Annual Fuel Demand Forecasting for International Aircraft by Fuzzy Logic

Abstract

Forecasting is the prediction of future events and conditions and is a key element in service organizations,especially banks, for management decision-making. In preparing a projection of a company's future revenues and expenses, a sales forecast must first be prepared. Whereas expenses can be controlled by management on a day by day basis, sales occur only when outside parties make a proactive purchase decision. Management, by devising a successful marketing strategy, influences the buying decisions of its customers but cannot make the customers buy. Therefore, management must somehow predict or forecast how many units will be sold and at what price and during what time frames. Fuel is a major cost expense for air carriers. A typical airline spends 10% of its operating budget on the purchase of jet fuel, which even exceeds its expenditures on aircraft acquisitions. [1] Thus, it is imperative that fuel consumption be managed as wisely as possible. [8]This study explores the potential of the neurofuzzy computing paradigm to model the annual fuel demand forecasting for international aircraft in India. [8] The neurofuzzy computing technique is a combination of a fuzzy computing approach and an artificial neural network technique. Parameter optimization in the model was performed by a combination of back propagation and least squares error methods. [8] Performance of the neurofuzzy model was comprehensively evaluated with that of independent fuzzy and neural network models developed for the same basin. [11]Fuzzy based forecasted annual demand is further computed by time series analysis forecasting. Error and absolute deviations are predicted and tracking signal is evaluated for the same.