PMID- 35746227
OWN - NLM
STAT- MEDLINE
DCOM- 20220627
LR  - 20220716
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 22
IP  - 12
DP  - 2022 Jun 12
TI  - Hyperparameter Optimization of Bayesian Neural Network Using Bayesian 
      Optimization and Intelligent Feature Engineering for Load Forecasting.
LID - 10.3390/s22124446 [doi]
LID - 4446
AB  - This paper proposes a new hybrid framework for short-term load forecasting (STLF) 
      by combining the Feature Engineering (FE) and Bayesian Optimization (BO) 
      algorithms with a Bayesian Neural Network (BNN). The FE module comprises feature 
      selection and extraction phases. Firstly, by merging the Random Forest (RaF) and 
      Relief-F (ReF) algorithms, we developed a hybrid feature selector based on grey 
      correlation analysis (GCA) to eliminate feature redundancy. Secondly, a radial 
      basis Kernel function and principal component analysis (KPCA) are integrated into 
      the feature-extraction module for dimensional reduction. Thirdly, the Bayesian 
      Optimization (BO) algorithm is used to fine-tune the control parameters of a BNN 
      and provides more accurate results by avoiding the optimal local trapping. The 
      proposed FE-BNN-BO framework works in such a way to ensure stability, 
      convergence, and accuracy. The proposed FE-BNN-BO model is tested on the hourly 
      load data obtained from the PJM, USA, electricity market. In addition, the 
      simulation results are also compared with other benchmark models such as 
      Bi-Level, long short-term memory (LSTM), an accurate and fast convergence-based 
      ANN (ANN-AFC), and a mutual-information-based ANN (ANN-MI). The results show that 
      the proposed model has significantly improved the accuracy with a fast 
      convergence rate and reduced the mean absolute percent error (MAPE).
FAU - Zulfiqar, M
AU  - Zulfiqar M
AD  - Department of Telecommunication Systems, Bahauddin Zakariya University, Multan 
      60000, Pakistan.
FAU - Gamage, Kelum A A
AU  - Gamage KAA
AUID- ORCID: 0000-0002-4832-3373
AD  - James Watt School of Engineering, James Watt South Building, University of 
      Glasgow, Glasgow G12 8QQ, UK.
FAU - Kamran, M
AU  - Kamran M
AD  - Department of Electrical Engineering, University of Engineering and Technology, 
      Lahore 54000, Pakistan.
FAU - Rasheed, M B
AU  - Rasheed MB
AD  - Escuela Politecnica Superior, Universidad de Alcala, ISG, 28805 Alcala de 
      Henares, Spain.
LA  - eng
GR  - 00/University of Glasfow/
GR  - 754382/Horizon 2020/
PT  - Journal Article
DEP - 20220612
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - *Algorithms
MH  - Bayes Theorem
MH  - Forecasting
MH  - *Neural Networks, Computer
MH  - Principal Component Analysis
PMC - PMC9231108
OTO - NOTNLM
OT  - Bayesian Neural Networks
OT  - Bayesian Optimization
OT  - Hamilton dynamic
OT  - convergence rate
OT  - electric load forecasting
COIS- The authors declare no conflict of interest.
EDAT- 2022/06/25 06:00
MHDA- 2022/06/28 06:00
PMCR- 2022/06/12
CRDT- 2022/06/24 01:40
PHST- 2022/05/05 00:00 [received]
PHST- 2022/06/02 00:00 [revised]
PHST- 2022/06/09 00:00 [accepted]
PHST- 2022/06/24 01:40 [entrez]
PHST- 2022/06/25 06:00 [pubmed]
PHST- 2022/06/28 06:00 [medline]
PHST- 2022/06/12 00:00 [pmc-release]
AID - s22124446 [pii]
AID - sensors-22-04446 [pii]
AID - 10.3390/s22124446 [doi]
PST - epublish
SO  - Sensors (Basel). 2022 Jun 12;22(12):4446. doi: 10.3390/s22124446.