Toggle Main Menu Toggle Search

Open Access padlockePrints

Demand forecasting over complex geographical networks: the case of Northern Gas Networks

Lookup NU author(s): Dr Kevin Wilson, Dr Sarah Heaps, Dr Malcolm Farrow



This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND).


Organisations which distribute resources over complex networks need to be able to meet demand.They require accurate forecasts of demand across the network. We consider short term demand forecasting forNorthern Gas Networks (NGN), who deliver gas to 2.7 million homes and businesses. They require forecasts atdifferent locations for each hour over each day. The locations are of distinct types by the dominant user groups.For each we develop a time series model to forecast short term demand, utilising seasonality at monthly, dailyand hourly levels and temperature. Annually NGN produce Gas Demand forecasts for a decade, which supportinvestment and planning and inform National Grid. We develop time-series models and Bayesian inference toprovide forecasts of daily demand. A challenge arises in modelling demand by industry where weather has lesspredictive power and step changes occur due to large consumers switching to or from gas.

Publication metadata

Author(s): Wilson KJ, Heaps SE, Farrow M

Editor(s): Walls, L; Revie, M; Bedford, T;

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: Risk, Reliability and Safety: Innovating Theory and Practice: Proceedings of ESREL 2016

Year of Conference: 2016

Pages: 425-432

Print publication date: 13/09/2016

Acceptance date: 13/06/2016

Date deposited: 03/11/2016

Publisher: CRC Press


Library holdings: Search Newcastle University Library for this item

Series Title: Risk, Reliability and Safety: Innovating Theory and Practice: Proceedings of ESREL 2016

ISBN: 9781138029972