Scalable Optimization Methods for Distribution Networks With High PV Integration

Guggilam, Swaroop S.; Dall’Anese, Emiliano; Chen, Yu Christine; Dhople, Sairaj V.; Giannakis, Georgios B.

doi:10.1109/tsg.2016.2543264

Cited by 151 publications

(101 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Reference [6] leverages semi-definite programming relaxation for efficiently solve an optimization of SI real and reactive power. An Alternating Direction Method of Multipliers based algorithm is developed in [7] for optimal SI reactive power dispatch and voltage regulation. Reference [8] studies coordination of OLTCs and SIs.…”

Section: Introductionmentioning

confidence: 99%

Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation

Jin²,

Sharma³

2019

2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Increasing adoption of solar photovoltaic (PV) presents new challenges to modern power grid due to its variable and intermittent nature. Fluctuating outputs from PV generation can cause the grid violating voltage operation limits. PV smart inverters (SIs) provide a fast-response method to regulate voltage by modulating real and/or reactive power at the connection point. Yet existing local autonomous control scheme of SIs is based on local information without coordination, which can lead to suboptimal performance. In this paper, a deep reinforcement learning (DRL) based algorithm is developed and implemented for coordinating multiple SIs. The reward scheme of the DRL is carefully designed to ensure voltage operation limits of the grid are met with more effective utilization of SI reactive power. The proposed DRL agent for voltage control can learn its policy through interaction with massive offline simulations, and adapts to load and solar variations. The performance of the DRL agent is compared against the local autonomous control on the IEEE 37 node system with thousands of scenarios. The results show a properly trained DRL agent can intelligently coordinate different SIs for maintaining grid voltage within allowable ranges, achieving reduction of PV production curtailment, and decreasing system losses.

show abstract

Section: Introductionmentioning

confidence: 99%

Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation

Jin²,

Sharma³

2019

2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

show abstract

“…• The Flat linearization profile [10]: Constraints (7b) are linearized around the voltage phasor:Ẽ i = 1,F i = 0, ∀i ∈ N . • The No-Load linearization profile developed in [11] and [10], and used in [18] and [19]: Constraints (7b) are linearized aroundẼ + jF = −(G + jB) −1 (G + jB)(E 0 + jF 0 ) where the index 0 denotes the slack bus. The admittance matrix is decomposed so that the bus current injections can be expressed as:…”

Section: Numerical Resultsmentioning

confidence: 99%

Optimal Linearizations of Power Systems With Uncertain Supply and Demand

Hohmann

Warrington

Lygeros

2019

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

Linearized models of power systems are often desirable to formulate tractable control and optimization problems that still reflect real-world physics adequately under various operating conditions. In this paper, we propose an approach that can make use of known data concerning the distribution of demand, and/or intermittent supply, to minimize expected model inconsistency with respect to the original non-linear model. The optimal linearization is obtained by approximating a generalized moment problem with a hierarchy of sparse semi-definite relaxations. The output is a linearization point that minimizes the expected absolute constraint violation with respect to the uncertain supply and demand. Numerical results for different power systems networks demonstrate the accuracy and scalability of our linearization method.

show abstract

“…Previous work [19], [21] showed that the nodes at the end of the line tend to curtail more solar energy than those closer to the transformer. Thus, we introduce a fairness objective to ensure more equal distribution of curtailment across the nodes…”

Section: Objective Functionmentioning

confidence: 97%

“…This technique was proposed in [20] and applied in [13], [15], [21], however it has not yet been widely deployed. Constant active and reactive loads are denoted by P d , Q d .…”

Section: B Optimal Power Flowmentioning

confidence: 99%

Reducing the Unfairness of Coordinated Inverter Dispatch in PV-Rich Distribution Networks

Lusis

Andrew

Liebman

et al. 2019

2019 IEEE Milan PowerTech

View full text Add to dashboard Cite

The integration of a high share of solar photovoltaics (PV) in distribution networks requires advanced voltage control technologies or network augmentation, both associated with significant investment costs. An alternative is to prevent new customers from installing solar PV systems, but this is against the common goal of increasing renewable energy generation. This paper demonstrates that solar PV curtailment in low voltage areas can be reduced and fairly distributed among PV owners by centrally coordinating the operation of PV inverters. The optimal inverter active and reactive power operation points are computed by solving a multi-objective optimization problem with a fairness objective. The main results show that fair optimal inverter dispatch (FOID) results in less power curtailment than passive voltage regulation based on Volt/VAr droop control, especially at high solar PV to load ratios. The effectiveness of the model is demonstrated on a residential low voltage network.

show abstract

Scalable Optimization Methods for Distribution Networks With High PV Integration

Cited by 151 publications

References 27 publications

Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation

Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation

Optimal Linearizations of Power Systems With Uncertain Supply and Demand

Reducing the Unfairness of Coordinated Inverter Dispatch in PV-Rich Distribution Networks

Contact Info

Product

Resources

About