Data-Driven Power Flow Linearization: A Regression Approach

Liu, Yuxiao; Zhang, Ning; Wang, Yi; Yang, Jingwei; Chen, Kang

doi:10.1109/tsg.2018.2805169

Cited by 153 publications

(69 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6(c) shows the convergence of residuals in Eq. (15). The residual decreases rapidly at the beginning until it converges to the predetermined accuracy ε, and then decreases at a slower rate within 10 iterations.…”

Section: B Data-driven Adaptive Operation Of Sop 1) Mfac-based Operation Control Of Sopmentioning

confidence: 96%

See 1 more Smart Citation

Data-Driven Adaptive Operation of Soft Open Points in Active Distribution Networks

Huo

et al. 2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

The integration of soft open point (SOP) effectively improves the flexibility of active distribution networks (ADNs).However, in practical operation, accurate network parameters are difficult to obtain and the operation state changes rapidly with distributed generators (DGs). With the development of information technologies, massive operation data can be acquired in ADNs. How to utilize multi-source data has become the key to realize the intelligent operation of ADNs. This paper proposes a data-driven operation strategy of SOP based on model-free adaptive control (MFAC). First, considering the inaccurate parameters and frequent change of operation states, a data-driven framework is formulated for the real-time operation of SOP. Then, the operation strategies of multiple SOPs are further improved with inter-area coordination. The results of case studies show that driven by the measurement data, the potential benefits of SOPs are explored to adaptively respond to system state changes and improve the operational performance of ADNs.

show abstract

Section: B Data-driven Adaptive Operation Of Sop 1) Mfac-based Operation Control Of Sopmentioning

confidence: 96%

“…The authors in [14] summarized and provided a prospect of data-driven analysis of power system security assessment. As for the efficient operation, a data-driven approach was used in [15] to linearize power flow calculations. The authors in [16] further implemented local control of DG based on data-driven methods to reduce dependence on topology parameters.…”

mentioning

confidence: 99%

Data-Driven Adaptive Operation of Soft Open Points in Active Distribution Networks

Huo

et al. 2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…The numerical tests indicated that such estimation might cause large errors under specific conditions, so further validation and fine-tuning were extremely important. Reference [42] proposed a linear power flow model to accelerate and approximate the power flow calculation. This work was further extended in [43] to tackle the challenge of hidden measurement noises.…”

Section: B Category 2 Optimization Option Selectionmentioning

confidence: 99%

Review of Learning-Assisted Power System Optimization

Ruan,

Zhong,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Machine learning, with a dramatic breakthrough in recent years, is showing great potential to upgrade the power system optimization toolbox. Understanding the strength and limitation of machine learning approaches is crucial to answer when and how to integrate them in various power system optimization tasks. This paper pays special attention to the coordination between machine learning approaches and optimization models, and carefully evaluates to what extent such data-driven analysis may benefit the rule-based optimization. A series of typical references are selected and categorized into four kinds: the boundary parameter improvement, the optimization option selection, the surrogate model and the hybrid model. This taxonomy provides a novel perspective to understand the latest research progress and achievements. We further discuss several key challenges and provide an in-depth comparison on the features and designs of different categories. Deep integration of machine learning approaches and optimization models is expected to become the most promising technical trend.

show abstract

“…The LSD-based acceleration is applicable as long as the optimal power flow problems are in convex formulation, so that we can implement the multi-parametric programming framework [30]. Recently, some convex power flow models are proposed with high accuracy [31], [32]. Such convex models can address the calculation of voltage magnitudes and reactive power, and thus enable the simulation of more protections triggered by voltage magnitudes or reactive power.…”

Section: ) Implementing Other Simulationsmentioning

confidence: 99%

Fast Power System Cascading Failure Path Searching With High Wind Power Penetration

Liu

Wang

Yong

et al. 2020

IEEE Trans. Sustain. Energy

Self Cite

View full text Add to dashboard Cite

Cascading failures have become a severe threat to interconnected modern power systems. The ultrahigh complexity of the interconnected networks is the main challenge toward the understanding and management of cascading failures. In addition, high penetration of wind power integration introduces large uncertainties and further complicates the problem into a massive scenario simulation problem. This paper proposes a framework that enables a fast cascading path searching under high penetration of wind power. In addition, we ease the computational burden by formulating the cascading path searching problem into a Markov chain searching problem and further use a dictionary-based technique to accelerate the calculations. In detail, we first generate massive wind generation and load scenarios. Then, we utilize the Markov search strategy to decouple the problem into a large number of DC power flow (DCPF) and DC optimal power flow (DCOPF) problems. The major time-consuming part, the DCOPF and the DCPF problems, is accelerated by the dynamic construction of a line status dictionary (LSD). The information in the LSD can significantly ease the computation burden of the following DCPF and DCOPF problems. The proposed method is proven to be effective by a case study of the IEEE RTS-79 test system and an empirical study of China's Henan Province power system.Index Terms-Cascading failure, power systems, algorithm acceleration, wind power, optimal power flow, Markov chain searching.

show abstract

Data-Driven Power Flow Linearization: A Regression Approach

Cited by 153 publications

References 28 publications

Data-Driven Adaptive Operation of Soft Open Points in Active Distribution Networks

Data-Driven Adaptive Operation of Soft Open Points in Active Distribution Networks

Review of Learning-Assisted Power System Optimization

Fast Power System Cascading Failure Path Searching With High Wind Power Penetration

Contact Info

Product

Resources

About