ELMOPP: an application of graph theory and machine learning to traffic light coordination

Abstract

Purpose: This paper presents the Edge Load Management and Optimization through Pseudoflow Prediction (ELMOPP) algorithm, which aims to solve problems detailed in previous algorithms; through machine learning with nested long short-term memory (NLSTM) modules and graph theory, the algorithm attempts to predict the near future using past data and traffic patterns to inform its real-time decisions and better mitigate traffic by predicting future traffic flow based on past flow and using those predictions to both maximize present traffic flow and decrease future traffic congestion. Design/methodology/approach: ELMOPP was tested against the ITLC and OAF traffic management algorithms using a simulation modeled after the one presented in the ITLC paper, a single-intersection simulation. Findings: The collected data supports the conclusion that ELMOPP statistically significantly outperforms both algorithms in throughput rate, a measure of how many vehicles are able to exit inroads every second. Originality/value: Furthermore, while ITLC and OAF require the use of GPS transponders and GPS, speed sensors and radio, respectively, ELMOPP only uses traffic light camera footage, something that is almost always readily available in contrast to GPS and speed sensors.