Baohang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Baohang Zhang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Shangce Gao
University of Toyama
11 shared publications - Zhenyu Lei
University of Toyama
6 shared publications - Haotian Li
Faculty of Engineering, University of Toyama, Toyama, Japan
3 shared publications - Lin Yang
School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213032, China
3 shared publications - Zhe Xu
School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213032, China
3 shared publications - Ziqian Wang
Nanjing University of Posts and Telecommunications
3 shared publications
Latest Publications
- Open Access
Cross-Swarm Recombination Particle Swarm Optimizer for Offshore Wind Farm Layout and Cable Routing Optimization
Previous studies have applied particle swarm optimization to coupled offshore wind farm layout and cable design and used geometry-guided genetic search to preserve spatial configurations during crossover. Transferring a successful relocation between layouts requires reassessing its wake and cable effects in the receiving layout. We propose cross-swarm recombination particle swarm optimization (CSRPSO) for offshore layouts with embedded capacity-constrained routing under a levelized cost of energy (LCOE) objective. Two swarms use wake interactions and cable connections to guide turbine relocations. Successful relocations are reconstructed in the other swarm’s personal-best layouts and compared with candidates generated from current layouts using complete LCOE evaluations. Six algorithms were compared across eight wind-farm cases over 30 repetitions per case, using matched seeds and initial populations, populations of 30 and 15,000 complete evaluations including initialization. CSRPSO achieved the lowest mean and median LCOE in every case, reducing mean LCOE by 0.041–0.697% versus adaptive replacement strategy-incorporated genetic learning particle swarm optimization (AGPSO), the closest baseline. At 10,000 evaluations, one-third below budget, its mean LCOE was below AGPSO’s final mean in every case. Mean annual energy production exceeded AGPSO’s in all eight cases, and mean cable expenditure was lower in six.
Open AccessCross-Swarm Recombination Particle Swarm Optimizer for Offshore Wind Farm Layout and Cable Routing Optimization
Previous studies have applied particle swarm optimization to coupled offshore wind farm layout and cable design and used geometry-guided genetic search to preserve spatial configurations during crossover. Transferring a successful relocation between layouts requires reassessing its wake and cable effects in the receiving layout. We propose cross-swarm recombination particle swarm optimization (CSRPSO) for offshore layouts with embedded capacity-constrained routing under a levelized cost of energy (LCOE) objective. Two swarms use wake interactions and cable connections to guide turbine relocations. Successful relocations are reconstructed in the other swarm’s personal-best layouts and compared with candidates generated from current layouts using complete LCOE evaluations. Six algorithms were compared across eight wind-farm cases over 30 repetitions per case, using matched seeds and initial populations, populations of 30 and 15,000 complete evaluations including initialization. CSRPSO achieved the lowest mean and median LCOE in every case, reducing mean LCOE by 0.041–0.697% versus adaptive replacement strategy-incorporated genetic learning particle swarm optimization (AGPSO), the closest baseline. At 10,000 evaluations, one-third below budget, its mean LCOE was below AGPSO’s final mean in every case. Mean annual energy production exceeded AGPSO’s in all eight cases, and mean cable expenditure was lower in six.
- Open Access
- 26 June 2026
- Published by Elsevier in SSRN Electronic Journal
A Parallel Dendritic Neural Learning Model for Photovoltaic Power Forecasting using Variational Mode Decomposition
Accurate photovoltaic (PV) power forecasting is essential for ensuring grid stability and economical power system operation. However, the influence of weather stochasticity has resulted in progressively intricate patterns of PV power generation, presenting significant challenges to existing forecasting methods. This study proposes a parallel dendritic learning framework that integrates graph convolution, long short-term memory, and the dendritic neural model to address the above issue. Firstly, variational mode decomposition is employed to decompose the PV power series, capturing underlying dynamics and detailed time-frequency characteristics. Then, multivariate PV time series are represented as a graph, where feature relationships are modeled as edges, and graph convolution is applied to extract informative representations. Meanwhile, long short-term memory is employed to capture temporal dependencies. Finally, inspired by the nonlinear excitatory behavior of biological neurons, the dendritic neuron model is incorporated, leading to a parallel dendritic learning framework for deep feature integration. Extensive experiments on two public datasets demonstrate that the proposed model consistently outperforms six baseline methods across four evaluation metrics. Ablation studies further indicate that the integration of dendritic learning effectively enhances model performance for accurate PV power forecasting.
- 26 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Parallel Dendritic Neural Learning Model for Photovoltaic Power Forecasting using Variational Mode Decomposition
Accurate photovoltaic (PV) power forecasting is essential for ensuring grid stability and economical power system operation. However, the influence of weather stochasticity has resulted in progressively intricate patterns of PV power generation, presenting significant challenges to existing forecasting methods. This study proposes a parallel dendritic learning framework that integrates graph convolution, long short-term memory, and the dendritic neural model to address the above issue. Firstly, variational mode decomposition is employed to decompose the PV power series, capturing underlying dynamics and detailed time-frequency characteristics. Then, multivariate PV time series are represented as a graph, where feature relationships are modeled as edges, and graph convolution is applied to extract informative representations. Meanwhile, long short-term memory is employed to capture temporal dependencies. Finally, inspired by the nonlinear excitatory behavior of biological neurons, the dendritic neuron model is incorporated, leading to a parallel dendritic learning framework for deep feature integration. Extensive experiments on two public datasets demonstrate that the proposed model consistently outperforms six baseline methods across four evaluation metrics. Ablation studies further indicate that the integration of dendritic learning effectively enhances model performance for accurate PV power forecasting.
