Jishen Peng

Dr. Jishen Peng


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
5 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LLLi Li
Li Li
JPJishen Peng
Jishen Peng
YWYingcai Wan
Yingcai Wan
Low-light image enhancement is crucial for accurately interpreting images captured under low-lighting conditions. Existing low-light enhancement methods based on diffusion models have demonstrated effectiveness; however, they suffer from slow training processes and less structured guidance during optimization. We propose a navel patch-wise-based diffusion model, which introduces the low curvature reverse trajectory to ensure stable parameter optimization and uncertainty guidance in the diffusion training process. Specifically, we randomly select patches of varying sizes from the entire image and apply patch-wise optimization between the generated image and the ground truth to enforce a stable optimization path in the diffusion model. Additionally, within each patch-wise region, an uncertainty network estimates the uncertainty, which is then integrated as a weighting factor in the diffusion process to balance areas of abrupt change in the image. Experimental evaluations on various datasets demonstrate that our method achieves significant improvements, particularly in experiments with real-world images. These results indicate that the proposed patch-wise-based diffusion model enhancements are effective.

8 August 2025 in Symmetry
Verified
Journal Article
Open access
PDF file
HHHaotong Han
Haotong Han
JPJishen Peng
Jishen Peng
JMJun Ma
Jun Ma
HLHao Liu
Hao Liu
SLShanglin Liu
Shanglin Liu
The core structure of modern power systems reflects a fundamental symmetry between electricity supply and demand, and accurate load forecasting is essential for maintaining this dynamic balance. To improve the accuracy of short-term load forecasting in power systems, this paper proposes a novel model that combines a Multi-Strategy Improved Sand Cat Swarm Optimization algorithm (MSCSO) with a Self-Attention Temporal Convolutional Network (SA TCN). The model constructs efficient input features through data denoising, correlation filtering, and dimensionality reduction using UMAP. MSCSO integrates Uniform Tent Chaos Mapping, a sensitivity enhancement mechanism, and Lévy flight to optimize key parameters of the SA TCN, ensuring symmetrical exploration and stable convergence in the solution space. The self-attention mechanism exhibits structural symmetry when processing each position in the input sequence and does not rely on fixed positional order, enabling the model to more effectively capture long-term dependencies and preserve the symmetry of the sequence structure—demonstrating its advantage in symmetry-based modeling. Experimental results on historical load data from Panama show that the proposed model achieves excellent forecasting accuracy (RMSE = 24.7072, MAE = 17.5225, R2 = 0.9830), highlighting its innovation and applicability in symmetrical system environments.

4 September 2026 in Symmetry
Verified
Journal Article
Open access
PDF file
JMJun Ma
Jun Ma
JPJishen Peng
Jishen Peng
HHHaotong Han
Haotong Han
LSLiye Song
Liye Song
HLHao Liu
Hao Liu
High penetrations of wind and photovoltaic generation create simultaneous challenges for battery energy storage system (BESS) planning in distribution networks, including differences in nodal regulation value, power-energy configuration, and day-ahead operation under forecast uncertainty. This study develops a sequential planning-to-operation workflow comprising candidate-bus generation, siting and sizing within the candidate set, and finite-scenario day-ahead scheduling for a fixed configuration. First, nodal net-injection sensitivities, Jacobian-assisted pre-screening, and deterministic topology/support safeguards are used to generate the main candidate set, and alternating-current (AC) finite-difference refinement is performed only for the sensitivity-led fast set; in the IEEE-33 system, this refinement reduces the number of AC power-flow calls from 65 for full-node analysis to 17. Next, Sensitivity-Guided Envelope-Based Nonanticipative Adjustable Recourse Optimal Power Flow (SG-ENAR-OPF) is solved separately for each bus in the main candidate set; the BESS location and power/energy capacities are jointly determined subject to the P-Q LinDistFlow model, BESS duration constraints, a shared affine response, and finite-scenario constraints. The full-node audit serves only as an independent paper-level validation benchmark and is not part of the deployable workflow. After the configuration is fixed, interval forecasts for load, photovoltaic (PV) output, and wind-turbine (WT) output at q05/q50/q95 are used to construct 25 static load-renewable disturbance points and seven temporal stress paths, over which a shared finite-scenario day-ahead policy is optimized. The IEEE-33 MAIN case selects Bus 30, with BESS capacities of approximately 10.66 MW/10.66 MWh. Using scaled public time-series data, the final policy is replayed over 46 consecutive 24 h execution windows, comprising 1104 h actual trajectories; under the 0.002 MW/MWh storage-engineering criterion, all 46/46 windows pass storage engineering validation, and energy continuity is maintained across all 45/45 interday boundaries. Further nonlinear AC post-validation converges at all 1104/1104 operating points, of which 1058/1104 satisfy the complete voltage and branch-capacity constraints. Supplementary results for IEEE-69 show that the workflow can be executed on a second radial test feeder. However, the conclusions are strictly limited to the tested feeders, finite scenarios, scaled public-data settings, and stated engineering tolerances and do not constitute a formal guarantee over a continuous uncertainty domain or of general cross-system applicability.

