Accurate prediction of photovoltaic (PV) ramp events is essential for maintaining grid stability and ensuring reliable operation of renewable-rich power systems. However, conventional evaluation metrics often fail to reflect the operational consequences of forecasting errors under asymmetric cost conditions. This study proposes a decision-aware framework for PV ramp event prediction that explicitly links predictive performance to operational decision quality. A rigorous temporal evaluation methodology combining leave-one-month-out validation with an independent fixed test set is adopted to ensure realistic generalization assessment. Three machine learning models, namely LogitBoost, Random Forest, and Support Vector Machines, are evaluated, with LogitBoost achieving the best overall predictive performance (area under the ROC curve (AUC) = 0.9468, F1-score = 0.7140, and Precision-Recall AUC = 0.7185). The results demonstrate a substantial discrepancy between the F1-optimal threshold and the operational cost-optimal threshold, indicating that conventional metric optimization may lead to suboptimal operational decisions. Post-hoc threshold optimization is further compared with cost-sensitive learning approaches under asymmetric penalties assigned to false positives (100 €) and false negatives (500 €). Although the investigated cost-sensitive learning approaches improve recall, they generate more false alarms and do not achieve the lowest operational cost under the considered evaluation setting, whereas the proposed post-hoc framework yields lower operational expenditure. Furthermore, the analysis reveals a strong dependence of decision quality on weather variability. To address this issue, regime-adaptive decision thresholds are calibrated on an internal forward-chaining validation subset of the training data and subsequently applied unchanged to the independent December test set, thereby ensuring a leakage-free evaluation. On the independent test set, the proposed adaptive strategy reduces operational cost by 3.0% (from 50,400 € to 48,900 €) while improving recall from 0.911 to 0.926 with only a marginal reduction in precision. Within the evaluated PV ramp forecasting setting, the proposed decision-level optimization framework achieves lower operational cost than the investigated cost-sensitive learning approaches, while the low-overhead regime-adaptive thresholding strategy provides additional operational improvements without modifying the predictive model.
S. Boumous, Z. Boumous, S. Latreche et al.· Energy Exploration & Exp...· 0 citations
This article presents a comprehensive and critical review of power quality issues (PQIs) arising from the integration of electric vehicles (EVs) into modern power grids, particularly under high penetration scenarios. As EV adoption accelerates globally—driven by decarbonization goals, government policies, and advances in battery and charging technologies—its impact on grid infrastructure has become a significant concern. The study systematically examines the power disturbances introduced by EV charging systems, differentiating between unidirectional grid-to-vehicle and bidirectional vehicle-to-grid (V2G) operations. Key PQIs such as harmonic distortion, voltage sags and swells, reactive power imbalance, frequency deviations and voltage unbalance are investigated for different charging levels (Level 1, Level 2, direct current fast charging), charger topologies and battery states of charge. We pay special attention to the compounding effects of high EV penetration, where stochastic and simultaneous charging behaviors worsen grid instability, transformer overloading, and communication interference. The review discusses conventional mitigation approaches such as passive and active harmonic filters, distribution static compensators, grid-supportive inverter topologies and other emerging solutions including smart charging algorithms, machine-learning-based predictive control, adaptive reactive power compensation and integration of renewable energy sources. The importance of bidirectional charging in providing ancillary services such as frequency control and peak shaving is highlighted, and new PQIs originating from dynamic switching of modes, supraharmonic generation and failures in communications in V2G are identified. A gap analysis identifies the need for dynamic grid models, secure communications protocols (ISO 15118, IEEE 2030.5) and technoeconomic assessment of the grid for large-scale implementation of EVs. The novelty of this review is that it adopts an integrated approach by considering all three aspects to evaluate the issues and opportunities associated with EV integration from a system-wide perspective. The present study offers important insights by exploring trends in current research, identifying gaps, and suggesting possible solutions.
Bhuvanesh Arun Ct, Wesley Jeevadason Aruldoss, T. Yuvaraj et al.· Energy Exploration & Exp...· 0 citations
Accurate short-term wind power prediction plays a critical role in ensuring stable grid operation, effective energy management, and the large-scale integration of renewable energy systems under highly variable wind conditions. Although data-driven and deep learning models have demonstrated promising forecasting capability, many existing approaches suffer from performance degradation during rapid wind fluctuations due to the lack of embedded physical constraints and the high computational complexity associated with recurrent architectures. To address these limitations, this article proposes a Physics-Guided Residual Temporal Convolutional Network (PG-ResTCN) for short-term wind power forecasting. The proposed framework integrates dilated temporal convolutional learning with residual connections to effectively capture multiscale temporal dependencies in wind power time series while avoiding the sequential computation of recurrent neural networks, thereby improving computational efficiency. Furthermore, a physics-based smoothness constraint is incorporated into the training loss function to enforce physically consistent power ramping behavior that reflects the inherent operational dynamics and inertia of wind turbines, reducing unrealistic fluctuations in predicted power outputs. The effectiveness of the proposed model is validated using a large real-world dataset containing approximately 140,161 hourly samples collected from five wind farm locations, including meteorological variables and corresponding turbine power outputs. Comprehensive experiments are conducted by comparing the proposed method with widely used benchmark models, including Support Vector Regression, Random Forest, Extreme Gradient Boosting, and Long Short-Term Memory networks. Results demonstrate that the proposed PG-ResTCN model achieves superior forecasting performance, obtaining a root mean square error of 0.0359, mean absolute error of 0.0296, and R
2
of 0.9759, outperforming all baseline models. The integration of physics-guided constraints with the temporal convolutional architecture significantly enhances prediction accuracy, stability, and generalization capability. In addition, the proposed framework maintains high computational efficiency and robustness, making it suitable for real-time wind energy forecasting applications, intelligent energy management systems, and microgrid power system operations.
S. Marisargunam, T. Mariprasath, Mohit Bajaj et al.· Energy Exploration & Exp...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
