arXiv subjects

Wanqing Zhao

Publications and source records attributed to Wanqing Zhao.

6 recordsLinked to original sources

arXiv2025

A New Error Temporal Difference Algorithm for Deep Reinforcement Learning in Microgrid Optimization

Predictive control approaches based on deep reinforcement learning (DRL) have gained significant attention in microgrid energy optimization. However, existing research often overlooks the issue of uncertainty stemming from imperfect prediction models, which can lead to suboptimal control strategies. This paper presents a new error temporal difference (ETD) algorithm for DRL to address the uncertainty in predictions,aiming to improve the performance of microgrid operations. First,a microgrid system integrated with renewable energy sources (RES) and energy storage systems (ESS), along with its Markov decision process (MDP), is modelled. Second, a predictive control approach based on a deep Q network (DQN) is presented, in which a weighted average algorithm and a new ETD algorithm are designed to quantify and address the prediction uncertainty, respectively. Finally, simulations on a realworld US dataset suggest that the developed ETD effectively improves the performance of DRL in optimizing microgrid operations.

cs.LG↗

arXiv2025

Trend-Aware Multi-Task Learning for Short-Term Energy Forecasting

Short-term energy forecasting plays an important role in real-time operational decision-making, such as electricity market bidding and power system dispatch, where both numerical accuracy and correct directional signals are essential. However, most existing forecasting approaches formulate the problem purely as a regression task, limiting their ability to explicitly capture stepwise directional movements and trend consistency required for operational decisions. To address this limitation, this paper proposes a trend-aware multi-task forecasting framework that decomposes forecasting outputs into directional movements and deviation magnitudes relative to the latest observation, enabling both accurate numerical prediction and interpretable trend-aware outputs. The framework adopts a task-specific dual-stream architecture and explores key design choices for integrating trend and deviation information, including hard versus probabilistic trend representations, symmetric versus asymmetric deviation modelling, and parallel versus sequential conditioning strategies. To stabilize multi-task learning and reduce manual tuning, an uncertainty-aware task weighting scheme is incorporated to automatically balance directional classification, deviation regression, and final output prediction during training. Experimental results on real-world energy datasets demonstrate that the proposed framework achieves competitive numerical accuracy compared with state-of-the-art algorithms, while consistently improving trend prediction performance with moderate computational cost. This capability is particularly beneficial in short-term energy system management, where consistent directional forecasting can provide more reliable decision support for practical operational scenarios such as market bidding, resource scheduling, and risk-aware energy management.

cs.LG↗

arXiv2025

Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models

Prompt learning facilitates the efficient adaptation of Vision-Language Models (VLMs) to various downstream tasks. However, it faces two significant challenges: (1) inadequate modeling of class embedding distributions for unseen instances, leading to suboptimal generalization on novel classes; (2) prevailing methodologies predominantly confine cross-modal alignment to the final output layer of vision and text encoders, which fundamentally limits their capacity to preserve topological consistency with pre-trained multi-modal embedding spaces. To this end, we introduce MuGCP (Multi-modal Mutual-Guidance Conditional Prompt Learning), a novel paradigm designed for conditional prompt generation. MuGCP leverages Multi-modal Large Language Models (MLLMs) as conditional prompt learners to adaptively generate Semantic Conditional Prompts (SCP) that incorporate rich, fine-grained high-level semantic knowledge for image instances. To ensure effective alignment and interaction across the multi-modal space of Vision-Language Models (VLMs), we introduce the Attention Mutual-Guidance (AMG) module, which facilitates interactions between visual and semantic information. Through mutual guidance, the AMG module generates Visual Conditional Prompts (VCP), enhancing the model's performance in multi-modal tasks. Additionally, we present a Multi-Prompt Fusion (MPF) mechanism that integrates SCP and VCP with contextual prompts, ensuring seamless coordination among the different prompts and enhancing the modeling of class embeddings and instance-specific knowledge. Our MuGCP outperforms existing state-of-the-art methods on 14 different datasets. The code will be made available after publication.

