Demand Forecasting and Location Optimization of Recharging Stations for Electric Vehicles in Carsharing Industries

摘要: Carsharing is an alternative to private car usage. Using electric-vehicles as a substitute fuel vehicles wiser option which leads lower emissions, more energy savings and decreased oil dependency. However, there are some barriers in using electric at large scale carsharing companies. Battery power limitation lack of sufficient infrastructures them. Accurate demand forecasting must for this purpose. In the first part thesis, we investigate problem industries apply four techniques namely simple linear regression, seasonally adjusted forecast, Winter's Model artificial neural networks decide right number be made available each station meet customer requests. The results on randomly generated test datasets show that perform better over other three. second part, location planning recharging stations vehicles. base model used study mathematical optimization proposed by Wang & Lin (2013). Firstly, improve their MIP solve it AIMMS (Advanced Interactive Multidimensional Modeling System). Secondly, propose Genetic Algorithm same implement Matlab. obtained compared with previous work done comparisons performance methods.