A Physical Testbed for Intelligent Transportation Systems

Abstract

Intelligent transportation systems (ITSs) and other smart-city technologies are increasingly advancing in capability and complexity. While simulation environments continue to improve, their fidelity and ease of use can quickly degrade as newer systems become increasingly complex. To remedy this, we propose a hardware-and software-based traffic management system testbed as part of a larger smart-city testbed. It comprises a network of connected vehicles, a network of intersection controllers, a variety of control services, and data analytics services. The main goal of our testbed is to provide researchers and students with the means to develop novel traffic and vehicle control algorithms with higher fidelity than what can be achieved with simulation alone. Specifically, we are using the testbed to develop an integrated management system that combines model-based control and data analytics to improve the system performance over time. In this paper, we give a detailed description of each component within the testbed and discuss its current developmental state. Additionally, we present initial results and propose future work.

A Review of IoT-Based Smart City Development and Management

“…ITS usually focuses on four primary aspects: monitoring, communication, energy efficiency, and lighting control. There are testbeds for the traffic management system that combine data analysis and model-based control to enhance performance, consisting of a network of connected vehicles, intersection controllers, data analysis services, and a variety of control services [75]. Other research focuses on vehicle routing, as travel time ambiguity affects identifying optimal routes and schedules on very congested urban roads and safe propagation using convolutional neural network [76].…”

Software‐in‐the‐loop simulation for developing and testing carbon‐aware applications

“…The use of testbeds is common practice in the development of software that depends on the behavior of physical systems. [11][12][13][14] However, in many cases the installation and operation of physical testbeds is impractical, unsafe, or simply too expensive. In these cases, SiL simulation can be an effective alternative, where real software is executed in a partially simulated domain environment.…”

“…The use of testbeds is common practice in the development of software that depends on the behavior of physical systems 11‐14 . However, in many cases the installation and operation of physical testbeds is impractical, unsafe, or simply too expensive.…”

Learning-based Model Predictive Control for Smart Building Thermal Management

“…One of the efficient model-based techniques in building thermal control is model predictive control (MPC) [3]. Just like other model-based strategies, MPC requires an accurate model (mathematical model) to predict the process inputs/outputs and obtain the control signal [4][5][6]. The performance of MPC is directly relevant to the accuracy of the model, and it diminishes by the model inaccuracy.…”