions. However, derived from evolutionary computation, QD algorithms are population-based methods which…
Modern machine learning tools such as deep neural networks (DNNs) are playing a revolutionary role in many fields such as natural language processing, computer vision, and the internet of things. Once they are trained, deep learning models…