- Advanced Battery Technologies Research
- Electric Vehicles and Infrastructure
- Smart Grid Energy Management
- Smart Grid Security and Resilience
- Power Systems and Renewable Energy
- Energy, Environment, and Transportation Policies
- Energy Harvesting in Wireless Networks
- Energy Load and Power Forecasting
- Wind Energy Research and Development
- Electric and Hybrid Vehicle Technologies
- Economic Development and Digital Transformation
- Fluid Dynamics Simulations and Interactions
- Electrostatic Discharge in Electronics
- Data Stream Mining Techniques
- Rough Sets and Fuzzy Logic
- Embedded Systems and FPGA Design
- Microgrid Control and Optimization
- Robotic Path Planning Algorithms
- Smart Grid and Power Systems
- Power Systems and Technologies
- Error Correcting Code Techniques
- Vehicle emissions and performance
- Innovation Diffusion and Forecasting
- Educational Technology and Assessment
- Power System Optimization and Stability
Shanghai Electric (China)
2018-2024
Nanchang Hangkong University
2022
Shanghai Jiao Tong University
2014
Purdue University West Lafayette
2008
The technology deployed for lithium-ion battery state of charge (SOC) estimation is an important part the design electric vehicle management systems. Accurate SOC can forestall excessive charging and discharging batteries, thereby improving discharge efficiency extending cycle life. In this study, key technologies are summarized. First, research status modeling introduced. Second, main difficulties in model parameter identification batteries discussed. Third, development advantages...
Traditional experimental economics methods often consume enormous resources of qualified human participants, and the inconsistence a participant’s decisions among repeated trials prevents investigation from sensitivity analyses. The problem can be solved if computer agents are capable generating similar behaviors as given participants in experiments. An based analysis method is presented to extract deep information questionnaire data emulate any number participants. Taking customers’...
Performance of disk I/O schedulers is affected by many factors, such as workloads, file systems, and systems. Disk scheduling performance can be improved tuning scheduler parameters, the length read timers. Scheduler mostly done manually. To automate this process, we propose four self-learning schemes: change-sensing Round-Robin, feedback learning, per-request two-layer learning. experiments show that novel learning scheme performs best. It integrates workload-level request-level algorithms....
The interaction between the gird and wind farms has significant impact on power grid, therefore prediction of is great significance. In this paper, a turbine-gird model based long short term memory (LSTM) network under TensorFlow framework presented. First, multivariate time series was screened by principal component analysis (PCA) to reduce data dimensionality. Secondly, LSTM used nonlinear relationship selected sequence turbine interactions actual output farms, it proved that higher...
The operation prediction of wind farms will be accompanied by the need for massive data processing, especially preprocessing farm meteorological or numerical weather (NWP). Because NWP are strongly correlated with operation, proper processing could not only reduce volume but also improve correlations predictions. For this purpose, paper proposes a algorithm based on t-distributed stochastic neighbor embedding (t-SNE). Firstly, collected were normalized to eliminate influence caused different...
In view of the strong volatility and randomness photovoltaic (PV) power generation, energy management mode PV generation station with ESS based on prediction is proposed. Firstly, circuit model, unit storage battery unit, established inthe ESS(ES). Then, to meet requirements smoothing tracking planned output, control scheme system (ESS) designed. Finally, in MATLAB/Simulink, built simulation model. It shown from results that proposed can effectively suppress fluctuation or output. The be...
Predictive Coding (PC) is a theoretical framework in cognitive science suggesting that the human brain processes cognition through spatiotemporal prediction of visual world. Existing studies have developed neural networks based on PC theory, emulating its two core mechanisms: Correcting predictions from residuals and hierarchical learning. However, these models do not show enhancement skills real-world forecasting tasks ignore Precision Weighting mechanism theory. The precision weighting...
At present, China has built a number of DG (distributed power generation) demonstration projects as part intelligent cities, business parks, university campuses and residential areas. The interaction mechanism, among DGs-especially those with energy storage, the users distribution grid need to be clear; i.e. how unify coordination solar systems, small wind generation battery reserve electrical vehicles, so optimize resources allocation, cut peak compensate trough loads; enable future homes...
With the development of science and technology, Industry, transportation other industries used to discharge a large number pollutants into atmosphere, which results in air pollution. When pollution become serious, it will do great harm human health. High-precision Air Quality Index(AQI) prediction is as important weather prediction. People could arrange traveling their life according highly precise results, so better protect own Considering lot complex factors, we choose several potential...
Battery energy and power density are limiting factors in the development of electric vehicle systems, particularly context wide-range charge exchange needed for traction batteries vehicles. A novel battery management system combining technology radio frequency identification, internet things GPS is put forward to guarantee safe operation. The EV's intelligent integrated station proposed this paper not only charges vehicles' batteries, but also functions as an interface between vehicles grid....
The accurate prediction of time series data in the industrial production process can provide important guidance for scheduling and decision-making systems, is also an part predictive control technology. In this paper, a model which introduces graph neural network (GCN) proposed. This mainly consists feature extraction module relational modeling module. module, Att-LSTM proposed to extract information data. novel M-GCN relevance among different nodes. addition, based on model,...
It’s important to make the suitable energy alternatives with comprehensive technical and economic indicators for energy-saving, emissions reduction utilization under condition of optimal technology economy index. A new fuzzy multi-attribute decision making method based on expectation is proposed construct evaluation index system electric in case that weight information completely unknown or only partially available. The quantitative analysis attribute value carried out, each layer determined...
There are many problems in energy enterprises, such as insufficient understanding of internationalization, serious shortage international talents, unthorough investigation the rules standards organization, and inadequate transformation existing achievements into standards, which seriously restrict development standardization. The article relies on research management strategy State Grid Shanghai Electricity Research Institute, proposes a “Five Targets” standardized formulation system,...
To effectively and efficiently manage the information of power industry, especially in State Grid China, data-oriented intelligent operation maintenance have always been a crucial task. Hence, this paper, roadmap on industrial knowledge system is presented for Chinese industry. Firstly, background described, it has pointed out that core problem data explosion lack China. This important not only construction smart grid, but also global energy savings. Secondly, as maintenance, graph can be...
It is widely accepted that wireless communications play an important role in smart grid. However, communication usually lacks sufficient quality, security, and reliability are critically demanded by power Thus, it indispensable to study the applicability of for In this paper, interactions between a network grid characterised from perspective cyber-physical system (CPS). Based on CPS framework, integration networks categorised into two scenarios: loosely-coupled tightly-coupled CPS. The...
When the lightning current enters ground through grounding system, impulse dispersion performance can be observed by phenomenon of soil spark discharge, which is fundamentally determined nearby soil. At present, engineers use an empirical formula to convert discharge coefficient resistance. Therefore, there no available quantitative analysis method evaluate performance. To solve this problem, paper proposes evaluation for efficiency using X-ray images, define VI as parameter, ratio volume...
It is widely accepted that wireless communications play an important role in smart grid. However, communication usually lacks sufficient quality, security, and reliability are critically demanded by power Thus, it indispensable to study the applicability of for In this paper, interactions between a network grid characterised from perspective cyber-physical system (CPS). Based on CPS framework, integration networks categorised into two scenarios: loosely-coupled tightly-coupled CPS. The...