Skip to Content

Forecasting, Volume 5, Issue 3

2023 September - 5 articles

Cover Story: This paper proposes a new hybrid model to forecast electricity market prices up to four days ahead. The components of the proposed model are combined in two dimensions. In the “vertical” dimension, long short-term memory (LSTM) neural networks and extreme gradient boosting (XGBoost) models produce supplementary price forecasts that are then compared to a price spike threshold to determine the final predictions. In the “horizontal” dimension, five models are designed to extend the forecasting horizon by up to four days. The proposed method is tested using data from Alberta’s electricity market, which are known for their high volatility. The numerical results and an economic application demonstrate the effectiveness of the proposed methodology in enhancing the forecasting accuracy, detecting price spikes, and providing valuable insights for market players. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
  • You may sign up for email alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles (5)

  • Review
  • Open Access
58 Citations
7,089 Views
24 Pages

Data-Driven Methods for the State of Charge Estimation of Lithium-Ion Batteries: An Overview

  • Panagiotis Eleftheriadis,
  • Spyridon Giazitzis,
  • Sonia Leva and
  • Emanuele Ogliari

14 September 2023

In recent years, there has been a noticeable shift towards electric mobility and an increasing emphasis on integrating renewable energy sources. Consequently, batteries and their management have been prominent in this context. A vital aspect of the B...

  • Article
  • Open Access
2 Citations
2,609 Views
26 Pages

Searching for Promisingly Trained Artificial Neural Networks

  • Juan M. Lujano-Rojas,
  • Rodolfo Dufo-López,
  • Jesús Sergio Artal-Sevil and
  • Eduardo García-Paricio

4 September 2023

Assessing the training process of artificial neural networks (ANNs) is vital for enhancing their performance and broadening their applicability. This paper employs the Monte Carlo simulation (MCS) technique, integrated with a stopping criterion, to c...

(This article belongs to the Section Power and Energy Forecasting)
  • Article
  • Open Access
79 Citations
25,293 Views
14 Pages

Large Language Models: Their Success and Impact

  • Spyros Makridakis,
  • Fotios Petropoulos and
  • Yanfei Kang

25 August 2023

ChatGPT, a state-of-the-art large language model (LLM), is revolutionizing the AI field by exhibiting humanlike skills in a range of tasks that include understanding and answering natural language questions, translating languages, writing code, passi...

  • Article
  • Open Access
3 Citations
3,855 Views
14 Pages

Shrinking the Variance in Experts’ “Classical” Weights Used in Expert Judgment Aggregation

  • Gayan Dharmarathne,
  • Gabriela F. Nane,
  • Andrew Robinson and
  • Anca M. Hanea

23 August 2023

Mathematical aggregation of probabilistic expert judgments often involves weighted linear combinations of experts’ elicited probability distributions of uncertain quantities. Experts’ weights are commonly derived from calibration experime...

(This article belongs to the Special Issue Feature Papers of Forecasting 2023)
  • Article
  • Open Access
33 Citations
10,229 Views
23 Pages

A Hybrid Model for Multi-Day-Ahead Electricity Price Forecasting considering Price Spikes

  • Daniel Manfre Jaimes,
  • Manuel Zamudio López,
  • Hamidreza Zareipour and
  • Mike Quashie

19 July 2023

This paper proposes a new hybrid model to forecast electricity market prices up to four days ahead. The components of the proposed model are combined in two dimensions. First, on the “vertical” dimension, long short-term memory (LSTM) neu...

(This article belongs to the Collection Energy Forecasting)
XFacebookLinkedIn
Forecasting - ISSN 2571-9394