Optimisation of the bidding strategy for wind power trading

David I. Hamilton; David McMillan; Victoria M. Catterson

Optimisation of the bidding strategy for wind power trading

David I. Hamilton, David McMillan, Victoria M. Catterson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

33 Downloads (Pure)

Abstract

The optimal bidding strategy for trading electricity from a wind farm is not always clear. This paper outlines a method for predicting whether the market will be long or short and uses this information to select the best quantile regression for the current market conditions. Results from a simulation with a 2.5MW turbine produced a savings of over £2,000 compared to using only a P50 forecaster.

Original language	English
Title of host publication	PowerTech, 2015 IEEE Eindhoven
Publisher	IEEE
Number of pages	5
ISBN (Electronic)	9781479976935
Publication status	Published - 29 Jun 2015
Event	IEEE PowerTech 2015 - Eindhoven, Netherlands Duration: 29 Jun 2015 → 2 Jul 2015

Conference

Conference	IEEE PowerTech 2015
Country/Territory	Netherlands
City	Eindhoven
Period	29/06/15 → 2/07/15

Keywords

wind energy
energy markets
quantille regression
wind forecasting
pricing
predictive models
artificial neural networks
generators
wind farms
electricity supply industry

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Hamilton-etal-Powertech2015-Optimisation-of-the-bidding-strategy-for-wind-power-tradingAccepted author manuscript, 281 KB

Doctoral training centre in wind energy systems
Leithead, B. & Infield, D.
EPSRC (Engineering and Physical Sciences Research Council)
1/10/09 → 31/03/18
Project: Research - Studentship

Cite this

@inproceedings{642c9fcca9454f568826848efb977077,

title = "Optimisation of the bidding strategy for wind power trading",

abstract = "The optimal bidding strategy for trading electricity from a wind farm is not always clear. This paper outlines a method for predicting whether the market will be long or short and uses this information to select the best quantile regression for the current market conditions. Results from a simulation with a 2.5MW turbine produced a savings of over £2,000 compared to using only a P50 forecaster.",

keywords = "wind energy, energy markets, quantille regression, wind forecasting, pricing, predictive models, artificial neural networks, generators, wind farms, electricity supply industry",

author = "Hamilton, {David I.} and David McMillan and Catterson, {Victoria M.}",

note = "{\textcopyright} 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; IEEE PowerTech 2015 ; Conference date: 29-06-2015 Through 02-07-2015",

year = "2015",

month = jun,

day = "29",

language = "English",

booktitle = "PowerTech, 2015 IEEE Eindhoven",

publisher = "IEEE",

}

TY - GEN

T1 - Optimisation of the bidding strategy for wind power trading

AU - Hamilton, David I.

AU - McMillan, David

AU - Catterson, Victoria M.

N1 - © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2015/6/29

Y1 - 2015/6/29

N2 - The optimal bidding strategy for trading electricity from a wind farm is not always clear. This paper outlines a method for predicting whether the market will be long or short and uses this information to select the best quantile regression for the current market conditions. Results from a simulation with a 2.5MW turbine produced a savings of over £2,000 compared to using only a P50 forecaster.

AB - The optimal bidding strategy for trading electricity from a wind farm is not always clear. This paper outlines a method for predicting whether the market will be long or short and uses this information to select the best quantile regression for the current market conditions. Results from a simulation with a 2.5MW turbine produced a savings of over £2,000 compared to using only a P50 forecaster.

KW - wind energy

KW - energy markets

KW - quantille regression

KW - wind forecasting

KW - pricing

KW - predictive models

KW - artificial neural networks

KW - generators

KW - wind farms

KW - electricity supply industry

M3 - Conference contribution book

BT - PowerTech, 2015 IEEE Eindhoven

PB - IEEE

T2 - IEEE PowerTech 2015

Y2 - 29 June 2015 through 2 July 2015

ER -

Optimisation of the bidding strategy for wind power trading

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Projects

Doctoral training centre in wind energy systems

Cite this