Yulong Che

Dr. Yulong Che


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
1 January 2025 in Energy Engineering
Verified
Journal Article
Open access
PDF file
HSHongsheng Su
Hongsheng Su
WSWenyao Su
Wenyao Su
YCYulong Che
Yulong Che
XMXiping Ma
Xiping Ma
TZTian Zhao
Tian Zhao
LRLimiao Ren
Limiao Ren
Aiming at the issues of insufficient carrying capacity, limited flexibility, and weak source-network-load-storage coordination capability in distribution networks under the background of high-proportion new energy integration. This study proposes a bi-level optimization model for ADN integrating hybrid wind-solar-hydrogen-storage systems. First, an electro-hydrogen coupling system framework is constructed, including models for electrolytic hydrogen production, hydrogen storage, and fuel cells. Meanwhile, typical scenarios of wind-solar joint output are developed using Copula functions to characterize the variability of renewable energy generation. Second, a bi-level optimization model for ADN with electrolytic hydrogen production and storage systems is established: the upper layer employs a multi-objective differential evolution algorithm to solve the optimal siting and sizing problem, aiming to minimize life-cycle costs; the lower layer formulates a coordinated operation optimization model that incorporates contribution degree functions, Voltage Distribution Equilibrium Metric (VDEM), and the renewable energy consumption and absorption rate to ensure real-time synergistic optimization of power flow and voltage stability. Finally, simulations based on the IEEE 33-bus system demonstrate that the proposed method reduces the system’s energy curtailment costs by 34.6% and increases the renewable energy accommodation rate to 99.27%. This study verifies the effectiveness of electrolytic hydrogen production and storage systems as flexible loads in enhancing the hosting capacity of distribution networks, significantly improving grid operational flexibility, and source-network-load-storage coordination. These findings provide a technical pathway for the synergistic planning of high-renewable-penetration power systems, highlighting the critical role of electro-hydrogen coupling in balancing economic efficiency and technical reliability in modern ADN.

17 October 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
HSHongsheng Su
Hongsheng Su
DYDu Yuwei
Du Yuwei
YCYulong Che
Yulong Che
DLDan Li
Dan Li
WSWenyao Su
Wenyao Su
The global pursuit of sustainable development amplifies renewable energy’s strategic importance, positioning wind power as a vital modern grid component. Accurate wind forecasting is essential to counter inherent volatility, enabling robust grid operations, security protocols, and optimization strategies. Such predictive precision directly governs wind energy systems’ stability and sustainability. This research introduces a novel spatio-temporal hybrid model integrating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and graph convolutional networks (GCN) to extract temporal patterns and meteorological dynamics (wind speed, direction, temperature) across 134 wind turbines. Building upon conventional methods, our architecture captures turbine spatio-temporal correlations while assimilating multivariate meteorological characteristics. Addressing data integrity compromises from equipment failures and extreme weather-which undermine data-driven models-we implement Wasserstein GAN (WGAN) for generative missing-value interpolation. Validation across severe data loss scenarios (30–90% missing values) demonstrates the model’s enhanced predictive capacity. Rigorous benchmarking confirms significant accuracy improvements and reduced forecasting errors.

1 August 2025 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
XHXuchun Hou
Xuchun Hou
YQYong Qian
Yong Qian
YCYulong Che
Yulong Che
To address the interference of ambient substation noise on the collected transformer sound signals and enhance the quality and reliability of the signals, this paper proposes a hybrid denoising method that integrates CEEMDAN, SVD, and wavelet thresholding. Firstly, the transformer sound signals are decomposed using CEEMDAN to obtain a series of Intrinsic Mode Functions (IMFs), screening the IMF components based on the differences in kurtosis values between the inherent transformer noise and the ambient noise. Then, Singular Value Decomposition (SVD) is employed to extract the principal components and remove noise from each Intrinsic Mode Function (IMF). Subsequently, wavelet thresholding is used to further denoise the signal. Finally, the denoised signal is reconstructed. This paper uses two evaluation indicators, the signal energy ratio and the noise suppression ratio, to analyze the denoising effect, the results show that the method used in this paper effectively removes noise while preserving the fidelity of the useful signal, this is of great significance for improving the subsequent feature extraction and modal identification based on the denoised signals.

