arXiv subjects

Dunnan Liu

Publications and source records attributed to Dunnan Liu.

6 recordsLinked to original sources

arXiv2026

PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction

Accurate photovoltaic (PV) power forecasting is essential for reliable grid dispatch and renewable energy integration, yet it remains challenging because PV generation is jointly shaped by weather variability, day-night transitions, regime-dependent dynamics, and strict physical constraints. We propose PARA-PV, a Physics-Aware Retrieval-Augmented framework that embeds physical knowledge throughout the forecasting process. The framework first encodes multivariate PV observations into patch-level representations and, through a physics-aware retrieval-augmented learner, retrieves historical patches and analog trajectories that are consistent with the current window in temporal shape, power level, PV operating state, and intra-day period; this yields a physically grounded base forecast. To supplement local memory with broader temporal knowledge, the base forecast is then calibrated against a frozen Chronos time-series foundation-model prior through a lightweight residual adapter, so that general temporal regularities are adapted to PV-specific dynamics without overriding the physically grounded prediction. Because residual conditional distribution shifts persist when weather and diurnal regimes change, a physics-aware distribution shift correction module subsequently adjusts the preliminary forecast using power, weather, timestamp, and day/night conditions, applying gated mean-shift and scale corrections selectively. Finally, a physics-constrained loss function partitions the samples into peak, ramping, night-time, and regular regimes and adaptively reweights their error contributions, preventing the dominant regular regime from suppressing learning of operationally critical states. Our code is available at https://github.com/weican1103/PARA-PV.

cs.AI↗

arXiv2026

An End-to-end Building Load Forecasting Framework with Patch-based Information Fusion Network and Error-weighted Adaptive Loss

Accurate building load forecasting plays a critical role in facilitating demand response aggregation and optimizing energy management. However, the complex temporal dependencies and high volatility of building loads limit the improvement of prediction accuracy. To this end, we propose a novel end-to-end building load forecasting framework. Specifically, the framework can be divided into two main stages. In the two-stage data preprocessing module enhanced by interpretable feature selection, we utilize the Local Outlier Factor (LOF) algorithm to accurately detect and correct anomalies in the original building load series. Furthermore, we employ SVM-SHAP feature analysis to quantify the impact of environmental variables, filtering out critical feature combinations to mitigate redundancy. In the building load forecasting module, we propose the patch-based information fusion network (PIF-Net). This model applies patching technology to process input series into local blocks, extracting temporal features through a shared Gated Recurrent Unit (GRU) network with residual connections. Subsequently, an information fusion module based on a customized gating mechanism integrates the ensemble hidden states to weight the importance of different temporal patches dynamically. Additionally, the framework is trained using a novel Error-weighted Adaptive Loss (EWAL) function. By combining a rational quadratic function and logarithmic loss to dynamically adjust penalty weights based on real-time prediction error distributions, EWAL significantly enhances the model's robustness under extreme load conditions. Finally, extensive experiments demonstrate the effectiveness and superiority of our proposed framework.

cs.CE↗

arXiv2025

IDS-Net: A novel framework for few-shot photovoltaic power prediction with interpretable dynamic selection and feature information fusion

With the growing demand for renewable energy, countries are accelerating the construction of photovoltaic (PV) power stations. However, accurately forecasting power data for newly constructed PV stations is extremely challenging due to limited data availability. To this end, we propose a novel interpretable dynamic selection network (IDS-Net) based on feature information fusion to achieve accurate few-shot prediction. This transfer learning framework primarily consists of two parts. In the first stage, we pre-train on the large dataset, utilizing Maximum Mean Discrepancy (MMD) to select the source domain dataset most similar to the target domain data distribution. Subsequently, the ReliefF algorithm is utilized for feature selection, reducing the influence of feature redundancy. Then, the Hampel Identifier (HI) is used for training dataset outlier correction. In the IDS-Net model, we first obtain the initial extracted features from a pool of predictive models. Following this, two separate weighting channels are utilized to determine the interpretable weights for each sub-model and the adaptive selection outcomes, respectively. Subsequently, the extracted feature results from each sub-model are multiplied by their corresponding weights and then summed to obtain the weighted extracted features. Then, we perform cross-embedding on the additional features and fuse them with the extracted weighted features. This fused information is then passed through the MLP (Multi-Layer Perceptron) layer to obtain predictions. In the second stage, we design an end-to-end adaptive transfer learning strategy to obtain the final prediction results on the target dataset. We validate the transfer learning process using two PV power datasets from Hebei province, China, to demonstrate the effectiveness and generalization of our framework and transfer learning strategy.

