DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow

Pan, Xiaojun; Zhao, Tianyu; Chen, Minghua; Zhang, Shengyu

doi:10.1109/tpwrs.2020.3026379

Cited by 138 publications

(82 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The substantial increase of uncertainty in generation and demand requires to solve OPF repeatedly and closer to real-time, in order to analyze a large number of scenarios; this leads to significant computational challenges [4]. Neural networks present a promising alternative to conventional optimization solvers, achieving a speed-up of several orders of magnitude [5]- [9]. However, the lack of any guarantees related to the neural network performance presents a major barrier towards their application in safetycritical systems.…”

Section: Introductionmentioning

confidence: 99%

“…Machine learning including neural networks have been applied to a range of power system applications over the past three decades; for a recent survey please refer to [10]. The focus of this work is on obtaining guarantees for machine learning approaches such as the ones in [5]- [9], which predict solutions to OPF problems and replace the use of conventional optimization solvers. These approaches can result to larger computational speed-ups compared to predicting inactive constraints [11] or warm-start points [12] that could accelerate conventional optimization solvers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

Venzke

Low

et al. 2020

2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

This paper introduces for the first time a framework to obtain provable worst-case guarantees for neural network performance, using learning for optimal power flow (OPF) problems as a guiding example. Neural networks have the potential to substantially reduce the computing time of OPF solutions. However, the lack of guarantees for their worst-case performance remains a major barrier for their adoption in practice. This work aims to remove this barrier. We formulate mixed-integer linear programs to obtain worst-case guarantees for neural network predictions related to (i) maximum constraint violations, (ii) maximum distances between predicted and optimal decision variables, and (iii) maximum sub-optimality. We demonstrate our methods on a range of PGLib-OPF networks up to 300 buses. We show that the worst-case guarantees can be up to one order of magnitude larger than the empirical lower bounds calculated with conventional methods. More importantly, we show that the worst-case predictions appear at the boundaries of the training input domain, and we demonstrate how we can systematically reduce the worst-case guarantees by training on a larger input domain than the domain they are evaluated on.Index Terms-Neural networks, mixed-integer linear programming, optimal power flow.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

Venzke

Low

et al. 2020

2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

show abstract

“…Nonlinear Optimization. Except linear programming, all mathematical programming models are categorized as nonlinear optimization, i.e., the optimal power flow (OPF) model [133]. In [152], a mixed-integer linear programming (MILP) method is introduced to guarantee the worst case for deep neural network predictions which enables a significant reduction of computational time for the OPF model in terms of maximum constraint violations.…”

Section: A Knowledge Based Optimizationmentioning

confidence: 99%

“…Nonlinear optimization 2019 [133] Security-constrained DC OPF A predict-and-reconstruct approach is developed for training a deep neural network to learn a highdimensional mapping from the load inputs to the generation and phase angle outputs which can predict the result of new problems.…”

Section: Evolutionary Computationmentioning

confidence: 99%

AI-powered Energy Internet Towards Carbon Neutrality: Challenges and Opportunities

Li¹

2021

Preprint

View full text Add to dashboard Cite

From self-driving vehicles, voice recognition based virtual digital assistants, smart thermostats to recommendation systems, Artificial Intelligence (AI) is becoming a crucial part of the carbon neutral society that has drawn considerable interest from energy supply firms, startups, technology developers, financial institutions, national governments and the academic community. The emergence of AI initiates numerous opportunities to transform energy industry to AI-powered smart system which can revolutionize traditional approaches of creativity thinking, strategical operation, and solution seeking, especially for accelerating carbon neutrality of our society. This survey provides a comprehensive overview of fundamental principles that underpin applications of big data analysis in Energy Internet (EI), such as smart energy supply and consumption, smart health and Fintech. Next, we focus on intelligent decision-making for the energy industry and inform the state-of-the-art by thoroughly reviewing the literature. Subsequently, cybersecurity issues for AI system related to EI are discussed with recent advancements from vulnerability analysis of AI system to differential privacy and to blockchain based security technology. To our knowledge, this is one of the first academic, peer-reviewed works to provide a systematic review of AI applications for EI research and initiatives in terms of big data analysis, intelligent decision-making and AI related cybersecurity These initiatives were systematically classified into different groups according to the field of application, methodology and contribution Afterwards, potential challenges, limitations for existing research and opportunities for future directions are discussed, ranging from emerging explainable AI, to localized multi-energy marketplaces, self-driving electric vehicle charging and e-mobility. This paper can help us understand how to build smart cities and critical infrastructure for a climate-changed world towards the UN’s sustainable development goals.

show abstract

“…Optimal power flow can be solved by various FACTS techniques and devices, which certainly allow safety restrictions in the power system. System security is guaranteed by the optimal placement of the FACTS device in the system, for example, SVC, TCSC [6], Thyristor-Controlled Phase-Shifting Transformer (TCPST), Static Synchronous Compensator (STATCOM) [5], UPFC [7] Thyristor-Controlled Voltage Regulator (TCVR), and IPFC [8]. The FACTS devices should provide the highest advantage to power networks for maintaining stability and security constraints.…”

Section: Introductionmentioning

confidence: 99%

Security Enhancement in Power System Using FACTS Devices and Atom Search Optimization Algorithm

Amarendra¹,

Srinivas²,

Rao³

2018

EAI Endorsed Transactions on Energy Web

View full text Add to dashboard Cite

In power systems, control, system operations are an important and difficult task by enhancing the power systems' security. An enhancement of the security system is done by the optimal location selection of the Flexible Alternating Current Transmission System (FACTS) devices, for instance, Unified Power Flow Controller (UPFC), Thyristor-Controlled Series Capacitor (TCSC), Interlink Power Flow Controller (IPFC), and Static VAR Compensator (SVC). Therefore, the Atom Search Algorithm (ASO) is utilized to compute the precise optimal placement of the FACTS device. FACTS devices must be in the correct location on the power system to improve system safety. The performances are evaluated by severity index, Line Overload Sensitivity Index (LOSI), voltage, voltage deviation¸, power loss, fitness function, and the fuel cost with the IEEE 30, IEEE 118, and IEEE 300 bus system. To validate the proposed methodology, it is contrasted with the conventional techniques like Dragonfly Algorithm (DA), Whale Optimization Algorithm (WOA), Jaya, Flower Pollination Algorithm (FPA), Grey Wolf Algorithm (GWA), and the Jaya Flower Pollination (JA-FPA) systems.

show abstract

DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow

Cited by 138 publications

References 39 publications

Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

AI-powered Energy Internet Towards Carbon Neutrality: Challenges and Opportunities

Security Enhancement in Power System Using FACTS Devices and Atom Search Optimization Algorithm

Contact Info

Product

Resources

About