Table 11 LTLF techniques
LF type | Year | Technical approach | Contribution | Challenges |
|---|---|---|---|---|
LTLF | 2021 | Improved ANN model with an Adaptive Backpropagation Algorithm (ABPA) [211] | Fixes deviations between trained datasets and newly collected forecast datasets | 1. Randomness 2. Uncertainty of output |
Hybrid Support Vector Regression (HSVR) [212] | Long-term load forecasting for real industrial power consumption in China | |||
Feature-fusion-kernel-based Gaussian process model [213] | Converts one dimensional time-series data into multidimensional features to minimize the gap between original datasets and forecasting | |||
2020 | Takagi–Sugeno model, RFNN, Fuzzy Rules, Nonlinear System, BP [214] | Retaining temperature data from weather stations with LTLF process and holiday feature management | ||
FFNN. BPNN [215] | Mean square error reduction for smart grid consisting of low voltage | |||
LSTM, ANN [216] | Enhancing system marginal price using ANN | |||
DML, Apache Spark, Apache Hadoop, Linear Regression, Generalized Linear Regression, Decision Tree, Random Forest, Gradient-boosted trees, Distributed computing [188] | Single residential user load forecasting using CNN on time series datasets | |||
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. | |||
2019 | Parallel deep learning, DC-DC converter [207] | Ensuring control of hybrid energy storing system in a distributed system using parallel deep learning | ||
2018 | Neuro-fuzzy, ANFIS, BPNN, Levenberg–Marquardt algorithm [217] | Effectively predicting long term load forecasting using ANN | ||
BPNN [210] | Identification of max power load at photovoltaic power generation and power capacity |