Grouped Gaussian processes for solar power prediction
- 484 Downloads
We consider multi-task regression models where the observations are assumed to be a linear combination of several latent node functions and weight functions, which are both drawn from Gaussian process priors. Driven by the problem of developing scalable methods for forecasting distributed solar and other renewable power generation, we propose coupled priors over groups of (node or weight) processes to exploit spatial dependence between functions. We estimate forecast models for solar power at multiple distributed sites and ground wind speed at multiple proximate weather stations. Our results show that our approach maintains or improves point-prediction accuracy relative to competing solar benchmarks and improves over wind forecast benchmark models on all measures. Our approach consistently dominates the equivalent model without coupled priors, achieving faster gains in forecast accuracy. At the same time our approach provides better quantification of predictive uncertainties.
KeywordsGaussian processes multi-task learning Bayesian nonparametric methods scalable inference solar power prediction
This research was conducted with support from the Cooperative Research Centre for Low-Carbon Living in collaboration with the University of New South Wales and Solar Analytics Pty Ltd.
- Álvarez, M., & Lawrence, N. D. (2009). Sparse convolved Gaussian processes for multi-output regression. In Neural Information Processing Systems.Google Scholar
- Álvarez, M. A., Luengo, D., Titsias, M. K., & Lawrence, N. D. (2010). Efficient multioutput Gaussian processes through variational inducing kernels. In Artificial Intelligence and Statistics.Google Scholar
- Bonilla, E. V., Chai, K. M. A., & Williams, C. K. I. (2008). Multi-task Gaussian process prediction. In Neural Information Processing Systems.Google Scholar
- Bonilla, E. V., Krauth, K., & Dezfouli, A. (2016). Generic inference in latent Gaussian process models. arxiv:1609.00577.
- Dahl, A. & Bonilla, E. (2017). Scalable Gaussian process models for solar power forecasting. In W. L. Woon, Z. Aung, O. Kramer, & S. Madnick (Eds.), Data analytics for renewable energy integration: Informing the generation and distribution of renewable energy (pp. 94–106). Springer International Publishing.Google Scholar
- Dezfouli, A., & Bonilla, E. V. (2015). Scalable inference for Gaussian process models with black-box likelihoods. In Neural Information Processing Systems.Google Scholar
- Gardner, J. R., Pleiss, G., Wu, R., Weinberger, K. Q., & Wilson, A. G. (2018). Product kernel interpolation for scalable Gaussian processes. arXiv:1802.08903.
- Goovaerts, P. (1997). Geostatistics for natural resources evaluation. Oxford: Oxford University Press.Google Scholar
- Hensman, J., Matthews, A., & Ghahramani, Z. (2015). Scalable variational Gaussian process classification. In AISTATS.Google Scholar
- Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. CoRR. arXiv:1412.6980.
- Kingma, D. P., & Welling, M. (2014). Auto-encoding variational Bayes. International Conference on Learning Representations.Google Scholar
- Krauth, K., Bonilla, E. V., Cutajar, K., & Filippone, M. (2017). AutoGP: Exploring the capabilities and limitations of Gaussian process models. In Uncertainty in Artificial Intelligence.Google Scholar
- Matthews, A. G. de G., van der Wilk, M., Nickson, T., Fujii, K., Boukouvalas, A., León-Villagrá, P., et al. (2017). GPflow: A Gaussian process library using TensorFlow. Journal of Machine Learning Research, 18(40), 1–6.Google Scholar
- Nguyen, T. V. & Bonilla, E. V. (2014). Automated variational inference for Gaussian process models. In Neural Information Processing Systems.Google Scholar
- Remes, S., Heinonen, M., & Kaski, S. (2017). A mutually-dependent Hadamard kernel for modelling latent variable couplings. In M.-L. Zhang & Y.-K. Noh (Eds.), Proceedings of the Ninth Asian Conference on Machine Learning, vol. 77 of Proceedings of Machine Learning Research, (pp. 455–470).Google Scholar
- Rezende, D. J., Mohamed, S., & Wierstra, D. (2014). Stochastic backpropagation and approximate inference in deep generative models. In International Conference on Machine Learning.Google Scholar
- Teh, Y. W., Seeger, M., & Jordan, M. I. (2005). Semiparametric latent factor models. In Artificial Intelligence and Statistics.Google Scholar
- Titsias, M. (2009). Variational learning of inducing variables in sparse Gaussian processes. In AISTATS.Google Scholar
- Wilson, A. G., Knowles, D. A., & Ghahramani, Z. (2012). Gaussian process regression networks. In International Conference on Machine Learning.Google Scholar