Resilience Analysis of Urban Road Networks Based on Adaptive Signal Controls: Day-to-Day Traffic Dynamics with Deep Reinforcement Learning

Abstract

Improving the resilience of urban road networks suffering from various disruptions has been a central focus for urban emergence management. However, to date the effective methods which may mitigate the negative impacts caused by the disruptions, such as road accidents and natural disasters, on urban road networks is highly insufficient. This study proposes a novel adaptive signal control strategy based on a doubly dynamic learning framework, which consists of deep reinforcement learning and day-to-day traffic dynamic learning, to improve the network performance by adjusting red/green time split. In this study, red time split is regarded as extra traffic flow to discourage drivers to use affected roads, so as to reduce congestion and improve the resilience when urban road networks are subject to different levels of disruptions. In addition, we utilize the convolution neural network as Q-network to approximate Q values, link flow distribution and link capacity are regarded as the state space, and actions are denoted as red/green time split. A small network is utilized as a numerical example, and a fixed time signal control and other two adaptive signal controls are employed for the comparisons with the proposed one. The results show that the proposed adaptive signal control based on deep reinforcement learning can achieve better resilience in most of the cases, particularly in the scenarios of moderate and severe disruptions. This study may shed light on the advantages of the proposed adaptive signal control dealing with major emergencies compared to others.

Benchmark Analysis for Robustness of Multi-Scale Urban Road Networks Under Global Disruptions

“…The equations above include the objective (6), and a series of constraints, respectively, for conservation (7) and (8), and nonnegative flows (9). The link cost function increases monotonically such that the link flow pattern of UE is unique [59] and the objective of the program is convex.…”

“…Urban road networks (URN) are crucial infrastructure components of urban transportation and constitute an essential backbone underpinning most social and economic activities [2,3]. Road traffic networks and infrastructure are vulnerable to disasters [4][5][6], however, some of which, like extreme weather events or earthquakes, can be so disruptive as to lead to a complete system failure [7,8]. In such circumstances the direct loss of life and economic loss arising from the disaster event itself are supplemented by indirect losses resulting from delays caused by the inability of emergency services and humanitarian agencies to use the road network effectively [4,9].…”

“…The differences in types of network, the infrastructure they use and in the constraints and objectives applied to those networks have meant that it has been difficult for scholars to agree on a definition of what "robustness" actually means in the context of networked systems. In the context of electrical networks, robustness has been defined, variously, as "the degree to which a system or component can function correctly in the presence of invalid inputs or stressful environmental conditions" [10] and "the ability to keep the network structure (function) intact when exposed to perturbations" [7]. In [11], Immers et al consider robustness to be "the degree to which a system is capable of functioning according to its design specifications in the case of serious disruptions".…”

Dynamic Measurement Analysis of Urban Innovation Ability and Ecological Efficiency in China

“…Based on the analysis of the relationship between urban air pollution and the regional economy by Tiening and Lina [11], Huang and Fang [12] hold that the relationship between urbanization and the ecological environment conforms to the characteristics of a "double exponential curve." Wen-Long Shang et al analysed the relationship between urban management level and environment from urban transportation system, and studies big data and traffic path planning by using GIS technology, which shows the importance of information technology in urban management [13][14][15].…”

Providing a Multiproduct and Multiperiodic Model for Closed‐Loop Green Supply Chain under Conditions of Uncertainty Based on a Fuzzy Approach for Solving Problem of Business Market

“…e MILP model was created by Zhou et al [16] to assist decision-makers in planning oil pipeline supply chain networks. [17] Yang et al After that, Shang et al [18,19] looked into the green production of substations as well as the optimization of urban road transportation networks.…”