An immune memory inspired case-based reasoning system to control interrupted flow at a signalized intersection

To monitor and control traffic at signalized intersections, several traffic signal control systems (TSCSs) were developed based on optimization and artificial intelligence techniques. Unfortunately, existing approaches put little emphasis on providing concepts and mechanisms that are generic enough to deal with a variety of disturbances while maintaining traffic fluidity. Moreover, only a few works have investigated case-based reasoning (CBR) to control traffic at signalized intersections. Existing works usually state that the case-base is created using experts' knowledge but do not specify how this knowledge is acquired and how the case-base is built. The contribution of this study is threefold. First, a new TSCS is designed to monitor and control traffic at a signalized intersection using innovative concepts and mechanisms borrowed from the biological immune memory and secondary immune response. Immune memory provides the concepts to represent cases to deal with disturbances in a more generic way, and immune secondary response mechanisms guide the design of a CBR system to monitor traffic and control disturbances. Second, a new learning algorithm for the creation of the case-base combining simulation-optimisation, condensed nearest neighbour algorithm and a rule-based system are developed. Third, the performance of the suggested TSCS is assessed by benchmarking it against two standard control strategies from the literature, namely fixed-time traffic signal control and the longest queue first-maximal weight matching algorithm. The suggested TSCS is implemented in Python and applied on an intersection simulated using VISSIM, a state-of-the-art traffic simulation software. The results show that the suggested TSCS is able to handle different traffic scenarios with competitive performance, and that it is recommended for extreme situations involving blocked approaches and high traffic flow.