Filters








1,083 Hits in 7.6 sec

Neural networks in day-ahead electricity price forecasting: Single vs. multiple outputs [article]

Grzegorz Marcjasz, Jesus Lago, Rafał Weron
2020 arXiv   pre-print
In electricity price forecasting, neural networks are the most popular machine learning method as they provide a non-linear counterpart for well-tested linear regression models.  ...  Recent advancements in the fields of artificial intelligence and machine learning methods resulted in a significant increase of their popularity in the literature, including electricity price forecasting  ...  The third dataset contains the French electricity prices from the EPEX SPOT market, the day-ahead load forecast in France and the day-ahead generation forecast in France.  ... 
arXiv:2008.08006v1 fatcat:ian7bin4yzeh3d6pnx537ukdte

Transfer Learning for Electricity Price Forecasting [article]

Salih Gunduz, Umut Ugurlu, Ilkay Oksuz
2022 arXiv   pre-print
Our experiments on five different day-ahead markets indicate that transfer learning improves the performance of electricity price forecasting in a statistically significant manner.  ...  The accurate prediction of the day-ahead electricity prices is an active research field and available data from various markets can be used as an input for forecasting.  ...  Related Works In this section, we provide an overview of the relevant literature on electricity price forecasting, neural networks, local vs. global models, and transfer learning.  ... 
arXiv:2007.03762v3 fatcat:qw3bvdhgdnbepi7mviqa6spjva

Forecasting Nord Pool day-ahead prices with an autoregressive model

Tarjei Kristiansen
2012 Energy Policy  
This paper discusses building multiple Nord Pool forecasting models for hourly day-ahead prices, which utilize the Python programming language.  ...  Price forecasting accuracy is crucially important for electricity trading and risk management.  ...  Singh et al. (2017) , describe an application of a neural network to the price forecasting of New South Wales day-ahead electricity prices.  ... 
doi:10.1016/j.enpol.2012.06.028 fatcat:cdsgzcewxrbp5fwdhxoaukyiiu

Wholesale Electricity Price Forecasting using Integrated Long-term Recurrent Convolutional Network Model [article]

Vasudharini Sridharan, Mingjian Tuo, Xingpeng Li
2021 arXiv   pre-print
Case studies reveal that the proposed ILRCN model is accurate and efficient in electricity price forecasting as compared to the support vector machine (SVM) model, fully-connected neural network model,  ...  Accurate forecasting of electricity prices is very important and is also very challenging since electricity price is highly volatile due to various factors.  ...  Hour-ahead forecasted settlement point price by the LRCN model vs.  ... 
arXiv:2112.13681v1 fatcat:srtfgqyybzhkhj7dg67br5eg5m

Classification of load forecasting studies by forecasting problem to select load forecasting techniques and methodologies [article]

Jonathan Dumas, Bertrand Cornélusse
2020 arXiv   pre-print
The key contribution of this paper is to propose a classification into two dimensions of the load forecasting studies to decide which forecasting tools to use in which case.  ...  This paper can be read in two passes. The first one by identifying the forecasting problem of interest to select the corresponding class into one of the four classification tables.  ...  [10] use feature extraction with random forest and artificial neural network to compute a quarterly day-ahead forecast of a building electricity demand.  ... 
arXiv:1901.05052v2 fatcat:xnc2spbbfzci3nxnixylmucw2i

DEEP LEARNING APPROACH TO FORECASTING ELECTRICITY PRICE FROM LOAD DATA

Vladimir BABUSHKIN, Gheorghe CĂPĂȚÂNĂ
2021 Zenodo  
In this work we propose a deep Convolutional Neural Network-based model for day-ahead electricity price forecasting from historical price/load data and predicted load values.  ...  The accurate forecasting of electricity price and load is essential for maintaining a stable interplay between demand and supply in the dynamic electricity market.  ...  In this work we present a novel CNN-based approach for day ahead electricity price prediction that takes as inputs the historical price and load data along with the predicted load to generate price forecast  ... 
doi:10.5281/zenodo.4457524 fatcat:tnujynnnj5gvlovcrhm27dx3nu

Electrical peak demand forecasting- A review [article]

Shuang Dai, Fanlin Meng, Hongsheng Dai, Qian Wang, Xizhong Chen
2021 arXiv   pre-print
In this paper we first give a precise and unified problem definition of peak load demand forecast.  ...  To this end, this paper provides a timely and comprehensive overview of peak load demand forecast methods in the literature.  ...  [86] was presented to forecast daily peak load up to seven days ahead based on a feed-forward neural network with the steepest descent, Bayesian regularization, resilient and adaptive backpropagation  ... 
arXiv:2108.01393v1 fatcat:2egx6ozkqzgvpfamdtpd6r2d4a

Demand Forecasting in Smart Grid Using Long Short-Term Memory [article]

Koushik Roy, Abtahi Ishmam, Kazi Abu Taher
2021 arXiv   pre-print
In this paper, an LSTM based model using neural network architecture is proposed to forecast power demand.  ...  From the findings, it is clear that the inclusion of neural network in predicting power demand reduces the error of prediction significantly.  ...  0.9951 generation fossil gas 0.5489 generation fossil oil 0.4971 generation hydro water reservoir 0.4795 price day ahead 0.4739 price actual 0.4361 forecast solar day ahead 0.4044 generation  ... 
arXiv:2107.13653v1 fatcat:4dv3gasqb5e2bhbh4u6rl4ym3y