17 September 2025 in Periodica Polytechnica Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
HSHongshen Su
Hongshen Su
TZTian Zhao
Tian Zhao
YCYulong Che
Yulong Che
LGLeijiao Ge
Leijiao Ge
XMXiping Ma
Xiping Ma
YZYangyang Zheng
Yangyang Zheng
The disordered integration of high-penetration distributed photovoltaics (DPVs) into smart distribution networks has caused critical challenges including transformer reverse overloading and degraded power quality. Strategically deploying grid-level energy storage systems (ESSs) presents an effective solution to address these issues while enhancing operational efficiency and power quality. This paper proposes a non-cooperative game theory-driven optimal siting and sizing method for DPVs and ESSs in smart distribution networks. A tri-objective optimization model is formulated to mitigate grid vulnerability, reduce power losses, and minimize life-cycle carbon emissions of PV generation. To resolve conflicting interests among multiple stakeholders (DPV owners, ESS operators, and grid companies), a non-cooperative game framework with equilibrium strategies is established. An improved multi-objective particle swarm optimization (IMOPSO) algorithm is developed to solve the Nash equilibrium point that maximizes benefits for all participants. Case studies on IEEE 33 bus and IEEE-69 bus distribution systems demonstrate that the proposed method achieves: 2.43% reduction in grid vulnerability index, 4.29% decrease in network losses, and 44.44% reduction in PV life-cycle carbon emissions – all while maintaining voltage quality requirements and realizing Pareto-optimal allocation solutions for multi-stakeholder interests.

1 January 2026 in Energy Engineering
Verified
Journal Article
Closed access
PDF file
YCYulong Che
Yulong Che
XJXia Jin
Xia Jin
YDYunchuan Deng
Yunchuan Deng
XWXiaoru Wang
Xiaoru Wang
EHEnjie He
Enjie He
XLXiaoqin Lv
Xiaoqin Lv
As high-speed railway (HSR) networks expand and train density increases, traction substations (TSSs) face short-duration, high-intensity power pulses and concentrated regenerative-braking power, which increase grid-capacity pressure and limit regenerative-braking energy (RBE) utilization. Because lithium-ion batteries (LIBs) are poorly suited to sustained high-frequency, high-rate impacts, this study proposes a weighted multi-criteria capacity-optimization framework for a fully active LIB-supercapacitor (SC) hybrid energy storage system (HESS) based on adaptive frequency-domain decomposition. First, the HESS is integrated into the TSS through the common DC link of a railway power conditioner (RPC). Positive traction power exceeding a prescribed peak-shaving threshold and all negative bus-side regenerative-braking power are extracted to form the HESS regulation sequence. Second, a first-order low-pass filter assigns the low-frequency component to the LIB and the complementary high-frequency component to the SC. Both branches’ rated energy and power and the filter cutoff frequency are jointly optimized. The time-series dispatch enforces rated-power, energy, state-of-charge (SOC), terminal-SOC, and 3C design-screening constraints, together with idle-state filter reset and residual-command reallocation. Finally, a normalized weighted optimization model combining initial capital cost, maximum grid-side demand, and unabsorbed bus-side RBE is formulated and solved using an improved sparrow search algorithm (ISSA). The three objectives are non-exhaustive. Based on one anonymized 7 h aggregate TSS power record sampled every 10 s, the selected terminal-feasible design comprises a 717.460 kWh/0.500 MW LIB, a 62.645 kWh/2.474 MW SC, and a boundary cutoff frequency of 0.000200 Hz. It reduces the grid-side peak power from 13.580 to 10.606 MW, corresponding to a peak-shaving rate of 21.90%, and absorbs 128.000 kWh, or 76.77%, of the bus-side RBE while satisfying terminal-SOC tolerances. Weight, normalization, threshold, terminal-SOC, and battery-stress analyses reveal material trade-offs, indicating that the reported sizing result is specific to the adopted design preferences and measured load record rather than a universal HSR configuration.