The field of edge computing and Internet of Things (IoT) is rapidly evolving, with a focus on optimizing resource allocation, improving energy efficiency, and enhancing task offloading. Researchers are exploring innovative approaches, such as cloud-edge collaboration, knowledge distillation, and generative AI-enhanced multi-agent reinforcement learning, to address the challenges of large-scale IoT networks and edge computing systems. Noteworthy papers in this area include 'Optimizing Multi-Gateway LoRaWAN via Cloud-Edge Collaboration and Knowledge Distillation', which proposes a cloud-edge collaborative resource allocation method, and 'Task Assignment and Exploration Optimization for Low Altitude UAV Rescue via Generative AI Enhanced Multi-agent Reinforcement Learning', which introduces a novel cooperation framework for UAVs and ground-embedded robots. Other significant contributions include the development of progressive, content-aware image compression models and dynamic likelihood-weighted cooperative infotaxis approaches for multi-source search in urban environments.
Advances in Edge Computing and IoT
Sources
Optimizing Multi-Gateway LoRaWAN via Cloud-Edge Collaboration and Knowledge Distillation
Task Assignment and Exploration Optimization for Low Altitude UAV Rescue via Generative AI Enhanced Multi-agent Reinforcement Learning
LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
The Effect of the Network in Cutting Carbon for Geo-shifted Workloads
End-Edge Model Collaboration: Bandwidth Allocation for Data Upload and Model Transmission
DLW-CI: A Dynamic Likelihood-Weighted Cooperative Infotaxis Approach for Multi-Source Search in Urban Environments Using Consumer Drone Networks
Joint Optimization of Offloading, Batching and DVFS for Multiuser Co-Inference
Energy-Efficient Irregular RIS-aided UAV-Assisted Optimization: A Deep Reinforcement Learning Approach
Energy-Efficient UAV-Mounted RIS for IoT: A Hybrid Energy Harvesting and DRL Approach
To Offload or Not To Offload: Model-driven Comparison of Edge-native and On-device Processing
State-Aware IoT Scheduling Using Deep Q-Networks and Edge-Based Coordination
FailLite: Failure-Resilient Model Serving for Resource-Constrained Edge Environments
GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network
A UAV-Aided Digital Twin Framework for IoT Networks with High Accuracy and Synchronization
Balancing Costs and Utilities in Future Networks via Market Equilibrium with Externalities
MEC Task Offloading in AIoT: A User-Centric DRL Model Splitting Inference Scheme
Preemption Aware Task Scheduling for Priority and Deadline Constrained DNN Inference Task Offloading in Homogeneous Mobile-Edge Networks
AGCo-MATA: Air-Ground Collaborative Multi-Agent Task Allocation in Mobile Crowdsensing
Cooperative Task Offloading through Asynchronous Deep Reinforcement Learning in Mobile Edge Computing for Future Networks