A Multi-Horizon Quantile Recurrent Forecaster [article]

Ruofeng Wen, Kari Torkkola, Balakrishnan Narayanaswamy, Dhruv Madeka
2018 arXiv   pre-print
The performance of the framework is demonstrated in an application to predict the future demand of items sold on Amazon.com, and in a public probabilistic forecasting competition to predict electricity  ...  price and load.  ...  Figure 5 . 5 MQ-RNN Forecasts for GEFCom 2014 dataset. Upper: electricity price, task 12, to forecast 24 hours ahead. Lower: electricity load, task 4, to forecast 744 hours ahead.  ... 
arXiv:1711.11053v2 fatcat:mjf4ablybnbhtbyvdybstkjtpa

A Comparative Analysis of Machine Learning Approaches for Short-/Long-Term Electricity Load Forecasting in Cyprus

Davut Solyali
2020 Sustainability  
In this paper, machine learning strategies including artificial neural network (ANN), multiple linear regression (MLR), adaptive neuro-fuzzy inference system (ANFIS), and support vector machine (SVM) were  ...  Estimating the electricity load is a crucial task in the planning of power generation systems and the efficient operation and sustainable growth of modern electricity supply networks.  ...  Dash [17] used the new hybrid adaptive autoregressive moving-average model for forecasting day-ahead mixed short-term demand and electricity prices in smart grids.  ... 
doi:10.3390/su12093612 fatcat:o7j62z4zdfbg5o47bjdbjhpdny

Recent advances in electricity price forecasting: A review of probabilistic forecasting

Jakub Nowotarski, Rafał Weron
2018 Renewable & Sustainable Energy Reviews  
Since the inception of competitive power markets two decades ago, electricity price forecasting (EPF) has gradually become a fundamental process for energy companies' decision making mechanisms.  ...  Academics and practitioners alike have come to understand that probabilistic electricity price (and load) forecasting is now more important for energy systems planning and operations than ever before.  ...  "forecasting electricity price" OR "day-ahead price forecasting" OR "day-ahead mar* price forecasting" OR (gefcom2014 AND price) OR (("electricity market" OR "electric energy market") AND "price forecasting  ... 
doi:10.1016/j.rser.2017.05.234 fatcat:zqukxsgaz5dkhocb76z52y6pfm

Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting

D. Benaouda, F. Murtagh, J.-L. Starck, O. Renaud
2006 Neurocomputing  
neural network (ERN) and the general regression neural network (GRNN) models.  ...  We propose a wavelet multiscale decomposition based autoregressive approach for the prediction of one-hour ahead ahead load based on historical electricity load data.  ...  ACKNOWLEDGEMENTS We are very grateful to NEMMCO for the electricity load and price data.  ... 
doi:10.1016/j.neucom.2006.04.005 fatcat:gbjrl4kodrd5ppcbsytjtujpgq

Electricity price forecasting: A review of the state-of-the-art with a look into the future

Rafał Weron
2014 International Journal of Forecasting  
A variety of methods and ideas have been tried for electricity price forecasting (EPF) over the last 15 years, with varying degrees of success.  ...  The paper also looks ahead and speculates on the directions EPF will or should take in the next decade or so.  ...  forecast balancing market and power exchange day-ahead prices jointly in Poland using a neural network.  ... 
doi:10.1016/j.ijforecast.2014.08.008 fatcat:gn47m4pvybgt5mx7c37fxp4tye

Bayesian deep learning based method for probabilistic forecast of day-ahead electricity prices

Alessandro Brusaferri, Matteo Matteucci, Pietro Portolani, Andrea Vitali
2019 Applied Energy  
The availability of accurate day-ahead energy prices forecasts is crucial to achieve a successful participation to liberalized electricity markets.  ...  Experiments have been performed on two day-ahead markets characterized by different behaviors.  ...  Conclusions In this paper we have presented a novel method to achieve probabilistic day-ahead electricity prices forecasting based on Bayesian deep learning.  ... 
doi:10.1016/j.apenergy.2019.05.068 fatcat:vfer6r7hfve3rmj6ymqcmkq6um

Multivariate Probabilistic Forecasting of Intraday Electricity Prices using Normalizing Flows [article]

Eike Cramer, Dirk Witthaut, Alexander Mitsos, Manuel Dahmen
2022 arXiv   pre-print
In Germany, the intraday electricity price typically fluctuates around the day-ahead price of the EPEX spot markets in a distinct hourly pattern.  ...  The model captures the emerging hourly pattern by considering the four 15 min intervals in each day-ahead price interval as a four-dimensional joint distribution.  ...  This work was performed as part of the Helmholtz School for Data Science in Life, Earth and Energy (HDS-LEE) and received funding from the Helmholtz Association of German Research Centres.  ... 
arXiv:2205.13826v1 fatcat:ffnoynu5wzfczof36tdr6vh27e
« Previous Showing results 1 — 15 out of 1,083 results