Optimised Deep Learning for Time-Critical Load Forecasting Using LSTM and Modified Particle Swarm Optimisation
| dc.contributor.author | Zulfiqar, M. | |
| dc.contributor.author | Gamage, K. A. A. | |
| dc.contributor.author | Rasheed, M. B. | |
| dc.contributor.author | Gould, C. | |
| dc.date.acceptance | 2024-10-29 | |
| dc.date.accessioned | 2024-11-05T16:26:17Z | |
| dc.date.available | 2024-11-05T16:26:17Z | |
| dc.date.issued | 2024-11-05 | |
| dc.description | open access article | |
| dc.description.abstract | Short-term electric load forecasting is critical for power system planning and operations due to demand fluctuations driven by variable energy resources. While deep learning-based forecasting models have shown strong performance, time-sensitive applications require improvements in both accuracy and convergence speed. To address this, we propose a hybrid model that combines long short-term memory (LSTM) with a modified particle swarm optimisation (mPSO) algorithm. Although LSTM is effective for nonlinear time-series predictions, its computational complexity increases with parameter variations. To overcome this, mPSO is used for parameter tuning, ensuring accurate forecasting while avoiding local optima. Additionally, XGBoost and decision tree filtering algorithms are incorporated to reduce dimensionality and prevent overfitting. Unlike existing models that focus mainly on accuracy, our framework optimises accuracy, stability, and convergence rate simultaneously. The model was tested on real hourly load data from New South Wales and Victoria, significantly outperforming benchmark models such as ENN, LSTM, GA-LSTM, and PSO-LSTM. For NSW, the proposed model reduced MSE by 91.91%, RMSE by 94.89%, and MAPE by 74.29%. In VIC, MSE decreased by 91.33%, RMSE by 95.73%, and MAPE by 72.06%, showcasing superior performance across all metrics. | |
| dc.funder | No external funder | |
| dc.identifier.citation | Zulfiqar, M. Gamage, K.A.A. Rasheed, M.B. Gould, C. (2024) Optimised Deep Learning for Time-Critical Load Forecasting Using LSTM and Modified Particle Swarm Optimisation. Energies, 17 (22) 5524 | |
| dc.identifier.doi | https://doi.org/10.3390/en17225524 | |
| dc.identifier.uri | https://hdl.handle.net/2086/24496 | |
| dc.language.iso | en | |
| dc.peerreviewed | Yes | |
| dc.projectid | N/A | |
| dc.publisher | MDPI | |
| dc.researchinstitute.institute | Institute of Sustainable Futures | |
| dc.rights | Attribution 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | long short-term memory | |
| dc.subject | modified particle swarm optimisation | |
| dc.subject | Adam optimiser | |
| dc.subject | hybrid feature selection | |
| dc.subject | deep learning | |
| dc.title | Optimised Deep Learning for Time-Critical Load Forecasting Using LSTM and Modified Particle Swarm Optimisation | |
| dc.type | Article |