- 21 April 2026
- Published by Elsevier in Applied Energy
- Vol. 415
A geometry-guided genetic algorithm for integrated offshore wind farm layout and electrical cable routing optimization
- 21 April 2026
- Published by Elsevier in Applied Energy
- Vol. 415
A geometry-guided genetic algorithm for integrated offshore wind farm layout and electrical cable routing optimization
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 494-498
A Topology-Driven Multi-Objective Evolutionary Algorithm for Offshore Wind Farm Layout Optimization
The design of offshore wind farms requires optimizing turbine layouts and electrical cabling simultaneously to maximize annual energy production (AEP) and minimize costs. This paper proposes a novel topology-driven multi-objective evolutionary algorithm (T-MOEA) for offshore wind farm layout optimization (WFLO). The T-MOEA introduces spatial clustering and network-aware mutation operators that account for aerodynamic wake interactions and cable capacity constraints in one integrated framework. Using a bi-objective formulation (AEP vs. total cable cost), the proposed method efficiently searches for turbine placement and routing configurations that balance energy yield and infrastructure expense. We benchmark T-MOEA on a real offshore wind farm and compare it against five state-of-the-art algorithms. Results show that T-MOEA converges faster and achieves a superior Pareto front, improving the hypervolume (HV) by up to 0.65 and reducing inverted generational distance (IGD) by 50% relative to alternatives. The obtained layouts demonstrate a clear trade-off between higher energy output and lower cabling cost, giving practical insight into offshore design decisions. In conclusion, the topology-driven approach significantly enhances optimization performance for wind farm layout design.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 494-498
A Topology-Driven Multi-Objective Evolutionary Algorithm for Offshore Wind Farm Layout Optimization
The design of offshore wind farms requires optimizing turbine layouts and electrical cabling simultaneously to maximize annual energy production (AEP) and minimize costs. This paper proposes a novel topology-driven multi-objective evolutionary algorithm (T-MOEA) for offshore wind farm layout optimization (WFLO). The T-MOEA introduces spatial clustering and network-aware mutation operators that account for aerodynamic wake interactions and cable capacity constraints in one integrated framework. Using a bi-objective formulation (AEP vs. total cable cost), the proposed method efficiently searches for turbine placement and routing configurations that balance energy yield and infrastructure expense. We benchmark T-MOEA on a real offshore wind farm and compare it against five state-of-the-art algorithms. Results show that T-MOEA converges faster and achieves a superior Pareto front, improving the hypervolume (HV) by up to 0.65 and reducing inverted generational distance (IGD) by 50% relative to alternatives. The obtained layouts demonstrate a clear trade-off between higher energy output and lower cabling cost, giving practical insight into offshore design decisions. In conclusion, the topology-driven approach significantly enhances optimization performance for wind farm layout design.
- Open Access
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 34879-34893
Dendritic Learning Empowered by Diversity-Aware Differential Evolution
The dendritic neuron model (DNM), inspired by the architecture of biological neurons and renowned for its superior nonlinear information processing capability, presents a promising alternative to the classical McCulloch–Pitts neuron model. However, its deployment is often constrained by the limitations of traditional backpropagation (BP), including gradient vanishing, over-reliance on gradient information, and inadequate adaptability in highly nonconvex optimization tasks. To address these issues, we propose a Diversity-Aware Differential Evolution (DADE) algorithm, a novel evolutionary learning framework for DNM training. DADE employs a population diversity–aware adaptive mutation strategy, in which the mutation factor is sampled from a Cauchy distribution, transformed via a nonlinear activation for stability, and dynamically adjusted according to real-time diversity measurements to prevent premature convergence. A refined population grouping mechanism further balances global exploration and local exploitation, while historical parameter updates enhance adaptability throughout the optimization process. Extensive experiments on diverse classification datasets demonstrate that DADE consistently outperforms BP-based training and conventional evolutionary algorithms in terms of accuracy, stability, and generalization.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 34879-34893
Open AccessDendritic Learning Empowered by Diversity-Aware Differential Evolution
The dendritic neuron model (DNM), inspired by the architecture of biological neurons and renowned for its superior nonlinear information processing capability, presents a promising alternative to the classical McCulloch–Pitts neuron model. However, its deployment is often constrained by the limitations of traditional backpropagation (BP), including gradient vanishing, over-reliance on gradient information, and inadequate adaptability in highly nonconvex optimization tasks. To address these issues, we propose a Diversity-Aware Differential Evolution (DADE) algorithm, a novel evolutionary learning framework for DNM training. DADE employs a population diversity–aware adaptive mutation strategy, in which the mutation factor is sampled from a Cauchy distribution, transformed via a nonlinear activation for stability, and dynamically adjusted according to real-time diversity measurements to prevent premature convergence. A refined population grouping mechanism further balances global exploration and local exploitation, while historical parameter updates enhance adaptability throughout the optimization process. Extensive experiments on diverse classification datasets demonstrate that DADE consistently outperforms BP-based training and conventional evolutionary algorithms in terms of accuracy, stability, and generalization.
- Open Access
- 27 November 2025
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
An Improved Artificial Bee Colony Algorithm with Differential Analysis and Deduplication for Feature Selection
- 27 November 2025
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Open AccessAn Improved Artificial Bee Colony Algorithm with Differential Analysis and Deduplication for Feature Selection
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 667-672
Revolutionizing Wind Energy: A Compact Evolutionary Algorithm for Layout Optimization
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 667-672
Open AccessRevolutionizing Wind Energy: A Compact Evolutionary Algorithm for Layout Optimization
- 27 February 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (4) , 1-34
An enhanced LSHADE with generalized Pareto distribution selection for escaping local optima
- 27 February 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (4) , 1-34
An enhanced LSHADE with generalized Pareto distribution selection for escaping local optima