Heyang Yu

Dr. Heyang Yu

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2024 in Energies
Verified
Journal Article
Open access
PDF file
WMWan Muchun
Wan Muchun
HYHeyang Yu
Heyang Yu
YHYingning Huo
Yingning Huo
KYKan Yu
Kan Yu
QJQuanyuan Jiang
Quanyuan Jiang
GGGuangchao Geng
Guangchao Geng
Electric vehicles (EVs) play a crucial role in the global transition towards decarbonization and renewable energy resources (RERs). As EVs gain popularity, this has resulted in various challenges for the power grid, such as an intensified peak-to-valley load differential, causing transformer overloading. Vehicle-to-grid (V2G) technology has emerged as a promising solution due to its controllable charging and discharging capabilities. Mature business schemes can incentivize the development of V2G technology. However, the business schemes of V2G technology are still unclear. Therefore, this paper provides a comprehensive review of the business schemes associated with V2G technology, especially focusing on its feasibility and challenges with respect to the electricity market. In this paper, several business schemes with respect to the electricity market are explored by conducting extensive literature reviews, including peak-to-valley arbitrage, the spot market, demand–response (DR), frequency regulation, voltage regulation, spinning reserve, and black start. Next, application scenarios and real-world use cases of the V2G technology’s business schemes are investigated. Furthermore, the challenges faced by the V2G technology’s business schemes are assessed by considering the technical, economical, and social aspects. By identifying these challenges, it is important to highlight the existing shortcomings and areas of interest for V2G technology’s research and development. This review contributes to a deeper understanding of V2G technology and its implications for the energy sector.

27 March 2023 in Applied Energy
Verified
Journal Article
Closed access
HYHeyang Yu
Heyang Yu
JZJingchen Zhang
Jingchen Zhang
JMJunchao Ma
Junchao Ma
CCChangyu Chen
Changyu Chen
GGGuangchao Geng
Guangchao Geng
QJQuanyuan Jiang
Quanyuan Jiang

16 October 2023 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
HYHeyang Yu
Heyang Yu
CXChuanzi Xu
Chuanzi Xu
WWWeifeng Wang
Weifeng Wang
GGGuangchao Geng
Guangchao Geng
QJQuanyuan Jiang
Quanyuan Jiang
The disordered charging of electric vehicles (EVs) in residential areas leads to a rapid increase of the peak load, causing transformer overload, but the charging control of EV group can effectively alleviate this phenomenon. However, existing charging control methods need reliable two-way communication infrastructure, which brings high operation costs and security risks. To offer a backup strategy for charging control of EVs after communication facilities fail, this paper proposes a communication-free charging control scheme to provide a decentralized on-site charging strategy for EV group. First, an uncontrollable EV group baseline estimation considering charging behaviors enabled by Gaussian mixture model (GMM) is proposed to acquire the capacity margin forecasting for controllable EVs. Next, this paper proposes a probabilistic distributed control method to assist users formulate the charging plan autonomously. Here, the charging behavior of EV group is regulated from an optimization with uncertain boundary conditions to a sampling with uncertain feasible regions expressed by a probability distribution. Finally, the scheme is verified via real-world EV charging data from a residential area in Hangzhou, China. The results show that this method can reduce the probability of transformer overload caused by out-of-order EV charging after a communication failure.

12 June 2023 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
HYHeyang Yu
Heyang Yu
CXChongjun Xu
Chongjun Xu
GGGuangchao Geng
Guangchao Geng
QJQuanyuan Jiang
Quanyuan Jiang
The performance of non-intrusive load monitoring (NILM) system is closely related to the uniqueness and comprehensiveness of the load features extracted from the equipment. However, existing feature extraction methods for NILM are difficult to extract interpretable intuitive features representing the uniqueness of load, and lack of comprehensive attention to the features on different time scales. Therefore, this paper proposes a multi-time-scale shapelet based feature extraction framework. First, shapelet, the most unique segment of a sequence, which can distinguish it from other sequences is introduced as a feature and multi-time-scale current shapelets are proposed to extract comprehensive characteristics of electric appliances and offer intuitive interpretability. Meanwhile, a shapelet transform is constructed, so that the essence of shapelet based NILM is transformed from sequence matching to a general classification problem. Next, an ensemble bagging classifier is proposed on multi-time scales to effectively balance the classification errors on each time scale and enhance the performance of NILM system. In addition, this framework can support small sample training to facilitate rapid deployment of NILM applications at the initial practical stage. The results show that this framework can effectively focus on the uniqueness of load on different time scales, provide interpretability for NILM, and achieve good classification effects.

7 December 2021 in IEEE Transactions on Cloud Computing
Verified
Journal Article
Closed access
CCChangyu Chen
Changyu Chen
GGGuangchao Geng
Guangchao Geng
HYHeyang Yu
Heyang Yu
ZLZixuan Liu
Zixuan Liu
QJQuanyuan Jiang
Quanyuan Jiang
Non-intrusive load monitoring (NILM) benefits both end users and utilities by perceiving the operation of individual appliances within a household merely based on analytical results of aggregated electrical data. Driven by diverse demands, a basic and practical NILM solution is on call to enable various downstream applications and strengthen the transfer ability to adapt to different real scenarios. Accordingly, an end-cloud collaborated framework for transferable NILM is proposed in this work. First, an end-to-end model with a multi-scale convolutional architecture is designed for identifying the activation of a specified target appliance using current waveform, which can be independently deployed according to actual needs. Furthermore, a transfer learning framework of NILM is established. Primarily, the model pretrained on the cloud is continuously fine tuned on the terminal side in a pseudo-supervised manner, where the group-weighted cross entropy (GWCE) is defined as the loss function. According to the experimental results based on two public datasets, the proposed model structure possesses prominent generalization ability across different appliances and scenarios, and the transfer learning procedure with GWCE can enhance the identification ability of the pretrained model, which is especially effective for unfamiliar scenarios. Provided with a NILM device eligible for terminal-side intelligence, our work is applicable with great prospects in practice.

31 July 2025 in Energies
Verified
Journal Article
Open access
PDF file
XJXin Jin
Xin Jin
TPTingzhe Pan
Tingzhe Pan
HYHeyang Yu
Heyang Yu
ZWZongyi Wang
Zongyi Wang
WCWangzhang Cao
Wangzhang Cao
In recent years, Transformer-based methods have shown full potential in power load forecasting problems. However, their computational cost is high, while it is difficult to capture the global characteristics of the time series. When the forecasting time length is long, the overall shift of the forecasting trend often occurs. Therefore, this paper proposes a gray relation analysis–frequency-enhanced decomposition transformer (GRA-FEDformer) method for forecasting power loads in power systems. Firstly, considering the impact of different weather factors on power loads, the correlation between various factors and power loads was analyzed using the GRA method to screen out the high-correlation factors as model inputs. Secondly, a frequency decomposition method for long short-time-scale components was utilized. Its combination with the transformer-based model can give the deep learning model an ability to simultaneously capture the fluctuating behavior of the short time scale and the overall trend of changes in the long time scale in power loads. The experimental results show that the proposed method had better forecasting performance than the other methods for a one-year dataset in a region of Morocco. In particular, the advantages of the proposed method were more obvious in the forecasting task with a longer forecasting length.