Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals

By Hao Quan, Dipti Srinivasan, Abbas Khosravi. IEEE Transactions on Neural Networks and Learning Systems, 2014

571 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/4220213d29d56e827ad4ecd62539daf7512a7958

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Short-Term Wind Speed or Power Forecasting With Heteroscedastic Support Vector Regression (2016, background): “Generally speaking, there are three different paradigms in wind speed prediction [4]–[8]: 1) physical; 2) spatial correlation; and 3) statistical (also called data-driven).”
Deep Learning-Based Multivariate Probabilistic Forecasting for Short-Term Scheduling in Power Markets (2019, background): “In this way, different approaches for obtaining such uncertainty regions (or by extrapolation densities) can be found in the literature for respectively wind power [3]– [ 7 ] , PV generation [8], load [7], [9] and electricity prices [10], [11].”
Residential probabilistic load forecasting: A method using Gaussian process designed for electric load data (2018, methodology): “Considering [57], even though their data was with 30min resolution, they forecasted the aggregate load which was smoother than the individual load of a single household that was forecasted here.”
History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining (2018, methodology): “In the study by Quan et al. (2014), a metric called coverage width-based criterion (CWC) is used to combine the two metrics mentioned above.”
Nearest-neighbor methodology for prediction of intra-hour global horizontal and direct normal irradiances (2015, background): “Popular approaches to quantify PIs often rely on the assumption of normality, but in this case such assumption is not always true.”
Pattern-based local linear regression models for short-term load forecasting (2016, methodology): “Some examples of using neural networks in STLF are: [6], where the complexity of the network is controlled by the Bayesian approach, [7], where a new hybrid forecasting method composed of wavelet transform, multilayer perceptron and evolutionary algorithm is proposed, [8], where a generic framework ”
Deep belief network based electricity load forecasting: An analysis of Macedonian case (2016, methodology): “Currently, the most widely used methods are those based on arti ﬁ cial neural networks [37,38] applied in this area since the 1980s.”
A novel stacked generalization ensemble-based hybrid LGBM-XGB-MLP model for Short-Term Load Forecasting (2021, background): “The STLF ensures high asset commitment and ﬂ exibility of the grid to enhance the serviceability of electricity operations over several time scales for day-to-day operations [7].”