9 November 2021 in IEEE Transactions on Power Systems
Regarding the continuing increase of anthropogenic carbon emissions in the power system with growing energy consumption, researchers have focused on managing the demand side to achieve low-carbon transition. However, such a low-carbon transition cannot be achieved effectively without the proper incentive scheme. Moreover, it is desired to improve the computation quality of carbon tracing tools and extend their applications by state-of-art techniques. To fulfil these existing research gaps, this paper proposes a low-carbon optimal scheduling model with demand response (DR) based carbon intensity control. It aims to reduce the dependence of customers on energy sources with high carbon intensities while decreasing reasonable energy consumption. Likewise, a data-driven approach conducted with the Bayesian interfere regression is proposed to carry out the carbon emission flow (CEF) model to cope with the drawbacks of the conventional emission calculation. Moreover, the storage emission and relevant dynamic impacts to the system are fully considered. The proposed data-driven approach is tested on a series of IEEE systems with different sizes, its high accuracy and efficiency are proved by the simulation results. Further, simulation results indicate that the proposed scheduling model can effectively achieve carbon emission mitigation.
5 June 2024 in Applied Energy
18 August 2021 in IEEE Transactions on Industrial Informatics
The increasing penetration of distributed energy resources and a large volume of unprecedented data from smart metering infrastructure can help consumers transit to an active role in the smart grid. In this article, we propose a human-machine reinforcement learning (RL) framework in the smart grid context to formulate an energy management strategy for electric vehicles and thermostatically controlled loads aggregators. The proposed model-free method accelerates the decision-making speed by substituting the conventional optimization process, and it is more capable of coping with the diverse system environment via online learning. The human intervention is coordinated with machine learning to: 1) prevent the huge loss during the learning process; 2) realize emergency control; and 3) find preferable control policy. The performance of the proposed human-machine RL framework is verified in case studies. It can be concluded that our proposed method performs better than the conventional deep Q-learning and deep deterministic policy gradient in terms of convergence capability and preferable result exploration. Besides, the proposed method can better deal with emergent events, such as a sudden drop of photovoltaic (PV) output. Compared with the conventional model-based method, there are slight deviations between our method and the optimal solution, but the decision-making time is significantly reduced.
6 July 2022 in IEEE Transactions on Transportation Electrification
To address the increasing concern on environmental issues, electric vehicles (EVs) have been attracting more attention. On the one hand, the high penetration level of EVs will bring potential risks to the electricity grids. On the other hand, EVs can enhance the flexibility of the grids via vehicle-to-grid (V2G) technology. With the advancement of digitalization and communication technologies, the concept of vehicle-to-vehicle (V2V) has emerged, which can provide an alternative charging way for EVs to relieve the charging overload problem in the power systems. In this article, we present a data-driven matching protocol for V2V energy management. First, deep reinforcement learning (DRL) is utilized to learn the long-term reward of the matching action based on the formulated Markov decision process (MDP) at an offline stage. To protect the private information of the EV owners, a federated learning framework is proposed where the cooperation between different EV aggregators can be realized without sharing sensitive information. At the online matching stage, a matching optimization model is established and is converted into a bipartite graph problem to enhance the computation efficiency. The proposed methodology is verified in case studies. Simulation results show that the proposed methodology can help EV owners save costs and increase revenues while hedging the trading risks. Besides, the local energy self-sufficiency is increased, indicating that less burden is brought to the electricity network.
4 November 2024 in IEEE Transactions on Consumer Electronics
In the current smart grid, managing high-energy consumption loads, particularly electric vehicles (EVs), become increasingly complex. This paper introduces a framework that employs non-intrusive load monitoring (NILM) techniques for enhanced energy management in smart grids. Our approach encompasses a broader range of common flexible loads and energy related to EV charging. The NILM technology enables the detailed analysis of individual appliance consumption patterns from aggregated smart meter data, addressing privacy concerns and technical limitations. In detail, we propose a new NILM algorithm, Serial Multi-task Transformer with Attention (SMTA), to address the problem of long-term household load disaggregation. SMTA uses a Serial-Correlation mechanism with period-based dependencies and cyclical information aggregation for effective period time series analysis and utilizes the Task-Specific Attention strategy to find the power influence between appliances. Afterwards, based on the NILM results, we develop an energy management model aiming to optimize the net operation cost in the smart grid, after all active customers participation in ancillary service programs. The proposed framework has been verified on a modified IEEE 57-bus radial distribution system based on real-world household data. The results show that the SMTA algorithm significantly improves load disaggregation accuracy. Furthermore, the proposed framework in comparison to basic energy management. reduces the net operation costs by up to 26.9%, highlighting the substantial economic benefits of integrating NILM into smart grid operations.