Toward Distributed Energy Services: Decentralizing Optimal Power Flow With Machine Learning

Dobbe, Roel; Sondermeijer, Oscar; Fridovich-Keil, David; Arnold, Dan; Callaway, Duncan S.; Tomlin, Claire J.

doi:10.1109/tsg.2019.2935711

Cited by 72 publications

(55 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A data-driven method presented in [117] adopts nonlinear control techniques to determine the reference values for real-time reactive power outputs of inverter-based DGs. The machine learning methods proposed in [118,119] employ multi-learning regression to calculate the optimal reactive power outputs of DGs. In [120], a voltage control approach at the grid edges is proposed using an artificial neural network (ANN) for DER inverters.…”

Section: Data-driven/machine Learning Approachesmentioning

confidence: 99%

An overview of grid-edge control with the digital transformation

et al. 2021

View full text Add to dashboard Cite

Distribution networks are evolving to become more responsive with increasing integration of distributed energy resources (DERs) and digital transformation at the grid edges. This evolution imposes many challenges to the operation of the network, which then calls for new control and operation paradigms. Among others, a so-called grid-edge control is emerging to harmonise the coexistence of the grid control system and DER’s autonomous control. This paper provides a comprehensive overview of the grid-edge control with various control architectures, layers, and strategies. The challenges and opportunities for such an approach at the grid edge with the integration of DERs and digital transformation are summarised. The potential solutions to support the network operation by using the inherent controllability of DER and the availability of the digital transformation at the grid edges are discussed.

show abstract

Section: Data-driven/machine Learning Approachesmentioning

confidence: 99%

An overview of grid-edge control with the digital transformation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A deep neural network was developed for this task, and the network size was properly configured according to approximation accuracy. In [40], a data-driven approach to reconstructing the solution of a centralized optimal power flow was proposed. The idea was that local controllers could find a near-optimal solution by learning the limited but locally available data.…”

Section: B Category 2 Optimization Option Selectionmentioning

confidence: 99%

“…The supervised and transfer learning were applied in [41] to estimate the Pareto front that is made up with a series of initial values. This task was indeed more difficult than [38]- [40]. The numerical tests indicated that such estimation might cause large errors under specific conditions, so further validation and fine-tuning were extremely important.…”

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

“…In [13–16], data‐driven approaches have been proposed to learn control strategies for each controlled asset, using data from off‐line OPF calculations to train the respective local models (one for each controlled asset), under a variety of operating conditions that are either historically observed or synthetically created using simulations [16].…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we focus on an online data‐driven approach for real‐time voltage control of distribution networks; specifically, we propose the Kernel‐based Decentralized Online Learning (K‐DOL) algorithm, where each inverter‐interfaced controlled asset learns a local control strategy, as local (or regional) observations become available. Compared to the works in [13–16], K‐DOL is valid for meshed, as well as, radial network topologies, and does not require off‐line OPF calculations to learn control strategies for each controlled asset. Moreover, K‐DOL has several advantages over centralized and distributed OPF solutions, as it does not require a detailed model of the network or a fully deployed communication infrastructure to infer solutions that contribute to the voltage control goal.…”

Section: Introductionmentioning

confidence: 99%