A5010845083- Smart Grid Energy Management
- Microgrid Control and Optimization
- Optimal Power Flow Distribution
- Electric Power System Optimization
- Energy Load and Power Forecasting
- Electric Vehicles and Infrastructure
- Integrated Energy Systems Optimization
- Smart Grid Security and Resilience
- Advanced Battery Technologies Research
- Hybrid Renewable Energy Systems
- Power System Reliability and Maintenance
- Solar Radiation and Photovoltaics
- Transportation and Mobility Innovations
- Cloud Computing and Resource Management
- Machine Learning and ELM
- Traffic Prediction and Management Techniques
- Power Systems and Renewable Energy
- Power Quality and Harmonics
- Power System Optimization and Stability
- Face and Expression Recognition
- Fuel Cells and Related Materials
- Energy and Environment Impacts
- Photovoltaic System Optimization Techniques
- Energy Efficiency and Management
- Building Energy and Comfort Optimization
Huazhong University of Science and Technology
2016-2025
Hong Kong University of Science and Technology
2024
University of Hong Kong
2024
Qingdao University of Science and Technology
2024
Ministry of Education of the People's Republic of China
2020-2023
North China Electric Power University
2016-2023
McMaster University
2023
Concordia University
2023
University of Calgary
2023
University of Nottingham
2023
As an important cyber-physical system (CPS), smart grid is highly vulnerable to cyber attacks. Amongst various types of attacks, false data injection attack (FDIA) proves be one the top-priority cyber-related issues and has received increasing attention in recent years. However, so far little been paid privacy preservation detection FDIAs grid. Inspired by federated learning, a FDIA method based on secure deep learning proposed this paper combining Transformer, Paillier cryptosystem. The as...
The utilization of large-scale distributed renewable energy (RE) promotes the development multimicrogrid (MMG), which raises need developing an effective management method to minimize economic costs and keep self sufficiency. multiagent deep reinforcement learning (MADRL) has been widely used for problem because its real-time scheduling ability. However, training requires massive operation data microgrids (MGs), while gathering these from different MGs would threaten their privacy security....
With increasing deployment of distributed energy resources, the market which aims for local generation and load profile redistribution is facing challenge to accommodate various types participants. To realize social welfare maximization with privacy preserving in a dynamic market, this article propose multiagent reinforcement learning (MARL) method quotation decision optimization continuous double auction (CDA)-based peer-to-peer (P2P) market. address nonstationarity violation brought by...
Microgrid (MG) represents one of the major drives adopting Internet Things for smart cities, as it effectively integrates various distributed energy resources. Indeed, MGs can be connected with each other and presented a system multimicrogrid (MMG). This paper proposes optimal operation MMGs by cooperative reserve scheduling model, in which cooperatively utilized among MMGs. In addition, values Shapely are introduced to allocate economic benefits operation. Finally, case study based on is...
This paper presents a model of multi-objective optimal dispatch microgrid (MODMG) under uncertainties via the interval optimization (IO) approach. In this model, multiple objectives are optimized simultaneously to meet economics, power quality, and security requirements (MG) operations. Moreover, in order adequately consider uncertain outputs wind turbines photovoltaic cells an MG, they presented as variables. turn, MODMG is formulated problem IO approach, which then solved by algorithm...
In this paper, the aggregation of electric vehicles (EVs) and fast charging station (FCS) is modeled as a leader-followers game to provide regulation reserves for power systems. The leader FCS operator, who manages local sources sets energy/reserve prices EVs increase its revenue, with consideration uncertain renewable called by independent system operator. On other hand, act followers obtain tradeoff between benefits from energy consumption provision, deciding their reserve strategies....
In this paper, a distributed robust energy management scheme for multiple interconnected microgrids (MGs) is developed. It aims to optimize the total operational cost of MGs through trading with neighboring and main grid in real-time market. Various uncertainties including renewable generation, load consumption, buying/selling prices are handled using an adjustable optimization technique. To keep consistent nature MGs, we propose optimal scheduling algorithm (DAROSA). Within framework, each...
