Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Tripathy, D.S.

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Multi-time instant probabilistic PV generation forecasting using quantile regression forests
    (Institute of Electrical and Electronics Engineers Inc., 2020) Tripathy, D.S.; Prusty, B.; Jena, D.; Sahu, M.K.
    Long-term planning for the reinforcement of power systems with PV-integration requires multi-time instant PV generation uncertainty modeling. Probabilistic forecasting of PV generation plays a vital role in the uncertainty management in power systems with PV penetration. An ensemble approach for probabilistic PV generation forecasting, such as the quantile regression forests, proves to be a suitable model because it models the uncertain PV generation more accurately compared to single mean models. The inherent nature of forests to prevent over-fitting by "bagging" the training data is an advantage. Also, the optimal choice of the model hyper-parameters adds to its efficiency as a forecaster. Further, the stochastic nature of weather conditions needs the selection of sensible regressors for the proposed quantile regression forests framework based on the physics of the underlying phenomenon. Real-world data for PV generation collected at multiple instants of time from the USA are employed to test the efficacy of the proposed probabilistic forecasting. The proposed model is compared against the basic quantile regression approach in terms of the accuracy of the quantile forecasts as well as prediction intervals using suitable scores and error metrics. © 2020 IEEE.
  • No Thumbnail Available
    Item
    Short-term PV generation forecasting using quantile regression averaging
    (Institute of Electrical and Electronics Engineers Inc., 2020) Tripathy, D.S.; Prusty, B.R.; Jena, D.
    The globally increasing demand for energy to carry out the various day-to-day activities needs renewable sources in conjunction with existing power plants. PV technology has seen tremendous growth over the past decades. However, the integration of PV generation to the power systems invites numerous planning and operational challenges. In the short-term, the real-time operation of PV-integrated power systems requires the characterization of the uncertainties associated with the PV generation. A probabilistic framework, such as the quantile regression averaging (QRA), has been successful in forecasting load power and electricity spot prices. This paper applies QRA to accomplish a probabilistic forecast of PV generation using its historical record from a rooftop installation at Lincoln, USA. This paper's main contribution is the use of two appropriate individual point forecasters, i.e., autoregressive conditional heteroscedastic and multiple linear regression models, to complement each other and make accurate quantile forecasts. The proposed model is used in the short-term forecasting of PV generation for the four major seasons up to two weeks ahead. A detailed result analysis shows that the combination of both models improves overall forecasting performance rather than using any of the models alone. © 2020 IEEE.