Neural network load forecasting with weather ensemble predictions

By James W. Taylor, Roberto Buizza. 2002

469 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/c51c48bdbcc93c6f9547cefdbca1a5f892fca742

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 Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

Probabilistic forecasts of the magnitude and timing of peak electricity demand (2005, background): “S. Bouwman and G. Bloemhof are with the KEMA Transmission and Distribution Consulting, 6800 ET Arnhem, The Netherlands (e-mail: Sonja.Bouwman@kema.com; Gabriel.Bloemhof@kema.com).”
A comparison of temperature density forecasts from GARCH and atmospheric models (2004, background): “Taylor and Buizza (2002, 2003) consider the use of weather ensemble predictions in”
Modeling and Forecasting Electricity Loads and Prices: A Statistical Approach (2006, methodology): “Many published studies use neural networks in conjunction with other techniques, like regression trees (Mori and Kosemura 2001), time series (Chow and Leung 1996), wavelets (Reis and da Silva 2005, Zhang and Dong 2001), weather ensemble predictions (Taylor and Buizza 2002), deterministic annealing (”
Probabilistic Load Forecasting via Quantile Regression Averaging on Sister Forecasts (2017, background): “Taylor and Buizza [14] estimated the variance of forecasting errors and prediction intervals (PIs) using load forecasts based on weather ensembles.”
Neural network ensemble operators for time series forecasting (2014, background): “…2006; Yu et al., 2008), fast-moving consumer goods (Trapero et al., 2012), tourism (Pattie and Snyder, 1996), electricity load (Hippert et al., 2001; Taylor and Buizza, 2002), temperature and weather (Roebber et al., 2007; Langella et al., 2010), river ﬂood (Campolo et al., 1999) and hydrological…”
Analyzing the impact of weather variables on monthly electricity demand (2005, methodology): “Parametric multiple regression is preferred in our analysis over neural network [5] or other non-parametric regression approaches [6] because the model is simple to use and easy to control since the inputs can be adjusted for each analysis.”
Short-Term Load Forecasting Methods: An Evaluation Based on European Data (2007, background): “It is well recognized that meteorological variables have a very significant influence on electricity demand (see, for example, [6]).”
Short-term electricity demand forecasting using double seasonal exponential smoothing (2003, methodology): “The multiplicative seasonality version of the method is presented in expressions ( 2 )-(5).”
A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings (2014, methodology): “In Table 4, it is possible to see that for these environments, there is a variety of solutions available: manual and linear models [25,51], expert systems [22,28], models based on ANN [18-19,21,23,26-27,2930,32,35,78,82,84-86,88,91,95,106,112,115-117,126]; and hybrid models with ANN [20,24,37,39,71,”
Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station (2020, background): “Moreover, the weather forecasting is not a linear process as each weather parameter could depend upon one or more other parameters (Elsner and Tsonis 1992; Glahn and Lowry 1972; Taylor and Buizza 2002).”
Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques (2019, background): “However, prior knowledge on the next day ’ s weather condition is missing in the problem context [34].”