9 January 2026 in Sensors
Verified
Journal Article
Open access
PDF file
Minglang XuMinglang Xu
Minglang Xu
JPJishen Peng
Jishen Peng
Power-equipment fault detection is challenging in real-world inspections due to subtle defect cues and cluttered backgrounds. This paper proposes an improved YOLOv12-based framework for multi-class power defect detection. We introduce a Prior-Guided Region Attention (PG-RA) module and design a Lightweight Residual Efficient Layer Aggregation Network (LR-RELAN). In addition, we develop a Dual-Spectrum Adaptive Fusion Loss (DSAF Loss) function to jointly improve classification confidence and bounding box regression consistency, enabling more robust learning under complex scenes. To support defect-oriented visual analytics and system interpretability, the framework further constructs Region of Interest (ROI) pseudo point clouds from detection outputs and compares two denoising strategies, Statistical Outlier Removal (SOR) and Radius Outlier Removal (ROR). A Python-based graphical prototype integrates image import, defect detection, ROI pseudo point cloud construction, denoising, 3D visualization, and result archiving into a unified workflow. Experimental results demonstrate that the proposed method improves detection accuracy and robustness while maintaining real-time performance, and the ROI pseudo point cloud module provides an intuitive auxiliary view for defect-structure inspection in practical applications.

17 June 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
JMJun Ma
Jun Ma
JPJishen Peng
Jishen Peng
HHHaotong Han
Haotong Han
LSLiye Song
Liye Song
HLHao Liu
Hao Liu
The transition toward sustainable power systems requires load forecasting methods that can support renewable integration under increasing uncertainty. However, many deep learning models mix historical load, temporal priors, and external drivers in black-box structures, and often assume that true future driver values are available. To address these issues, this study proposes ADDF (Automatic Driver Discovery and Fusion), a semi-explicit self-driven framework for multi-step load interval forecasting. ADDF organizes historical load, calendar priors, and external drivers into three functional branches to distinguish load inertia, temporal regularity, and external forcing. The Driver Branch estimates future driver states under practical information constraints and uses dynamic gating to screen useful driving information. The three branch representations are adaptively integrated through Three-Way Fusion, followed by bounded residual correction to generate multi-step quantile forecasts. Experiments on the Panama electricity load dataset and ETTh1 dataset under one-step and 24-step settings show that ADDF achieves competitive point accuracy and interval prediction performance. Mechanism analyses indicate that the proposed branch-level structure provides clearer interpretability than post-hoc black-box explanations. The framework offers uncertainty-aware forecasting support for sustainable power system operation, including day-ahead scheduling, reserve planning, and energy management.

18 March 2026 in Results in Engineering
Verified
Journal Article
Open access
YLYijiangze Liu
Yijiangze Liu
JPJishen Peng
Jishen Peng
BWBao Wang
Bao Wang
XSXinping Song
Xinping Song