cs.CE↗

arXiv2025

EV-STLLM: Electric vehicle charging forecasting based on spatio-temporal large language models with multi-frequency and multi-scale information fusion

With the proliferation of electric vehicles (EVs), accurate charging demand and station occupancy forecasting are critical for optimizing urban energy and the profit of EVs aggregator. Existing approaches in this field usually struggle to capture the complex spatio-temporal dependencies in EV charging behaviors, and their limited model parameters hinder their ability to learn complex data distribution representations from large datasets. To this end, we propose a novel EV spatio-temporal large language model (EV-STLLM) for accurate prediction. Our proposed framework is divided into two modules. In the data processing module, we utilize variational mode decomposition (VMD) for data denoising, and improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) for data multi-frequency decomposition. Fuzzy information granulation (FIG) for extracting multi-scale information. Additionally, ReliefF is used for feature selection to mitigate redundancy. In the forecasting module, the EV-STLLM is used to directly achieve EV charging and occupancy forecasting. Firstly, we fully capture the intrinsic spatio-temporal characteristics of the data by integrating adjacency matrices derived from the regional stations network and spatio-temporal-frequency embedding information. Then, the partially frozen graph attention (PFGA) module is utilized to maintain the sequential feature modeling capabilities of the pre-trained large model while incorporating EV domain knowledge. Extensive experiments using real-world data from Shenzhen, China, demonstrate that our proposed framework can achieve superior accuracy and robustness compared to the state-of-the-art benchmarks.

cs.CE↗

arXiv2025

Spatiotemporal Prediction of Electric Vehicle Charging Load Based on Large Language Models

The rapid growth of EVs and the subsequent increase in charging demand pose significant challenges for load grid scheduling and the operation of EV charging stations. Effectively harnessing the spatiotemporal correlations among EV charging stations to improve forecasting accuracy is complex. To tackle these challenges, we propose EV-LLM for EV charging loads based on LLMs in this paper. EV-LLM integrates the strengths of Graph Convolutional Networks (GCNs) in spatiotemporal feature extraction with the generalization capabilities of fine-tuned generative LLMs. Also, EV-LLM enables effective data mining and feature extraction across multimodal and multidimensional datasets, incorporating historical charging data, weather information, and relevant textual descriptions to enhance forecasting accuracy for multiple charging stations. We validate the effectiveness of EV-LLM by using charging data from 10 stations in California, demonstrating its superiority over the other traditional deep learning methods and potential to optimize load grid scheduling and support vehicle-to-grid interactions.

eess.SP↗

arXiv2024

Two-Stage Stochastic Optimization for Low-Carbon Dispatch in a Combined Energy System

While wind and solar power contribute to sustainability, their intermittent nature poses challenges when integrated into the grid. To mitigate these issues, renewable energy can be combined with coal fired power and hydropower sources to stabilize the energy system, with battery storage serving as a backup source to smooth the total output. This study develops a low carbon dispatch model for a combined energy system using a two stage stochastic optimization approach. The model incorporates a carbon trading mechanism to regulate emissions and addresses the uncertainty in wind and solar outputs by clustering output curves into typical scenarios to derive a joint distribution. In the initial stage of scheduling, decisions are made regarding the unit commitment for coal fired power plants. The second stage optimizes the expected operation cost of other energy generation sources. The feasibility of the model is demonstrated by comparing the results of stochastic and deterministic scenarios through simulation. Analysis of different carbon prices further explores the impact of the carbon trading mechanism on the system's operation cost.

eess.SY↗