Corpus ID: 85459171

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

  title={A Machine Learning approach to Risk Minimisation in Electricity Markets with Coregionalized Sparse Gaussian Processes},
  author={Daniel Poh and Stephen Roberts and Martin Tegn'er},
  journal={arXiv: Risk Management},
The non-storability of electricity makes it unique among commodity assets, and it is an important driver of its price behaviour in secondary financial markets. The instantaneous and continuous matching of power supply with demand is a key factor explaining its volatility. During periods of high demand, costlier generation capabilities are utilised since electricity cannot be stored and this has the impact of driving prices up very quickly. Furthermore, the non-storability also complicates… Expand


Risk-minimisation in electricity markets: Fixed price, unknown consumption
This paper analyses risk management of fixed price, unspecified consumption contracts in energy markets. We model the joint dynamics of the spot-price and the consumption of electricity, studyExpand
A Model for Hedging Load and Price Risk in the Texas Electricity Market
Energy companies with commitments to meet customers' daily electricity demands face the problem of hedging load and price risk. We propose a joint model for load and price dynamics, which isExpand
Stochastic Modeling of Electricity and Related Markets
The markets for electricity, gas and temperature have distinctive features, which provide the focus for countless studies. For instance, electricity and gas prices may soar several magnitudes aboveExpand
Hedging strategies in energy markets: the case of electricity retailers
As market intermediaries, electricity retailers buy electricity from the wholesale market or self-generate for re(sale) on the retail market. Electricity retailers are uncertain about how muchExpand
Hedging Quantity Risks with Standard Power Options in a Competitive Wholesale Electricity Market
This paper addresses quantity risk in the electricity market and explores several ways of managing such risk. The paper also addresses the hedging problem of a load-serving entity, which providesExpand
Equilibrium Pricing and Optimal Hedging in Electricity Forward Markets
Electricity cannot be economically stored, leading to volatile spot prices and implying that standard cost-of-carry relations are not useful for pricing electricity forward contracts. We model spotExpand
The relationship between spot and futures prices in the Nord Pool electricity market
We analyze 11 years of historical spot- and futures prices from the hydro-dominated Nord Pool electricity market. We find that futures prices tend to be higher than spot prices. The averageExpand
Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models
A novel re-parametrisation of variational inference for sparse GP regression and latent variable models that allows for an efficient distributed algorithm and shows that GPs perform better than many common models often used for big data. Expand
When Gaussian Process Meets Big Data: A Review of Scalable GPs
This article is devoted to reviewing state-of-the-art scalable GPs involving two main categories: global approximations that distillate the entire data and local approximation that divide the data for subspace learning. Expand
Gaussian Processes for Machine Learning
The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics, and deals with the supervised learning problem for both regression and classification. Expand