LF type | Year | Technical approach | Contribution | Challenges |
---|---|---|---|---|
VSTLF | 2022 | ANN [184] | Load forecasting with optimal asset management | 1. Weak performance on unstructured and sparse data 2. Improper short time intervals 3. Insufficient data 4. High calculation time 5. Random and big data 6. Over-fitting problem 7. Management of structured and unstructured data |
Extreme Gradient Boosting (XGBoost) [165] | Forecasts loads specifically for warehouses and logistics consumption | |||
2021 | Markov-chain mixture distribution (MCM) model [185] | Develops a standard model for household power consumption | ||
2020 | FFNN, Neuro-fuzzy, Fuzzy Multi-Objective Decision Making (F-MODM) [186] | Develops load forecasting 1Â h ahead based on weather data | ||
RNN, GRU, BP [187] | Predicting load demand of residential infrastructure for a short period | |||
DML, Apache Spark, Apache Hadoop, Linear Regression, Generalized Linear Regression, Decision Tree, Random Forest, Gradient-boosted trees, Distributed computing [188] | Reduces training time and testing time of load forecasting | |||
CNN, Mutual Information (MI), MI-ANN, Relief F, Kernel Principal Component Analysis (KPCA), BP [189] | Over-fitting issue reduction and computational time reduction using CNN, KPCA, MI etc. | |||
LTSM, Bayesian deep learning, Bayesian Theory [82] | Probabilistic-residential load forecasting for PV systems | |||
2019 | BPNN, Bayesian Regularization, Levenberg–Marquardt algorithm [190] | Load forecasting for individual district buildings | ||
DBN, BP, Phase Space, Reconstruction PSR, Levenberg–Marquardt algorithm [191] | Predicting load forecasting of bus-load forecasting and distributed energy penetration | |||
KNN-ANN, FFNN, Euclidean theory [192] | Load forecasting for hydro-thermal unit generation combining ANN and KNN | |||
2018 | Neuro-fuzzy, ANFIS, Genetic algorithm, Particle Swarm Optimization [193] | Decreasing execution or training time as well as reducing feature selection complexity |