Novel Techniques for Gas Demand Modeling and Forecasting

The ability to provide accurate forecasts of future gas demand has a major impact on
several business processes for Gas Regions in the UK and elsewhere in the world. Long
term forecasts provide the guidance for major structural needs, while short term forecasts
guide the operations management on requirements of supply purchase, supply storage and
delivery. Accurate forecasts guarantee optimum and safe gas supply at the lowest cost.
Currently there is no single technique that produces the perfect forecast, this research
will attempt to improve on current methods by applying Non-Linear techniques. The technique
to be tested is defined as ”Non-Linear Autoregressive Moving Average with eXogeneous
Inputs, polynomials, and a Forward Regression with Orthogonal Least Squares
estimation procedure”.
The goal of the research is is to produce a Mean Average Percentage Error of between
4-6% or better, which was proposed by DNV GL (supplier of software for the Gas Industry),
as a valid level of error to make any new methodology of value.