Feasibility of Economic Forecasting Model Based on Intelligent Algorithm of Smart City

Abstract

Smart cities make better use of space and have less traffic, cleaner air, and more efficient municipal services, improving people’s quality of life. The vast number of vehicles continually seeking to reach crowded spots in smart cities complicates acquiring a public parking space. It presents challenges for both traffic and residents. With such vast populations, road congestion is a serious challenge. It wastes vital resources such as fuel, money, and, most importantly, time. Finding a good location to park is one of the reasons for traffic congestion on the highway. This paper proposes a deep learning-based economic forecasting model (DL-EFM) for long-term economic growth in smart cities. Traffic management is vital for cities to guarantee that people and products can move freely across the city. Many automobiles attempting to reach crowded areas in smart cities make getting a public parking place difficult. It is inconvenient for both drivers and residents. Different traffic management authorities have implemented an artificial neural network (ANN) to resolve the issue, and modern vehicle systems have been coupled with intelligent parking solutions. The experimental outcome of the deep learning-based economic forecasting model improves traffic estimation, accuracy prediction in traffic flow, traffic management, and smart parking when compared to existing methods.