Publication Date:
2024-04-14
Description:
Accurate energy forecasting is important to facilitate the decision-making process in order to achieve higher efficiency and reliability in power system operation and security, economic energy use, contingency scheduling, the planning and maintenance of energy supply systems, and so on. In recent decades, many energy forecasting models have been continuously proposed to improve forecasting accuracy, including traditional statistical models (e.g., ARIMA, SARIMA, ARMAX, multi-variate regression, exponential smoothing models, Kalman filtering, Bayesian estimation models, etc.) and artificial intelligence models (e.g., artificial neural networks (ANNs), knowledge-based expert systems, evolutionary computation models, support vector regression, etc.). Recently, due to the great development of optimization modeling methods (e.g., quadratic programming method, differential empirical mode method, evolutionary algorithms, meta-heuristic algorithms, etc.) and intelligent computing mechanisms (e.g., quantum computing, chaotic mapping, cloud mapping, seasonal mechanism, etc.), many novel hybrid models or models combined with the above-mentioned intelligent-optimization-based models have also been proposed to achieve satisfactory forecasting accuracy levels. It is important to explore the tendency and development of intelligent-optimization-based modeling methodologies and to enrich their practical performances, particularly for marine renewable energy forecasting.
Keywords:
QA75.5-76.95
;
T58.5-58.64
;
Ensemble Empirical Mode Decomposition
;
Brain Storm Optimization
;
asset management
;
institutional investors
;
state transition algorithm
;
kernel ridge regression
;
energy price hedging
;
multi-objective grey wolf optimizer
;
five-year project
;
complementary ensemble empirical mode decomposition (CEEMD)
;
active investment
;
portfolio management
;
Long Short Term Memory
;
time series forecasting
;
LEM2
;
improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN)
;
feature selection
;
Markov-switching GARCH
;
condition-based maintenance
;
substation project cost forecasting model
;
Gaussian processes regression
;
deep convolutional neural network
;
individual
;
wind speed
;
empirical mode decomposition (EMD)
;
crude oil prices
;
artificial intelligence techniques
;
intrinsic mode function (IMF)
;
multi-step wind speed prediction
;
support vector regression (SVR)
;
short term load forecasting
;
energy futures
;
General Regression Neural Network
;
metamodel
;
sparse Bayesian learning (SBL)
;
commodities
;
ensemble
;
comparative analysis
;
crude oil price forecasting
;
electrical power load
;
differential evolution (DE)
;
fuzzy time series
;
kernel learning
;
short-term load forecasting
;
data inconsistency rate
;
renewable energy consumption
;
long short-term memory
;
energy forecasting
;
modified fruit fly optimization algorithm
;
forecasting
;
combination forecasting
;
Markov-switching
;
weighted k-nearest neighbor (W-K-NN) algorithm
;
hybrid model
;
interpolation
;
particle swarm optimization (PSO) algorithm
;
regression
;
diversification
;
thema EDItEUR::U Computing and Information Technology::UY Computer science
Language:
English
Format:
application/octet-stream
Permalink
