Research Article
Graph Neural Network Based Scheduling: Improved Throughput Under a Generalized Interference Model
@INPROCEEDINGS{10.1007/978-3-030-92511-6_9, author={Ramakrishnan Sambamoorthy and Jaswanthi Mandalapu and Subrahmanya Swamy Peruru and Bhavesh Jain and Eitan Altman}, title={Graph Neural Network Based Scheduling: Improved Throughput Under a Generalized Interference Model}, proceedings={Performance Evaluation Methodologies and Tools. 14th EAI International Conference, VALUETOOLS 2021, Virtual Event, October 30--31, 2021, Proceedings}, proceedings_a={VALUETOOLS}, year={2021}, month={12}, keywords={Resource allocation Graph Convolutional Neural Networks Adhoc networks}, doi={10.1007/978-3-030-92511-6_9} }- Ramakrishnan Sambamoorthy
Jaswanthi Mandalapu
Subrahmanya Swamy Peruru
Bhavesh Jain
Eitan Altman
Year: 2021
Graph Neural Network Based Scheduling: Improved Throughput Under a Generalized Interference Model
VALUETOOLS
Springer
DOI: 10.1007/978-3-030-92511-6_9
Abstract
In this work, we propose a Graph Convolutional Neural Networks (GCN) based scheduling algorithm for adhoc networks. In particular, we consider a generalized interference model called thek-tolerant conflict graph model and design an efficient approximation for the well-known Max-Weight scheduling algorithm. A notable feature of this work is that the proposed method do not require labelled data set (NP-hard to compute) for training the neural network. Instead, we design a loss function that utilises the existing greedy approaches and trains a GCN that improves the performance of greedy approaches. Our extensive numerical experiments illustrate that using our GCN approach, we can significantly (4–20%) improve the performance of the conventional greedy approach.
