Jiacheng Liu

Mr. Jiacheng Liu


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
6 September 2024 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
JLJiacheng Liu
Jiacheng Liu
Jun LiuJun Liu
Jun Liu
RYRudai Yan
Rudai Yan
TDTao Ding
Tao Ding
The machine learning-based transient stability assessment (TSA) has shown satisfactory accuracy while been limited by the lack of interpretability. This letter thereby presents a novel deep learning paradigm that naturally embeds the Lyapunov stability theory of dynamic systems, in which approximating Lyapunov functions (LFs) is transformed into traditional regression or classification tasks. The Lyapunov stability theory is firstly extended and then integrated into a specific neural network structure, which consists of a flexible LF approximator and its corresponding gradient adjoint network. It is originally revealed that transient stability binary classification by deep Lyapunov learning (DLL) is equivalent to constructing a semi-analytical LF in the state space. Case studies validate the effectiveness of the proposed DLL scheme.

14 November 2025 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
JLJiacheng Liu
Jiacheng Liu
Jun LiuJun Liu
Jun Liu
TDTao Ding
Tao Ding
Chao RenChao Ren
Chao Ren
RYRudai Yan
Rudai Yan
Machine learning (ML)-based transient stability assessment (TSA) provides extraordinary accuracy performance while limited by potential misjudgment risks. To address this issue, this letter originally develops a generic scene-dependent credibility evaluation (SCE) framework. The variance upper bound of ML model prediction error is inferred using an improved localized generalization error estimation (ILGEE) method, and the probability density of system stability is furtherly described as a Gaussian distribution incorporating Neumann boundary condition. Then the scene-dependent credibility index (SCI) is ultimately derived and defined as the information entropy implying the uncertainty of TSA results. Case studies verify the validity of the SCE framework and demonstrate the promising 100% accurate TSA performance with critical proposed SCI as 0.93.

22 December 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
JLJiacheng Liu
Jiacheng Liu
Jun LiuJun Liu
Jun Liu
XLXiaoming Liu
Xiaoming Liu
XLXinglei Liu
Xinglei Liu
YZYu Zhao
Yu Zhao
Transient stability assessment (TSA) is of great significance for the security of power systems. The widely studied postfault TSA based on machine learning methods relies on real-time transient response captured by phasor measurement units (PMUs), which faces difficulties when directly applied to large-scale power systems with a tremendous number of signals as inputs. In this article, we propose a complete scheme for recognizing the most discriminative PMU signals for TSA. First, the original PMU measurement trajectories are projected into uniformly distributed low-dimensional space while maintaining the inherent local structure. Then, a probabilistic dueling clustering method enhanced by a corrected Calinski-Harabaz index is proposed. It is able to divide the projected signals into discrete segments, and then the mutual information between signals and transient stability can be computed as the correlation indicator. Afterward, a signal recognition method based on Eigen decomposition of Laplacian matrix in the information domain is proposed to select the most discriminative signals, which aims to search for the global optimum of maximized relevance and minimized redundancy, and a parallel framework is adopted to improve the recognition efficiency. Key steps of the whole signal recognition scheme are strictly demonstrated in a theoretical way, and case studies on an actual power system provided by China Electric Power Research Institute also verify the effectiveness of the selected signals.

30 July 2024 in IEEE Transactions on Sustainable Energy
Verified
Journal Article
Closed access
XLXiaoming Liu
Xiaoming Liu
Jun LiuJun Liu
Jun Liu
YZYu Zhao
Yu Zhao
YNYongxin Nie
Yongxin Nie
JLJiacheng Liu
Jiacheng Liu
Tao DingTao Ding
Tao Ding
Accurate wind power prediction (WPP) is crucial to the secure and stable operation of large-scale power systems, and data-driven WPP methods have recently been widely studied and applied. However, existing data-driven methods cannot be applied to new wind farms due to the lack of operational data. This paper presents a novel Bayesian deep learning-based adaptive wind farm power prediction (BDL-AWFPP) method, which is the first time to utilize the computational fluid dynamics (CFD) simulation results as the prior of BDL-based method, thus avoiding the problem that data-driven approaches cannot be applied to newly constructed wind farms. Firstly, a CFD-based wind farm numerical simulation database and a wind turbine power curve database are established to construct a multi-source heterogeneous prior dataset. Then, the BDL-AWFPP model is proposed to utilize the multi-source heterogeneous prior dataset, which can be updated adaptively with newly acquired operational data and saved periodically throughout the life cycle. And an auxiliary aging assessment method for wind turbines is also developed according to the periodically-saved models. Finally, a stochastic variational inference (SVI)-based parameter updating algorithm is derived for the proposed BDL-AWFPP model. Case studies on an actual wind farm validate the effectiveness of the proposed method.

