Adaptive Edge-Cloud Environments for Rural AI

Abstract

Cloud computing provides on-demand access to computational resources while outsourcing infrastructure and service maintenance. Edge computing could extend cloud computing capability to areas with limited computing resources, such as rural areas, by utilizing low-cost hardware, such as singleboard computers. Cloud data centre hosted machine learning algorithms may violate user privacy and data confidentiality requirements. Federated learning (FL) trains models without sending data to a central server and ensures data privacy. Using FL, multiple actors can collaborate on a single machine learning model without sharing data. However, rural network outages can happen at any time, and the quality of a wireless network varies depending on location, which can affect the performance of the Federated Learning application. Therefore there is a need to have a platform that maintains service quality independent of infrastructure status. We propose a self-adaptive system for rural FL, which employs the Greedy Nominator Heuristic (GNH) based optimisation to orchestrate application workflows across multiple resources that make up a rural computing environment. GNH provides distributed optimization for workflow placement. GNH utilises resource status to reduce failure risks and costs while still completing tasks on time. Our approach is validated using a simulated rural environment -composed of multiple decentralized controllers sharing the same infrastructure and running a shared FL application. Results show that GNH outperforms three algorithms for deployment of FL tasks: random placement, round-robin load balancer and simple greedy algorithm.

Performance Analysis of Apache OpenWhisk Across the Edge-Cloud Continuum

“…Further performance optimization on a 64-bit cloud produces less significant results compared to RPis. Architectural variations such as processor type and data locality can cause bottlenecks in shared-memory parallel computing, leading to performance disparities [32]. Although both models predicted the right object classes, in the right position, as seen in Figure 11, the confidence score for detecting an object is higher in Figure 11a compared to Figure 11b.…”

An Edge-Cloud Infrastructure for Weed Detection in Precision Agriculture

“…Recent literature highlights advancements in weed detection and robotic weed management in agriculture, such as studying weed classification using AI [13], or adapting to rural infrastructure to securely train an AI model [14]. However, literature addressing infrastructure unreliability, especially in rural farming areas [6], [15] is limited.…”

funcX: Federated Function as a Service for Science

“…Flox uses funcX to enable users to train and deploy FL models on one or more remote computers, and in particular on edge devices. We are applying these techniques to Rural AI applications [25], using funcX to facilitate training and deployment of models in remote locations. Rural AI requires reliable task and result transmission as devices are deployed in rural settings where device and network outages are common, and the quality of wireless networks varies depending on location.…”