cs.CV↗

arXiv2025

A Self-organizing Interval Type-2 Fuzzy Neural Network for Multi-Step Time Series Prediction

Data uncertainty is inherent in many real-world applications and poses significant challenges for accurate time series predictions. The interval type 2 fuzzy neural network (IT2FNN) has shown exceptional performance in uncertainty modelling for single-step prediction tasks. However, extending it for multi-step ahead predictions introduces further issues in uncertainty handling as well as model interpretability and accuracy. To address these issues, this paper proposes a new selforganizing interval type-2 fuzzy neural network with multiple outputs (SOIT2FNN-MO). Differing from the traditional six-layer IT2FNN, a nine-layer network architecture is developed. First, a new co-antecedent layer and a modified consequent layer are devised to improve the interpretability of the fuzzy model for multi-step time series prediction problems. Second, a new link layer is created to improve the accuracy by building temporal connections between multi-step predictions. Third, a new transformation layer is designed to address the problem of the vanishing rule strength caused by high-dimensional inputs. Furthermore, a two-stage, self-organizing learning mechanism is developed to automatically extract fuzzy rules from data and optimize network parameters. Experimental results on chaotic and microgrid prediction problems demonstrate that SOIT2FNN-MO outperforms state-of-the-art methods, by achieving a better accuracy ranging from 1.6% to 30% depending on the level of noises in data. Additionally, the proposed model is more interpretable, offering deeper insights into the prediction process.

cs.LG↗

arXiv2024

A Holistic Power Optimization Approach for Microgrid Control Based on Deep Reinforcement Learning

The global energy landscape is undergoing a transformation towards decarbonization, sustainability, and cost-efficiency. In this transition, microgrid systems integrated with renewable energy sources (RES) and energy storage systems (ESS) have emerged as a crucial component. However, optimizing the operational control of such an integrated energy system lacks a holistic view of multiple environmental, infrastructural and economic considerations, not to mention the need to factor in the uncertainties from both the supply and demand. This paper presents a holistic datadriven power optimization approach based on deep reinforcement learning (DRL) for microgrid control considering the multiple needs of decarbonization, sustainability and cost-efficiency. First, two data-driven control schemes, namely the prediction-based (PB) and prediction-free (PF) schemes, are devised to formulate the control problem within a Markov decision process (MDP). Second, a multivariate objective (reward) function is designed to account for the market profits, carbon emissions, peak load, and battery degradation of the microgrid system. Third, we develop a Double Dueling Deep Q Network (D3QN) architecture to optimize the power flows for real-time energy management and determine charging/discharging strategies of ESS. Finally, extensive simulations are conducted to demonstrate the effectiveness and superiority of the proposed approach through a comparative analysis. The results and analysis also suggest the respective circumstances for using the two control schemes in practical implementations with uncertainties.

eess.SY↗

arXiv2024

Enhancing Fake News Detection in Social Media via Label Propagation on Cross-modal Tweet Graph

Fake news detection in social media has become increasingly important due to the rapid proliferation of personal media channels and the consequential dissemination of misleading information. Existing methods, which primarily rely on multimodal features and graph-based techniques, have shown promising performance in detecting fake news. However, they still face a limitation, i.e., sparsity in graph connections, which hinders capturing possible interactions among tweets. This challenge has motivated us to explore a novel method that densifies the graph's connectivity to capture denser interaction better. Our method constructs a cross-modal tweet graph using CLIP, which encodes images and text into a unified space, allowing us to extract potential connections based on similarities in text and images. We then design a Feature Contextualization Network with Label Propagation (FCN-LP) to model the interaction among tweets as well as positive or negative correlations between predicted labels of connected tweets. The propagated labels from the graph are weighted and aggregated for the final detection. To enhance the model's generalization ability to unseen events, we introduce a domain generalization loss that ensures consistent features between tweets on seen and unseen events. We use three publicly available fake news datasets, Twitter, PHEME, and Weibo, for evaluation. Our method consistently improves the performance over the state-of-the-art methods on all benchmark datasets and effectively demonstrates its aptitude for generalizing fake news detection in social media.

cs.MM↗