News-reported social, environmental, and grid events can substantially reshape electricity demand, yet quantifying how such events perturb forecasted load trajectories remains largely unaddressed. Existing news-augmented forecasting studies use news as auxiliary features to reduce prediction error but cannot answer counterfactual questions about demand under alternative event conditions. Counterfactual forecasting naturally formulates this problem by comparing the factual trajectory under observed news with counterfactual trajectories under alternative treatments, such as removing events or injecting hypothetical scenarios. However, counterfactual outcomes are inherently unobservable, so the prediction error cannot be directly minimized from data. This challenge is compounded by confounding: news occurrence is entangled with weather, calendar, and historical load conditions that independently affect demand. Guided by a generalization bound for continuous treatments that decomposes the unobservable counterfactual error into weighted factual loss and representation balance, this paper proposes the News-Aware Counterfactual Load Analysis Framework (NACF) to control this error upper bound through observable training objectives. NACF converts unstructured news into structured event streams via an offline large language model, encodes these as continuous semantic treatments with a no-news baseline, and estimates treatment-dependent load trajectories through a varying-coefficient response network with learned sample reweighting and Integral Probability Metric (IPM)-based representation balance regularization. Experiments on an Australian electricity-demand dataset show that NACF remains competitive in factual forecasting while providing evidence of treatment-intensity structure, improved representation balance, and interpretable demand perturbations in synthetic interventions and real event case studies.

Photovoltaic (PV) power forecasting is often developed under an implicit assumption of stationarity, yet the weather–power relationship evolves over time and induces distribution shifts commonly known as concept drift. Existing PV power forecasting models either ignore this issue entirely or address it in a limited and insufficient manner. To better understand this non-stationarity, we distinguish between internal and external drift, which motivate the key components of our design. Therefore, we present ADrift , a drift-aware forecasting framework that integrates patch-based temporal modeling, weather-guided representation learning, and lightweight online adaptation. To model internal drift, the backbone employs prototype-guided weather experts that capture diverse meteorological patterns within each input window. To cope with external drift, a learnable adapter updates its parameters through a temporal gap attention mechanism that enables targeted adjustments to the model. In addition, a proactive update strategy further mitigates supervision delays under rapidly changing conditions. Experiments on three real-world PV datasets show that ADrift consistently improves forecasting accuracy over static and online-learning baselines, demonstrating its potential for practical deployment under evolving weather conditions.

Batteries with silicon-graphite-based anodes, which offer higher energy density and improved charging performance, introduce pronounced voltage hysteresis, making state-of-charge (SoC) estimation particularly challenging. Existing approaches to modeling hysteresis rely on exhaustive high-fidelity tests or focus on conventional graphite-based lithium-ion batteries, without considering uncertainty quantification or computational constraints. This work introduces a data-driven approach for probabilistic hysteresis factor prediction, with a particular emphasis on applications involving silicon-graphite anode-based batteries. A data harmonization framework is proposed to standardize heterogeneous driving cycles across varying operating conditions. Statistical learning and deep learning models are applied to assess performance in predicting the hysteresis factor with uncertainties while considering computational efficiency. Extensive experiments are conducted to evaluate the generalizability of the optimal model configuration in unseen vehicle models through retraining, zero-shot prediction, fine-tuning, and joint training. By addressing key challenges in SoC estimation, this research facilitates the adoption of advanced battery technologies.

This paper presents an efficient approach to battery cycle life prediction through few-shot transfer learning, addressing the challenges of costly and limited battery aging data. Leveraging freely available datasets, a multi-layer perceptron (MLP) model was pretrained on diverse battery aging datasets to adapt to new prediction tasks with minimal training samples through few-shot fine-tuning techniques on the target data. The proposed fine-tuning strategy was validated using a heterogeneous aging dataset of 347 batteries, with cycle lives ranging from 144 to 4,052 cycles, incorporating batteries with lithium iron phosphate (LFP), lithium cobalt oxide (LCO), nickel cobalt aluminum oxide (NCA), and nickel manganese cobalt oxide (NMC) chemistries, which ensures robust validation of our methods. The results show that even with few samples of data from a target task, a comparable generalization performance to training from scratch with 100% data can be achieved, thus demonstrating its effectiveness in utilizing available resources for accurate cycle life prediction.

The battery thermal management of electric vehicles can be improved using neural networks predicting quantile sequences of the battery temperature. This work extends a method for the development of Quantile Convolutional and Quantile Recurrent Neural Networks (namely Q*NN). Fleet data of 225 629 drives are clustered and balanced, simulation data from 971 simulations are augmented before they are combined for training and testing. The Q*NN hyperparameters are optimized using an efficient Bayesian optimization, before the Q*NN models are compared with regression and quantile regression models for four horizons. The analysis of point-forecast and quantile-related metrics shows the superior performance of the novel Q*NN models. The median predictions of the best performing model achieve an average RMSE of 0.66°C and R2 of 0.84. The predicted 0.99 quantile covers 98.87% of the true values in the test data. In conclusion, this work proposes an extended development and comparison of Q*NN models for accurate battery temperature prediction.