Parallel Multi Objective Shortest Path Update Algorithm in Large Dynamic Networks

The multi objective shortest path (MOSP) problem, crucial in various practical domains, seeks paths that optimize multiple objectives. Due to its high computational complexity, numerous parallel heuristics have been developed for static networks. However, real-world networks are often dynamic where...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on parallel and distributed systems Vol. 36; no. 5; pp. 932 - 944
Main Authors: Shovan, S. M., Khanda, Arindam, Das, Sajal K.
Format: Journal Article
Language:English
Published: IEEE 01.05.2025
Subjects:
Aerodynamics
dynamic graph
GPU
Graphics processing units
Heuristic algorithms
Linear programming
Multi-objective shortest path
Optimization
Parallel algorithms
Pareto optimization
Scalability
Search problems
shared-memory
SYCL programming model
Wireless sensor networks
ISSN:1045-9219, 1558-2183
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The multi objective shortest path (MOSP) problem, crucial in various practical domains, seeks paths that optimize multiple objectives. Due to its high computational complexity, numerous parallel heuristics have been developed for static networks. However, real-world networks are often dynamic where the network topology changes with time. Efficiently updating the shortest path in such networks is challenging, and existing algorithms for static graphs are inadequate for these dynamic conditions, necessitating novel approaches. Here, we first develop a parallel algorithm to efficiently update a single objective shortest path (SOSP) in fully dynamic networks, capable of accommodating both edge insertions and deletions. Building on this, we propose DynaMOSP , a parallel heuristic for Dyna mic M ulti O bjective S hortest P ath searches in large, fully dynamic networks. We provide a theoretical analysis of the conditions to achieve Pareto optimality. Furthermore, we devise a dedicated shared memory CPU implementation along with a version for heterogeneous computing environments. Empirical analysis on eight real-world graphs demonstrates that our method scales effectively. The shared memory CPU implementation achieves an average speedup of 12.74× and a maximum of 57.22×, while on an Nvidia GPU, it attains an average speedup of 69.19×, reaching up to 105.39× when compared to state-of-the-art techniques.
ISSN:1045-9219
1558-2183
DOI:10.1109/TPDS.2025.3536357