Jul 2026· 2026 IEEE Canadian Atlantic Ocean Symposium (CAOS)· pp. 106-110· 0 citations· 11 references
Abstract
Accurate short-term load forecasting is important for running power systems efficiently and managing smart grids. In this study, we present an improved Temporal Convolutional Network (TCN) model and compare eight optimization algorithms: Adam, AdaBelief, RAdam, Ranger, AdamP, NovoGrad, Adan, and SAM. We used hourly electricity load data from Denmark to test each optimizer under the same settings and with three different random seeds to ensure a fair and reliable comparison. All optimizers showed strong predictive accuracy, with root mean square error (RMSE) values between 0.03 and 0.05. Adan and AdamP had the lowest errors and were the most stable. These results show that the choice of optimizer has a big impact on how well TCN models learn and generalize. Our framework offers a solid benchmark for building adaptive and reliable forecasting systems for future smart grids.
It is demonstrated that substation-level, data-driven forecasting can strengthen the signals used to detect grid losses, offering practical implications for grid operators and policymakers.
This research work captures the variation in wind resource variability by implementing advanced machine learning models for short-term power forecasting using SCADA data using a fresh framework to focus on parameters such as aerodynamic behavior, temporal patterns, and overall regime.
Mohammad Y. Mhawiash, B. Khassawneh, Kamal Alieyan et al.· International Journal of Dat...· 0 citations
Comparisons of six methods covering two statistical and four AI algorithms for forecasting electricity demand confirm that data richness particularly hourly granularity is a decisive factor in forecasting accuracy, and that deep learning models require substantial data volumes to outperform statistical baselines.
Kamal M. Othman· Journal of Intelligent Decis...· 0 citations
Short-term power load forecasting plays a crucial role in the operation scheduling, energy management, and security assessment of smart grids, as its accuracy directly affects the economic efficiency and reliability of power systems. However, power load series are characterized by strong nonlinearity, non-stationarity,...
Given the problems of non-stationary power time series, response lag, and amplified prediction errors due to sudden changes in wind direction under transitional meteorological conditions, this study proposes a wind power forecasting model that integrates multiscale time-series features, transition-aware attention mecha...
Y.-J. Li, J. Shen, S. Xu et al.· Advanced Electromagnetics· 0 citations
Experimental results demonstrated that the forecasting–detection pipeline effectively adapts to varying consumption behaviors, yielding improved forecasting accuracy and more reliable AD, particularly over longer forecasting horizons, confirming its suitability for practical smart-grid deployment.
T. Gupta, Richa Bhatia, Richa Sharma· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