10 April 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
XLXiaoming Liu
Xiaoming Liu
Jun LiuJun Liu
Jun Liu
JLJiacheng Liu
Jiacheng Liu
YZYu Zhao
Yu Zhao
ZYZhuwei Yang
Zhuwei Yang
Tao DingTao Ding
Tao Ding
Since wind resources increase with altitude, many wind turbines are installed in high-altitude areas, where blade icing may occur frequently in cold weather. Ice accretion on wind turbines can lead to severe aerodynamic performance degradation or even shutdown. Furthermore, considering the spatiotemporal uncertainty of wind resources, wind power prediction (WPP) in cold weather will be extremely complex. However, existing methods mostly focus on icing-related shutdown detection of wind turbines and pay little attention to the associated WPP during cold weather. To address this problem, a novel Bayesian deep learning-based WPP (BDL-WPP) model is proposed. First, hybrid features related to WPP are extracted based on the actual operational characteristics of wind turbines, and the whole process of blade icing and de-icing is considered for the first time. Then, a BDL-WPP model is proposed based on the extracted features. In order to process the time series information within the BDL framework, a variational Bayesian gated recurrent unit is developed to implement the proposed BDL-WPP model. Finally, a posterior inference algorithm is derived for the BDL-WPP model based on stochastic variational inference. The proposed method is tested on a real-world provincial grid, and the results show that its mean absolute error is consistently below 0.025 under both normal and icing conditions, verifying its effectiveness.

24 February 2025 in Energies
Verified
Journal Article
Open access
PDF file
GWGuangYao Wang
GuangYao Wang
Jun LiuJun Liu
Jun Liu
JLJiacheng Liu
Jiacheng Liu
YLYuting Li
Yuting Li
TMTianxiao Mo
Tianxiao Mo
JSJu Sheng
Ju Sheng
When a line-commutated converter–high-voltage direct current (LCC-HVDC) transmission system with large-scale integration of renewable energy encounters HVDC-blocking events, the sending-end power system is prone to transient overvoltage (TOV) risks. Renewable energy units that are connected via power electronic devices are susceptible to large-scale cascading disconnections due to electrical endurance and insulation limitations when subjected to an excessively high TOV, which poses a serious threat to the safe and stable operation of the system. Therefore, the prediction of TOV at renewable energy stations (RES) under DC blocking (DCB) scenarios is crucial for developing strategies for the high-voltage ride-through of renewable energy sources and ensuring system stability. In this paper, an approximate analytical expression for the TOV at RES under DCB fault conditions is firstly derived, based on a simplified equivalent circuit of the sending-end system that includes multiple DC transmission lines and RES, which can take into consideration the multiple renewable station short-circuit ratio (MRSCR). Building on this, a knowledge-embedded enhanced deep neural network (KEDNN) approach is proposed for predicting the RES’s TOV for complex power systems. By incorporating theoretical calculation values of the TOV into the input features, the task of the deep neural network (DNN) shifts from mining relationships within large datasets to revealing the correlation patterns between theoretical calculations and real values, thereby improving the robustness of the prediction model in cases of insufficient training data and irrational feature construction. Finally, the proposed method is tested on a real-world regional power system in China, and the results validate the effectiveness of the proposed method. The approximate analytical expression for the TOV at RES and the KEDNN-based TOV prediction method proposed in this paper can provide valuable references for scholars and engineers working in the field of power system operation and control, particularly in the areas of overvoltage theoretical calculation and mitigation.