A5029839382- Energy Load and Power Forecasting
- Machine Learning and ELM
- Grey System Theory Applications
- Railway Engineering and Dynamics
- Image and Signal Denoising Methods
- Building Energy and Comfort Optimization
- Acoustic Wave Phenomena Research
- Smart Grid Energy Management
- Vehicle Noise and Vibration Control
- IoT-based Smart Home Systems
- Noise Effects and Management
- Advanced Battery Technologies Research
- Machine Fault Diagnosis Techniques
- Wastewater Treatment and Nitrogen Removal
- Water Quality Monitoring and Analysis
- Wind Energy Research and Development
- Power Systems and Renewable Energy
- Aerodynamics and Fluid Dynamics Research
- Speech and Audio Processing
- Water Quality Monitoring Technologies
- Industrial Automation and Control Systems
- Aerospace Engineering and Energy Systems
- Solar Radiation and Photovoltaics
- Wind and Air Flow Studies
- Smart Grid Security and Resilience
Anhui University of Science and Technology
2021-2024
Qingdao Center of Resource Chemistry and New Materials
2021
Industrial customers consume a large part of the total electricity demand. In operation industrial energy systems, accurate prediction electric loads is prerequisite to help users adjust their load dispatch and improve efficiency. Therefore, this paper proposes day-ahead forecasting model employing change rate features combining firefly algorithm optimize extreme learning machine adaptive boosting (LCR-AdaBoost-FA-ELM). The mainly influenced by power users' production schedules, making its...
Short-term electric load forecasting plays a significant role in the safe and stable operation of power system market transactions. In recent years, with development new energy sources, more sources have been integrated into grid. This has posed serious challenge to short-term forecasting. Focusing on series non-linear time-varying characteristics, an approach using “decomposition ensemble” framework is proposed this paper. The method verified hourly data from Oslo surrounding areas Norway....
Commercial load is an essential demand-side resource. Monitoring commercial loads helps not only customers understand their energy usage to improve efficiency but also electric utilities develop management strategies ensure stable operation of the power system. However, existing non-intrusive methods cannot monitor multiple simultaneously and do consider high correlation severe imbalance among loads. Therefore, this paper proposes a deep learning-based monitoring method solve these problems....
Abstract Passengers' demands for riding comfort have been getting higher and as the high-speed railway develops. Scientific methods to analyze interior noise of train are needed operational transfer path analysis (OTPA) method provides a theoretical basis guidance control overcomes shortcomings traditional method, which has high test efficiency can be carried out during working state targeted machine. The OTPA model is established from aspects "path reference point-target point" "sound...
Abstract Commercial buildings are consuming an increasing amount of energy, and accurate load demand forecasting is critical for the reliable operation power systems efficient use resources. Therefore, in this paper, a short‐term commercial model based on tunicate swarm algorithm (TSA) combined with extreme learning machine (ELM) under peak‐valley features proposed as research case shopping mall Romania. This paper's overall structure divided into two steps. In first step, 24‐h day six...
Accurately identifying industrial loads helps to accelerate the construction of new power systems and is crucial today’s smart grid development. Therefore, this paper proposes an load classification method based on two-stage feature selection combined with improved marine predator algorithm (IMPA)-optimized kernel extreme learning machine (KELM). First, time- frequency-domain features electrical equipment (active reactive power) are extracted from data after cleaning, initial pool...
Short-term load forecasting is an important part of forecasting, which great significance to the optimal power flow and supply guarantee system. In this paper, we proposed series reconstruction method combined improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) sample entropy (SE). The decomposed by ICEEMDAN reconstructed into a trend component, periodic random component comparing original series. Extreme learning machine optimized salp swarm algorithm...
A prerequisite for refined load management, crucial intelligent energy is the precise classification of electric loads. However, high dimensionality samples and poor identification accuracy industrial scenarios make it difficult to be used in actual production. As such, this research presents a selection approach equilibrium optimizer-based joint time-frequency entropy feature method loads address these issues. The first introduces value features based on extracting domain then uses an...