Yanyouyou Liu

Yanyouyou Liu

Auto-generated profile, based on publicly available information

Yanyouyou Liu

Chengyi College, Jimei University,Big Data Analytics Laboratory,Xiamen,China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications

17 April 2026
Verified
Conference Paper
Closed access
HLHongwei Luo
Hongwei Luo
WZWei Zhao
Wei Zhao
CYChujia Yan
Chujia Yan
TXTongle Xie
Tongle Xie
YLYanyouyou Liu
Yanyouyou Liu
Accurate long-term residential load forecasting is critical for modern power grid scheduling and demand response. To address the challenges of non-stationary distribution shifts and the limitations of single-scale pattern capturing, this paper proposes RHFormer, an enhanced long-sequence load forecasting model built upon a deep decomposition framework. The model integrates Reversible Instance Normalization (RevIN) to mitigate the effects of non-stationarity and introduces a hybrid correlation module. By combining global auto-correlation with local multi-scale depthwise separable convolutions (MS-DSC), RHFormer enables collaborative modeling of complex load patterns. Experimental results on a public electricity dataset demonstrate that the proposed model consistently outperforms mainstream baselines across multiple forecasting horizons.

11 November 2025
Verified
Book Chapter
Open access
PDF file
TXTongle Xie
Tongle Xie
SQSuwei Qian
Suwei Qian
KHKeren He
Keren He
HSHanyi Sang
Hanyi Sang
YLYanyouyou Liu
Yanyouyou Liu
WZWei Zhao
Wei Zhao
Disputes involving vulnerable groups in grassroots public governance exhibit diverse characteristics, with the concurrent trends of population mobility and aging further complicating dispute mediation. This study employs the four core elements of social vulnerability theory—exposure, sensitivity, adaptive capacity, and resilience—as an explanatory framework to systematically identify barriers in grassroots mediation processes and propose low-cost recommendations compatible with existing procedures. The research divides the mediation process into four stages: (1) intake and orientation, (2) dispute communication and focus, (3) mediation solution formulation and implementation, and (4) post-settlement follow-up and stabilization. It analyzes the specific manifestations of vulnerability elements across these stages. Results indicate that the four dimensions of vulnerability interact in complex ways throughout the mediation process, creating different types of participation barriers. To address issues related to exposure, sensitivity, adaptive capacity, and resilience, this study proposes targeted strategies, including optimizing information delivery methods, providing structured support tools, and establishing progressive implementation designs. These recommendations help enhance the inclusiveness and accessibility of mediation processes, ensuring that different groups can participate equally and make effective use of mediation mechanisms.