Use this URL to cite or link to this record in EThOS:
Title: Commercial risk management in the electricity supply industry
Author: Adjepon-Yamoah, David Yaw
Awarding Body: University of Edinburgh
Current Institution: University of Edinburgh
Date of Award: 2002
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
The introduction of the New Electricity Trading Arrangements (NETA) in the UK from 31st March 2001 changed the nature of electricity trading from a centrally traded marginal pricing mechanism, known as the Pool, to a series of bilateral markets.  This changed the nature of the risks ‘facing market participants notably, higher price volatility, no single reference price on which to base long-term contracts and potentially punitive imbalance charges for participants whose commitments were not met. It would appear that Suppliers will be the major casualties of the changes because their function under the previous system was primarily the billing and metering of customers whereas the introduction of NETA means that they must submit exact information about their demand requirements and contracted position to the System Operator, 4 hours in advance of each half-hour. Any shortfalls between expectation and metered volume will attract prohibitive imbalance charges. Accurate forecasting is essential. This thesis describes effective forecasting methodologies that can be used by Suppliers to forecast their half-hourly demand at Bulk Supply Level. Artificial Neural Networks were selected as the most effective forecasting approach from an examination of the various short-term forecasting methods and by analytical comparison with Multiple Linear Regressions. The Artificial Neural Network (ANN) was optimised and configured to suit NETA’s requirements. The optimised ANN was used to forecast according to the time-of-day, and the day-of-week, to determine the most accurate configuration. Both models had their strengths, with the parallel method being more accurate but the linear, easier to implement. The present methods achieved better financial results than the current industrial standard when compared in a worked example.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available