Zhenhua Wei

Zhenhua Wei

Auto-generated profile, based on publicly available information

Zhenhua Wei

North China Electric Power University, Beijing, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 June 2015
Verified
Conference Paper
Closed access
WZWei Zhenhua
Wei Zhenhua
LZLiu Zhifeng
Liu Zhifeng
GLGuoliang Li
Guoliang Li
With the popularity of multi-core and many-core platform, multi-core-oriented parallel programming and optimization has become a research hotspot in computer field. However, the vast majority of programmers are still continuing the traditional serial programming habits. Meanwhile, the mainstream algorithms are still in serial. Therefore, how to parallelize the serial programs effectively and write the multi-core programs efficiently is becoming an urgent problem in the field of multi-core programming. In this paper, the optimization of the heap sort algorithm has been achieved adopting the parallel technology based on openMP. Firstly, based on the hypercube model, the heap data to be sorted are divided into n (n is the computer thread amount) blocks called sub-heap which will be sorted respectively. Thus, the scale of the problem is decomposed into 1/n, secondly, the sorted sub-heaps will be merged using merge sort algorithm, finally, the parallel optimized heap sort algorithm is compared to the traditional heap sort algorithm. When the data quantity comes up to ten million bytes, the execution efficiency of the optimized parallel heap sort algorithm of this paper is improved significantly compared with the traditional serial heap sort algorithm on the experimental computer. Furthermore, the efficiency gap between the two algorithms will be intensified prominently with the increasing data quantity.

9 August 2025 in Information Processing & Management
Verified
Journal Article
Closed access
LHLonggang He
Longgang He
ZWZhenhua Wei
Zhenhua Wei

19 August 2024 in IEEE Access
Verified
Journal Article
Open access
CYChang Yang
Chang Yang
LWLisha Wu
Lisha Wu
JXJing Xu
Jing Xu
YRYingjie Ren
Yingjie Ren
BTBo Tian
Bo Tian
ZWZhenhua Wei
Zhenhua Wei
The anomaly detection in data links aims to identify the state of the link during data transmission, which is a critical task for ensuring information transmission security. Most anomaly detection methods focus solely on individual link characteristics, disregarding the inter-link structural information, thus hindering effective generalization to graph-structured data. In this study, we introduce a Graph Learning-based Data Link Anomaly Detection model (GLDAE) that considers both the link features and the communication network structure. Specifically, GLDAE comprises a graph enhancement module, a link feature autoencoder, a structure autoencoder, and a discriminator, enabling simultaneous learning of edge features and the latent representation of the graph structure. Moreover, to enhance the model’s generalization capability, we employ contrastive learning between the original graph and its enhanced version. Additionally, to achieve joint learning of edge features and graph structure, we integrate edge feature embeddings and structure embeddings as inputs to the decoder. Finally, utilizing the well-trained encoder to encode link features and derive a new feature representation, we feed it into an MLP classifier to determine the link’s status. Experimental evaluations were conducted on four authentic datasets (NF-UNSW-NB15, NF-UNSW-NB15-v2, NF-ToN-IoT, NF-ToN-IoT-v2), comparing our model against state-of-the-art baseline models, showcasing the substantial potential of our approach.

26 August 2020 in IEEE Access
Verified
Journal Article
Open access
ZWZhenhua Wei
Zhenhua Wei
YWYuqi Wang
Yuqi Wang
ZLZhihong Li
Zhihong Li
LZLing Zheng
Ling Zheng
The tangentially fired furnace has the advantages of sufficient combustion and low NOx emission, and the smoke black concentration in the furnace reflects the combustion situation of combustion equipment. The flame field and smoke black concentration field in the furnace are complex, so it is meaningful to study the flame field and the smoke black concentration field of the tangential furnace. In this paper, the visual method was used to reconstruct the flame and smoke black concentration fields in the furnace. Due to the low resolution of industrial cameras, the final reconstruction effect is limited. Given this situation, this paper proposes a strengthen edge characteristic super-resolution network (SECSR) algorithm suitable for the tangentially fired furnace flame images. The flame edge processing is added to the depth neural network, which enhances the ability of flame edge feature extraction. It constructs a generative adversarial network which can greatly improve the resolution of furnace flame image, to obtain high-resolution tangential furnace flame image. Secondly, based on the high-quality flame image, this paper proposes an inversion algorithm of the black concentration field of the tangentially fired furnace smoke. The algorithm obtains the high-precision tangentially furnace flame temperature field through an inversion calculation to calculate the soot concentration field. In the future work, we will predict the variation trend of smoke black concentration in the furnace through the results of the inversion calculation model, to understand the combustion situation in the furnace and control the fuel consumption to reduce smoke black emission, which has important guiding significance for protecting the environment and saving resources.

7 November 2026 in Energy Reports
Verified
Journal Article
Open access
XHXin He
Xin He
YQYangang Qu
Yangang Qu
SZSenda Zhang
Senda Zhang
LYLufeng Yuan
Lufeng Yuan
HYHongyu Yue
Hongyu Yue
ZWZhenhua Wei
Zhenhua Wei

19 January 2026 in IEEE Access
Verified
Journal Article
Open access
SGShijie Gao
Shijie Gao
LYLufeng Yuan
Lufeng Yuan
BTBo Tian
Bo Tian
ZWZhenhua Wei
Zhenhua Wei
YLYuxi Liu
Yuxi Liu
Accurate power load forecasting plays a critical role in ensuring the stability and efficiency of modern power systems. However, as the penetration of renewable energy increases and user behaviors become more dynamic, power load data exhibit pronounced non-stationarity and complexity, posing significant challenges to existing forecasting models. To address these issues, this paper proposes a Dynamic Multi-Scale Coordination and Large Language Model Cascade Framework (DMC-LLMF) for power load forecasting. The framework aims to achieve two complementary objectives: 1) dynamically extract and coordinate temporal dependencies across multiple scales and 2) enhance contextual knowledge modeling through the semantic reasoning capability of large language models (LLMs). Specifically, the Dynamic Multi-Scale Decomposition Embedding (DMDE) module adaptively segments load sequences to capture temporal patterns at different scales, while the Triad Interaction Module (TIM) simultaneously models intra-patch, inter-patch, and inter-variable relationships for synergistic local–global dependency learning. Subsequently, a Cross-Modality Alignment (CMA) mechanism fuses semantic prompts generated by a pre-trained LLM with numerical load features, and an Adaptive Mixture-of-Experts Decoder (A-MoE) dynamically weighs multi-scale representations for final forecasting. Extensive experiments on four real-world power load datasets demonstrate that DMC-LLMF outperforms state-of-the-art baselines in both accuracy and robustness, achieving the lowest MSE and MAE across multiple prediction horizons. This framework introduces a novel paradigm for integrating data-driven temporal modeling with knowledge-enhanced semantic reasoning.