English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The non-storability of electricity makes it unique among commodity assets,and it is an important driver of its price behaviour in secondary financialmarkets. The instantaneous and continuous matching of power supply with demandis a key factor explaining its volatility. During periods of high demand,costlier generation capabilities are utilised since electricity cannot bestored and this has the impact of driving prices up very quickly. Furthermore,the non-storability also complicates physical hedging. Owing to these, theproblem of joint price-quantity risk in electricity markets is a commonlystudied theme.  We propose using Gaussian Processes (GPs) to tackle this problem since GPsprovide a versatile and elegant non-parametric approach for regression andtime-series modelling. However, GPs scale poorly with the amount of trainingdata due to a cubic complexity. These considerations suggest that knowledgetransfer between price and load is vital for effective hedging, and that acomputationally efficient method is required. To this end, we use thecoregionalized (or multi-task) sparse GPs which addresses the aforementionedissues.  To gauge the performance of our model, we use an average-load strategy ascomparator. The latter is a robust approach commonly used by industry. If thespot and load are uncorrelated and Gaussian, then hedging with the expectedload will result in the minimum variance position.  Our main contributions are twofold. Firstly, in developing a coregionalizedsparse GP-based approach for hedging. Secondly, in demonstrating that ourmodel-based strategy outperforms the comparator, and can thus be employed foreffective hedging in electricity markets.

A Machine Learning approach to Risk Minimisation in Electricity Markets with Coregionalized Sparse Gaussian Processes