A5039274642- Advanced Multi-Objective Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Traffic Prediction and Management Techniques
- Privacy-Preserving Technologies in Data
- Energy Load and Power Forecasting
- Evolutionary Algorithms and Applications
- Manufacturing Process and Optimization
- Image and Signal Denoising Methods
- Smart Grid Security and Resilience
- Anomaly Detection Techniques and Applications
Wuhan University
2022-2024
This paper introduces the election optimization algorithm (EOA), a meta-heuristic approach for engineering problems. Inspired by democratic electoral system, focusing on presidential election, EOA emulates complete process to optimize solutions. By simulating novel position-tracking strategy that expands scope of effectively solvable problems, surpassing conventional human-based algorithms, specifically, political optimizer. incorporates explicit behaviors observed during elections,...
Residential-level short-term load forecasting (STLF) is significant for power system operation. Data-driven models, especially machine-learning-based are sensitive to the amount of data. However, privacy and security concerns raised by supervision departments users limit data sharing. Meanwhile, limited from newly built houses not sufficient support building a powerful model. Another problem that different in non-identical independent distribution (non-IID), which makes general model fail...
The Aquila Optimizer (AO) algorithm is a meta-heuristic with excellent performance, although it may be insufficient or tend to fall into local optima as the complexity of real-world optimization problems increases. To overcome shortcomings AO, we propose an improved (IAO) which improves original AO via three strategies. First, in order improve process, introduce search control factor (SCF) absolute value decreasing iteration progresses, improving hunting strategies AO. Second, random...
Anomaly detection (AD) in energy consumption for buildings plays a critical role improving efficiency. In distributed systems, federated learning (FL) has gained widespread adoption due to its ability train robust models while preserving privacy. However, most FL algorithms face challenges handling heterogeneous data across different buildings, where distribution gaps exist. Moreover, addressing the heterogeneity necessitates additional efforts model personalization, resulting significant...