Junhua Zhao
YOU?
Author Swipe
View article: MVLFLM: A parameter-efficient large language model framework for cross-domain multi-voltage load forecasting in smart grids
MVLFLM: A parameter-efficient large language model framework for cross-domain multi-voltage load forecasting in smart grids Open
View article: Toward Reasoning-Centric Time-Series Analysis
Toward Reasoning-Centric Time-Series Analysis Open
Traditional time series analysis has long relied on pattern recognition, trained on static and well-established benchmarks. However, in real-world settings -- where policies shift, human behavior adapts, and unexpected events unfold -- eff…
View article: Deposit and withdraw: Reinforcement learning‐based incentive design for shared energy storage
Deposit and withdraw: Reinforcement learning‐based incentive design for shared energy storage Open
Many residential prosumers exhibit a high price tolerance for household electricity bills and a low response to price incentives. This is because household electricity bills are not inherently high, and the potential for saving electricity…
View article: Intelli-Dispatch-SQL: An LLM-based agent for reliable Text-to-SQL in power dispatching
Intelli-Dispatch-SQL: An LLM-based agent for reliable Text-to-SQL in power dispatching Open
View article: Interfacial thermal conductance at the gas-solid interface: microscopic energy transport mechanisms and the thermal rectification phenomenon
Interfacial thermal conductance at the gas-solid interface: microscopic energy transport mechanisms and the thermal rectification phenomenon Open
View article: Federated Unlearning with Gradient Descent and Conflict Mitigation
Federated Unlearning with Gradient Descent and Conflict Mitigation Open
Federated Learning (FL) has received much attention in recent years. However, although clients are not required to share their data in FL, the global model itself can implicitly remember clients' local data. Therefore, it’s necessary to ef…
View article: A large language model for advanced power dispatch
A large language model for advanced power dispatch Open
View article: Large Language Model-Based Power Dispatch Agent: Framework, Application, and Challenges
Large Language Model-Based Power Dispatch Agent: Framework, Application, and Challenges Open
View article: Power System Operational Reliability Evaluation with Retrieval-Augmented Generation Enhanced Large Language Model
Power System Operational Reliability Evaluation with Retrieval-Augmented Generation Enhanced Large Language Model Open
View article: Tool Wear Condition Diagnosis Using Ensemble Learning with Regularized Fusion of Domain Knowledge and Physical Information for Ti-6al-4v Milling
Tool Wear Condition Diagnosis Using Ensemble Learning with Regularized Fusion of Domain Knowledge and Physical Information for Ti-6al-4v Milling Open
View article: Power System Operation Security Verification with Retrieval-Augmented Generation Enhanced Large Language Model
Power System Operation Security Verification with Retrieval-Augmented Generation Enhanced Large Language Model Open
View article: Multi-Modal Data Information Alignment Based Soh Estimation for Lithium-Ion Batteries Using a Local-Global Parallel Cnn-Transformer Network
Multi-Modal Data Information Alignment Based Soh Estimation for Lithium-Ion Batteries Using a Local-Global Parallel Cnn-Transformer Network Open
View article: Large Language Model-enhanced Home Energy Management with Dynamic User Preference Elicitation and Hierarchical Data-sharing
Large Language Model-enhanced Home Energy Management with Dynamic User Preference Elicitation and Hierarchical Data-sharing Open
View article: An Integrated MFDS and Residual-Enhanced Multi-Task Learning Framework for Early Fault Diagnosis in Chiller Systems
An Integrated MFDS and Residual-Enhanced Multi-Task Learning Framework for Early Fault Diagnosis in Chiller Systems Open
View article: Power System Operation Regulations Verification with Retrieval-Augmented Generation Enhanced Large Language Model
Power System Operation Regulations Verification with Retrieval-Augmented Generation Enhanced Large Language Model Open
View article: Climate Change: What is Computing’s Responsibility? (Dagstuhl Perspectives Workshop 25122)
Climate Change: What is Computing’s Responsibility? (Dagstuhl Perspectives Workshop 25122) Open
This Manifesto was produced from the Perspectives Workshop 25122 entitled "Climate Change: What is Computing’s Responsibility?" held March 16-19, 2025 at Schloss Dagstuhl, Germany. The Workshop provided a forum for world-leading computer s…
View article: Federated Unlearning with Gradient Descent and Conflict Mitigation
Federated Unlearning with Gradient Descent and Conflict Mitigation Open
Federated Learning (FL) has received much attention in recent years. However, although clients are not required to share their data in FL, the global model itself can implicitly remember clients' local data. Therefore, it's necessary to ef…
View article: Coordinated Power Smoothing Control for Wind Storage Integrated System with Physics-informed Deep Reinforcement Learning
Coordinated Power Smoothing Control for Wind Storage Integrated System with Physics-informed Deep Reinforcement Learning Open
