Zhiyuan Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhiyuan Gao has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Xuewei Zhang
Army Engineering University of PLA
4 shared publications - Ronghao Wang
Army Engineering University of PLA
2 shared publications Changsheng Wang
National Defense Mobilization Office Command Information Assurance Center, Zhangjiakou, China
1 shared publication- Deshuai Han
Rocket Force University of Engineering
1 shared publication - Di Xu
Engineering Quality Supervision Centers of Beijing
1 shared publication Jianchun Xing
National Defense Engineering College, Army Engineering University of PLA, Nanjing, China
1 shared publication
Latest Publications
- 3 June 2026
- Published by Springer Nature
- p. 335-345
Research on Dynamic Prediction Model for Building Energy Consumption Based on EWC-SI
- 3 June 2026
- Published by Springer Nature
- p. 335-345
Research on Dynamic Prediction Model for Building Energy Consumption Based on EWC-SI
- Open Access
- 2 April 2026
- Published by Elsevier in SSRN Electronic Journal
Overcoming Catastrophic Forgetting in Building Energy Consumption Forecasting: A Hybrid EWC-SI Continual Learning Approach
Accurate forecasting of building energy consumption is critical for smart energy management and achieving carbon neutrality targets. However, conventional static models have limited adaptability to dynamic environmental shifts, such as meteorological fluctuations, equipment degradation, and evolving occupancy occupancy patterns, leading to long-term performance degradation. To address this, this study proposes a dynamic energy forecasting model based on a hybrid continual learning framework. By integrating Elastic Weight Consolidation (EWC) and Synaptic Intelligence (SI) regularization terms, the model preserves historical knowledge while adapting to new data distributions without storing raw data, effectively mitigating catastrophic forgetting. The model adopts an encoder-decoder architecture with Convolutional Gated Recurrent Units (dubbed EDCG) as its backbone, where ConvGRUs extract complex spatiotemporal features. Meanwhile, the decoder combines a Gated Recurrent Unit (GRU) with an attention mechanism to capture critical temporal dependencies and the nonlinear weather-energy coupling relationship.Furthermore, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to preprocess energy sequences, enhancing robustness against data volatility. Experimental results on datasets from real-world public buildings demonstrate that the proposed method achieves an R² of 0.97 and a MAPE of 3.3%. The framework significantly outperforms traditional EWC, Accumulative Retraining (AR), and static models in accuracy, training efficiency, and stability, validating its utility in non-stationary environments.
- 2 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessOvercoming Catastrophic Forgetting in Building Energy Consumption Forecasting: A Hybrid EWC-SI Continual Learning Approach
Accurate forecasting of building energy consumption is critical for smart energy management and achieving carbon neutrality targets. However, conventional static models have limited adaptability to dynamic environmental shifts, such as meteorological fluctuations, equipment degradation, and evolving occupancy occupancy patterns, leading to long-term performance degradation. To address this, this study proposes a dynamic energy forecasting model based on a hybrid continual learning framework. By integrating Elastic Weight Consolidation (EWC) and Synaptic Intelligence (SI) regularization terms, the model preserves historical knowledge while adapting to new data distributions without storing raw data, effectively mitigating catastrophic forgetting. The model adopts an encoder-decoder architecture with Convolutional Gated Recurrent Units (dubbed EDCG) as its backbone, where ConvGRUs extract complex spatiotemporal features. Meanwhile, the decoder combines a Gated Recurrent Unit (GRU) with an attention mechanism to capture critical temporal dependencies and the nonlinear weather-energy coupling relationship.Furthermore, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to preprocess energy sequences, enhancing robustness against data volatility. Experimental results on datasets from real-world public buildings demonstrate that the proposed method achieves an R² of 0.97 and a MAPE of 3.3%. The framework significantly outperforms traditional EWC, Accumulative Retraining (AR), and static models in accuracy, training efficiency, and stability, validating its utility in non-stationary environments.
- 13 April 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51 (13) , 1-15
Research on Building Energy Consumption Prediction Based on Hybrid GRU Neural Network
- 13 April 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51 (13) , 1-15
Research on Building Energy Consumption Prediction Based on Hybrid GRU Neural Network
- 6 February 2025
- Published by Springer Nature
- p. 149-161
Heterogeneous Event Matching Based on Event Structures
- 6 February 2025
- Published by Springer Nature
- p. 149-161
Heterogeneous Event Matching Based on Event Structures