Two-Stream Fused Fuzzy Deep Neural Network for Multiagent Learning

Fang, Baofu; Zheng, Caiming; Wang, Hao; Yu, Tingting

doi:10.1109/tfuzz.2022.3214001

Cited by 9 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, many scholars have focused on the method of traffic signal control under uncertainty. Various models handling uncertainty have been introduced, such as mean-standard deviation model (MSD), the conditional value-at-risk model and the min-max model [22], discretization model [23], constrained min-max model [24], dynamics model [25], two-stage stochastic planning method [26], offline scenario-based framework [27], and multiagent reinforcement learning [28,29]. These models also show their effectiveness and robustness in the problem of traffic signal control.…”

Section: Literature Reviewmentioning

confidence: 99%

A two‐stage robust optimal traffic signal control with reversible lane for isolated intersections

Sun,

Wang,

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

The integrated design of traffic signal control (TSC) and reversible lane (RL) is an effective way to solve the problem of tidal congestion with uncertainty at isolated intersections, because of its advantage in making full use of temporal‐spatial transportation facilities. Considering the contradiction between the dynamic TSC scheme and the fixed RL scheme in one period, a two‐stage optimization method based on improved mean‐standard deviation (MSD) model for isolated intersections with historical and real‐time uncertain traffic flow is proposed. In the first stage, applying the same‐period historical data of multiple days, a robust optimal traffic signal control model with reversible lane based on MSD model (MSD‐RTR model) is put forward to obtain the fixed RL scheme and the compatible initial TSC scheme. A double‐layer nested genetic algorithm (DN‐GA) is designed to solve this model. In the second stage, applying real‐time period data and multi‐day same‐period historical data, a robust optimal dynamic traffic signal control model based on MSD model (MSD‐RDT model) is put forward to obtain the dynamic TSC scheme. Three modes which reflect the different weights of historical period and real‐time period in this MSD‐RDT model are presented to improve the model stability, and a multi‐mode genetic algorithm (MM‐GA) is designed. Finally, a case study is presented to demonstrate the efficiency and applicability of the proposed models and algorithms.

show abstract