The Wind Storage Integrated System with Power Smoothing Control (PSC) has emerged as a promising solution to ensure both efficient and reliable wind energy generation. However, existing PSC strategies overlook the intricate interplay and d…
View article: Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods Open
With extensive pretrained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects, such as multitask learning, sample efficiency, and high-l…
View article: Artificial intelligence‐driven insights: Precision tracking of power plant carbon emissions using satellite data
Artificial intelligence‐driven insights: Precision tracking of power plant carbon emissions using satellite data Open
Human activities have been driving massive greenhouse gas emissions, causing global warming, and triggering increasingly frequent extreme weather events that severely threaten the environment. Power generation is the leading contributor to…
View article: From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection Open
This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptivel…
View article: Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation
Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation Open
Carbon footprint accounting is crucial for quantifying greenhouse gas emissions and achieving carbon neutrality.The dynamic nature of processes, accounting rules, carbon-related policies, and energy supply structures necessitates real-time…
View article: GAIA -- A Large Language Model for Advanced Power Dispatch
GAIA -- A Large Language Model for Advanced Power Dispatch Open
Power dispatch is essential for providing stable, cost-effective, and eco-friendly electricity to society. However, traditional methods falter as power systems grow in scale and complexity, struggling with multitasking, swift problem-solvi…
View article: Carbon market risk estimation using quantum conditional generative adversarial network and amplitude estimation
Carbon market risk estimation using quantum conditional generative adversarial network and amplitude estimation Open
Accurately and efficiently estimating the carbon market risk is paramount for ensuring financial stability, promoting environmental sustainability, and facilitating informed decision‐making. Although classical risk estimation methods are e…
View article: ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models
ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models Open
In response to the urgent demand for grid stability and the complex challenges posed by renewable energy integration and electricity market dynamics, the power sector increasingly seeks innovative technological solutions. In this context, …
View article: Self-Assembly Behavior, Aggregation Structure, and the Charge Carrier Transport Properties of S-Heterocyclic Annulated Perylene Diimide Derivatives
Self-Assembly Behavior, Aggregation Structure, and the Charge Carrier Transport Properties of S-Heterocyclic Annulated Perylene Diimide Derivatives Open
The construction of high-performance n-type semiconductors is crucial for the advancement of organic electronics. As an attractive n-type semiconductor, molecular systems based on perylene diimide derivatives (PDIs) have been extensively i…
View article: Perfednilm: a practical personalized federated learning-based non-intrusive load monitoring
Perfednilm: a practical personalized federated learning-based non-intrusive load monitoring Open
Non-Intrusive Load Monitoring (NILM) is a valuable technique for breaking down overall power consumption into the energy usage of individual appliances. Understanding power usage patterns through NILM plays an important role in reducing en…
View article: A comprehensive modeling framework for coupled electricity and carbon markets
A comprehensive modeling framework for coupled electricity and carbon markets Open
The carbon market plays a critical role in promoting the transition toward renewable energy sources and reducing greenhouse gas emissions in the electricity generation and transmission. Extant research has overlooked the dynamic bilateral …
View article: Framework of Resilient Transmission Network Reconfiguration Considering Cyber-Attacks
Framework of Resilient Transmission Network Reconfiguration Considering Cyber-Attacks Open
Fast and reliable transmission network reconfiguration is critical in improving power grid resilience to cyber-attacks. If the network reconfiguration following cyber-attacks is imperfect, secondary incidents may delay or interrupt post-at…
View article: Coordinated restoration of inverter‐based power sources and synchronous generators for the high renewable penetrated power system considering the dynamic frequency regulation capability
Coordinated restoration of inverter‐based power sources and synchronous generators for the high renewable penetrated power system considering the dynamic frequency regulation capability Open
Extensive inverter‐based power sources (IPS) impose significant challenges on the restoration of high renewable penetrated power systems (HRPPS). To enhance HRPPS resilience, the proper utilization of IPSs must be implemented. Combining fr…