This paper investigates multi-period optimal energy scheduling and trading for multi-microgrids (MMGs) integrated with an urban transportation network (UTN). Specifically, optimization based traffic assignment model is built to characterize the vehicular flows considering rational drivers time-flexible travel demand. Meanwhile, each microgrid (MG) modeled independently schedule its operation by other MGs charging electric vehicles (EVs) fast stations (FCSs). The EV prices could further...
Load forecasting is of crucial importance for operations electric power systems. In recent years, deep learning based methods are emerging load because their strong nonlinear approximation capabilities can provide more precision than conventional statistical methods. However, they usually suffer from some problems, e.g., the gradient vanishment and over-fitting. order to address these an unshared convolution model with densely connected network proposed. this model, backbone convolutional...
This paper develops a secure distributed transactive energy management (S-DTEM) scheme for multiple interconnected microgrids (MGs). Within the scheme, each MG is managed by system (MG-EMS) which only exchanges information of trading quantities and prices with other MGs to preserve information-privacy. When behaves as price taker, its S-DTEM dynamically optimizes selling operating schedule minimize local cost via MGs/main grid. In meantime, this algorithm can cooperatively aggregate MGs....
Integrated energy systems (IES) with cooling, heat, electricity, and natural gas have drawn significant interest recently as we embrace more sustainable a midst climate change. However, the uncertain outputs of distributed generators (DGs) make it challenging for IES planning while maintaining low-cost installation operation under carbon emission constraints. To tackle challenge, this work proposes an optimal model considering both DG output uncertainties punishments. reduce conservatism...
With the increasing penetration of renewable energy (RE), operations distribution network are threatened and some issues may appear, i.e., large voltage deviation, deterioration statistic stability, high power loss, etc. In turn, RE accommodation would be significantly impacted. Therefore, we propose a many-objective reconfiguration (MDNR) model, with consideration curtailment, generation cost. This aims to assess trade-off among these objectives for better networks. As proposed model is...
The electric vehicle (EV) and charging station (EVCS) have been widely deployed with the development of large-scale transportation electrifications. However, since behaviors EVs show large uncertainties, forecasting EVCS power is non-trivial. This paper tackles this issue by proposing a reinforcement learning assisted deep framework for probabilistic to capture its uncertainties. Since data are not standard time-series like electricity load, they first converted format. On basis, one most...
Peer-to-peer energy trading in an active distribution network can contribute to benefit sharing among multiple prosumers and efficient accommodation of distributed renewable energy. Nevertheless, the voltage constraints should be satisfied such that transactions securely implemented physical system. To this end, paper develops a fully decentralized dual-loop peer-to-peer mechanism with regulation capability. In inner-loop process, self-interested iteratively achieve optimal via...
The forecasting of the day-ahead electricity price (DAEP) has become more interest to decision makers in liberalized market, as it can help optimize bidding strategies and maximize profits with gradual market expansion. Deep learning (DL) is a promising method for its strong nonlinear approximation capabilities. However, challenging traditional DL models obtain high precision DAEP, due internal temporal feature-wise variabilities. To address issue, this paper proposes dense skip attention...
With the increasing penetration of renewable energy and flexible loads in smart grids, a more complicated power system with high uncertainty is gradually formed, which brings about great challenges to grid operations. Traditional optimization methods usually require accurate mathematical models parameters cannot deal well growing complexity uncertainty. Fortunately, widespread popularity advanced meters makes it possible for collect massive data, offers opportunities data-driven artificial...
Deep learning has emerged as an effective solution for addressing the challenges of short-term voltage stability assessment (STVSA) in power systems. However, existing deep learning-based STVSA approaches face limitations adapting to topological changes, sample labeling, and handling small datasets. To overcome these challenges, this paper proposes a novel phasor measurement unit (PMU) measurements-based method by using transfer learning. The leverages real-time dynamic information captured...