Goal-oriented access cuts communication errors by over 30 percent
Value-Based Massive Access through Goal-Oriented Irregular Repetition Slotted ALOHA
Networking and Internet ArchitectureMultiagent Systems
Summary
Connecting thousands of sensors to communicate important information without overloading networks is challenging. The authors present a new method called GO-IRSA that helps many devices share a communication channel more efficiently. This method reduces errors in estimating a process by about 30% compared to the best centralized methods. It works well even when the sensors have limited computing power and sometimes imperfect knowledge.
What this means in practice
- •For network schedulers: Manage massive numbers of sensors communicating with fewer errors and less feedback in large-scale monitoring networks.
- •For industrial automation engineers: Coordinate sensor data transmission in manufacturing plants to improve real-time estimation accuracy without heavy computation on devices.
Authors
Pietro Talli, Andrea Munari, Federico Mason, Federico Chiariotti, Andrea Zanella
Abstract
The goal-oriented communication paradigm is poised to enable novel real-time applications by easing the burden on communication networks while still delivering task-relevant information. However, efforts so far have focused on the encoding problem, while the design of medium access schemes is still in the early stages of development, especially when connectivity is to be provided to a massive number of devices, e.g., for remote monitoring. In this respect, existing goal-oriented approaches are often centralized or based on simplified underlying mechanisms, requiring unrealistic assumptions. In this work, we present the Goal-oriented Irregular Repetition Slotted ALOHA (GO-IRSA) scheme, which combines modern random access techniques with belief-based policies. GO-IRSA does not impose significant computing loads on the sensors or require frequent feedback, and it can reduce the average and worst-case error of the estimate of a distributed Wiener process by over 30% with respect to the optimal centralized solution in a network with thousands of sensors, and is robust to imperfect interference cancellation and inaccurate process knowledge.