Optimizing Mobility: A Study of Traffic Congestion and Route Planning in Cosmopolitan City

Abstract

The demand for transport has been steadily increasing because of urbanization, which has resulted in a number of significant problems, including the overloading of infrastructure, disruptions to traffic flow, and vehicular emissions. As a direct consequence of this, finding solutions to these issues has emerged as one of the top priorities for governments all over the world.  In cosmopolitan areas, the priority to target has been determined to be over-saturated intersections. These are intersections where the traffic density is high and the levels of vehicle exhaust pollution are large.

Chandigarh is one of the most rapidly developing cities in India. However, with the increasing population and number of vehicles, traffic congestion has become a serious problem, making it difficult for citizens to commute efficiently. Providing commuters with alternate routes that they would be willing to take is a crucial step in addressing traffic congestion. This idea has been described as a strategic routing dilemma, in which additional routes have to be recommended in addition to the already existing ones. The various routes issue, which involves finding various routes from a given starting point to a destination expands on this idea. Improving traffic control optimization to minimize overall travel time is a big problem because existing systems generally focus on adaptive techniques for typical traffic situations. This makes effective driver allocation across numerous routes critical. Optimizing control plans during serious accidents, especially when many lanes or entire intersections are affected, is still a problem. In order to tackle this issue, it is required to provide a novel optimization framework that combines the dependability of genetic algorithms (GA) with the speed and efficiency of fast machine learning (ML) techniques. A genetic algorithm was utilized to efficiently choose advantageous courses using a traffic congestion index. The effectiveness of the suggested genetic algorithm was then evaluated by comparing it to other optimization approaches. The results illustrated that the genetic algorithm found the ideal solution more quickly than the other optimization strategies. Furthermore, in order to predict vehicular traffic patterns using the number of registered vehicles within a city, a variety of modeling techniques are employed out of which the autoregressive integrated moving average (ARIMA) model turns out to be an effective method for predicting short-term traffic.