HeCSON: Heuristic for Configuration Selectionin Optical Network Planning

05/15/2020

∙

We present a transceiver configuration selection heuristic combining Enhanced Gaussian Noise (EGN) models, which shows a 40% increase in throughput and 87% decrease in execution time, compared to only approximate EGN and Full-Form EGN respectively.

READ FULL TEXT

HeCSON: Heuristic for Configuration Selectionin Optical Network Planning

Transmission-Aware Bandwidth Variable Transceiver Allocation in DWDM Optical Networks

Simulating Execution Time of Tensor Programs using Graph Neural Networks

Learning Heuristic Selection with Dynamic Algorithm Configuration

Improving tasks throughput on accelerators using OpenCL command concurrency

An Approximation Approach for Solving the Subpath Planning Problem

Automatic Selection of Machine Learning Models for WCET-aware Compiler Heuristic Generation

A heuristic extending the Squarified treemapping algorithm

HeCSON: Heuristic for Configuration Selectionin Optical Network Planning

Related Research

Transmission-Aware Bandwidth Variable Transceiver Allocation in DWDM Optical Networks

Simulating Execution Time of Tensor Programs using Graph Neural Networks

Learning Heuristic Selection with Dynamic Algorithm Configuration

Improving tasks throughput on accelerators using OpenCL command concurrency

An Approximation Approach for Solving the Subpath Planning Problem

Automatic Selection of Machine Learning Models for WCET-aware Compiler Heuristic Generation

A heuristic extending the Squarified treemapping algorithm