A New Approach for Solving Bilevel Fractional/quadratic Green Transportation Problem by Implementing AI with Multi Choice Parameters Under Uncertainty

Abstract

Modern technology is led by artificial intelligence (AI), which is transforming many aspects of our daily life. Urban regions continue to struggle with traffic congestion, which lengthens travel times, increases fuel consumption, and pollutes the environment. To reduce congestion and preserve a smooth traffic flow, AI systems can dynamically assign lanes, synchronize traffic lights, and optimize signal timings. The unpredictability of transportation conditions leads to degradation or damage to the products. In addition, there are elements like growing fuel costs and the desire to cut carbon emissions that make it difficult for businesses to move goods. In this paper a new model is proposed using AI with uncertain cost and multi-choice supply and demand parameters (BFQGMCTP) to develop a Bilevel Fractional/Quadratic Green Transportation Problem. The objective is to concurrently reduce transportation costs, transit-related deterioration costs, and carbon emission costs. Two distinct approaches namely, intuitionistic fuzzy programming and goal programming are used to tackle the current problem, and a comparative study of the two solutions is presented. The computations show that the implementation of AI technology reduced carbon emission, fuel consumption, and travel time by 18%, 15%, and 30% respectively.