Related papers: AI Inference as Relocatable Electricity Demand: A …

Edge computing enables AI inference closer to data sources, reducing latency and bandwidth costs. However, orchestrating AI services across the cloud-edge continuum remains challenging due to dynamic workloads and infrastructure…

We consider the problem of dispatching a fleet of heterogeneous energy storage units to provide grid support. Under the restriction that recharging is not possible during the time frame of interest, we develop an aggregate measure of fleet…

The vast data deluge at the network's edge is raising multiple challenges for the edge computing community. One of them is identifying edge storage servers where data from edge devices/sensors have to be stored to ensure low latency access…

The ongoing transition to renewable energy is increasing the share of fluctuating power sources like wind and solar, raising power grid volatility and making grid operation increasingly complex and costly. In our prior work, we have…

In this paper, we propose a self-deployment approach for finding the optimal placement of extenders in which both the wireless back-haul and front-haul throughput of the extender are optimized. We present an artificial intelligence (AI)…

Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving,…

The ICT industry today is placed as one of the major consumers of energy, where recent reports have also shown that the industry is a major contributor to global carbon emissions. While renewable energy-aware data centers have been…

Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that…

Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy…

Rural electrification demands the use of inexpensive technologies such as single wire earth return (SWER) networks. There is a steadily growing energy demand from remote consumers, and the capacity of existing lines may become inadequate…

The implementation of machine learning in Internet of Things devices poses significant operational challenges due to limited energy and computation resources. In recent years, significant efforts have been made to implement simplified ML…

The recent decades have seen a surge of interests in distributed computing. Existing work focus primarily on either distributed computing platforms, data query tools, or, algorithms to divide big data and conquer at individual machines etc.…

Resource-constrained Edge Devices (EDs), e.g., IoT sensors and microcontroller units, are expected to make intelligent decisions using Deep Learning (DL) inference at the edge of the network. Toward this end, there is a significant research…

The global energy system is undergoing a major transformation. Renewable energy generation is growing and is projected to accelerate further with the global emphasis on decarbonization. Furthermore, distributed generation is projected to…

While network slicing has become a prevalent approach to service differentiation, radio access network (RAN) slicing remains challenging due to the need of substantial adaptivity and flexibility to cope with the highly dynamic network…

Rapid advances in AI have incited extensive inquiry into its effects on productivity and labor, potentially profound in both positive and negative ways. Often neglected, however, is comprehension of how AI technologies diffuse across and…

This paper studies an edge intelligence-based IoT network in which a set of edge servers learn a shared model using federated learning (FL) based on the datasets uploaded from a multi-technology-supported IoT network. The data uploading…

As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided…

Multi-tenant AI inference platforms must balance resource utilization against service-level guarantees under variable demand. Conventional approaches fail to achieve this balance: dedicated endpoints strand capacity on idle models, while…

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…