A5100731338- Energy Load and Power Forecasting
- Solar Radiation and Photovoltaics
- Forecasting Techniques and Applications
- Regional Development and Environment
- Electric Power System Optimization
- Advancements in Battery Materials
- Face and Expression Recognition
- Power Systems and Renewable Energy
- Statistical Methods and Inference
- Evacuation and Crowd Dynamics
- Fire dynamics and safety research
- Wind Energy Research and Development
- Advanced Battery Materials and Technologies
- Statistical and numerical algorithms
- Advanced Measurement and Detection Methods
- Bayesian Methods and Mixture Models
- Advanced Memory and Neural Computing
- Constructed Wetlands for Wastewater Treatment
- Masonry and Concrete Structural Analysis
- Maritime Transport Emissions and Efficiency
- Wind Turbine Control Systems
- Wireless Signal Modulation Classification
- EEG and Brain-Computer Interfaces
- Traffic Prediction and Management Techniques
- Advanced Statistical Methods and Models
University of California, San Diego
2025
Guangdong University of Technology
2022-2024
Wuhan University of Technology
2022-2024
Ji Hua Laboratory
2024
Beijing Institute of Technology
2024
Chengdu University of Technology
2024
Xidian University
2024
Chongqing University
2024
Tsinghua University
2019-2023
Beijing Normal University
2023
The large fluctuations in charging loads of electric vehicles (EVs) make short-term forecasting challenging. In order to improve the load performance EV load, a corresponding model-based multi-channel convolutional neural network and temporal (MCCNN-TCN) are proposed. (MCCNN) can extract fluctuation characteristics at various time scales, while (TCN) build time-series dependence between forecasted load. addition, an additional BP maps selected meteorological date features into...
Li-rich Mn-based oxides (LRMOs) hold great promise as the next generation of lithium-ion battery cathode material due to their low cost and high capacity. Nonetheless, practical application LRMOs is impeded by initial Coulombic efficiency rapid voltage decay. Herein, a V-doped layered-spinel coherent layer was constructed on surface Co-free LRMO through simple NH<sub>4</sub>VO<sub>3</sub> treatment. The with 3D ion channels serves purpose enhancing Li<sup>+</sup> diffusion efficiency,...
The accuracy of doubly fed induction generator (DFIG) models and parameters plays an important role in power system operation. This paper proposes a parameter identification method based on the hybrid genetic algorithm for control DFIG converters. In improved algorithm, generation gap value immune strategy are adopted, “individual identification, elite retention, overall identification” is proposed. operation data information used considers loss rotor current, stator grid-side voltage,...
A bivariate order-replacement policy for a multi-state repairable system with imperfect repair is put forward in this paper, where the decisions on when to order spare part and place replacement are based number of failures. The geometric processes generalized depict characteristics that successive working times shorter while consecutive longer longer. According renewal reward theorem, constrained optimization model formulated, which aim minimize expected long-run cost rate (ELRCR) under...
Lithium-rich layered oxides with superior capacity over 250 mA h g–1 have been regarded as one of the most promising cathode materials to address problem low endurance electric vehicles. Unfortunately, their practical application has blocked for decades by severe voltage decay and fading, which mainly originate from structure evolution spinel-like phase undesirable cathode–electrolyte interfacial reactions. Herein, inhomogeneous distribution LiMO2 Li2MnO3 components on surface...
In view of the characteristics that linear exponential smoothing, secondary cubic smoothing had different fitting degree when predicted spares with consumption discipline, optimized results these three methods through combination prediction model, and solved it by genetic algorithm used obtained minimum error as quota. show model predicts accurately, high utility promotion.
In this paper, a novel Structure-Constrained Low-Rank and Partial Sparse Representation algorithm for image classification is proposed. First, dictionary learning proposed, which imposes both structure low-rank restriction on the coefficient matrix. Second, under assumption that representation of test sample sparse correlated with learned training samples, we concatenate samples to form data matrix find over by recovery technique. Experimental results demonstrate effectiveness proposed algorithm.
This article proposes a distance-based framework incentivized by the paradigm shift towards feature aggregation for high-dimensional data, which does not rely on sparse-feature assumption or permutation-based inference. Focusing outcomes that preserve information without truncating any features, class of semiparametric regression has been developed, encapsulates multiple sources variables using pairwise between-subject attributes. Further, we propose strategy to address interlocking...
For the problem that demand of vari-indenture Recoverable Parts did not submit to Poisson distribution, put forward Negative binomial distribution improve forecasting accuracy. Used fill rate estimate supply degree Parts, restricted total security funds and lowest as constraint conditions, searching for maximization objective function, established model through marginal analysis solve it. The example proves has good prediction effect.
Focusing on combined cooling-heating-power cogeneration dispatching problem for microgrid with windphoto voltaic-gas mixed generation and exchange the grid, this paper firstly presented an optimal energy model. Forecast errors of load, wind power PV are modeled in probabilistic ways, integrated forecast error is then transformed to up/down constraints ramping rates limits controllable micro resources. All into a new objective, proposed model turned bi-objective optimization one. The particle...
Wind power ultra-short-term prediction plays a key role in day scheduling of systems and cross-provincial trading. However, the randomness non-stationary nature wind power, mismatch between training data predicted have become main obstacles for improvement accuracy. This paper proposes algorithm based on variational mode decomposition (VMD) clustering. Firstly, original sequence is transformed into several relatively stationary modes utilizing VMD. Secondly, features can be conveniently...
According to the three conditions that varianceto-mean ratio of spares demand is larger than, equal or less than 1, put forward distributions such as Negative binomial distribution, Poisson distribution and Binomial distribution.For problem two-level materials follows use improve forecast accuracy.In given total security funds constraint conditions, through shortfall minimum instead supply availability maximum simplify objective function, establish inventory decision model, optimized by...