Prediction of Umbrella Constraints

Security-constrained optimal power flow (SCOPF) problems are essential tools to transmission system operators for long-term and operational planning and real-time operation. SCOPF is used in many system studies. However, the solution procedure of SCOPF problems is challenging because of the inherent size and scope of modern grids. As empirical evidence and past research shows relatively few constraints in SCOPF problems are necessary and sufficient to enclose the feasible set of solutions. These constraints are called umbrella constraints. An optimization-based formulation, called umbrella constraint discovery-UCD, has been proposed to identify such constraints. Additionally, it was shown that umbrella sets are relatively insensitive to load changes in the system. In order to leverage the results of prior UCD runs, this paper proposes the use of heuristic methods to predict the umbrella set of a system based on the UCD results for similar conditions. The proposed approach capitalizes on the cyclic nature of electric loads as well as on the insensitivity of umbrella sets to the system parameter changes. In other words, the proposed method predicts the members of the umbrella set of SCOPF problems when the system conditions change. Artificial neural networks have been used for this purpose. The results show the applicability of such methods for prediction of umbrella sets.

[1]  Francois Bouffard,et al.  Acceleration of Umbrella Constraint Discovery in Generation Scheduling Problems , 2015, IEEE Transactions on Power Systems.

[2]  Francois Bouffard,et al.  Acceleration of umbrella constraint discovery in generation scheduling problems , 2014, 2015 IEEE Power & Energy Society General Meeting.

[3]  John N. Tsitsiklis,et al.  Introduction to linear optimization , 1997, Athena scientific optimization and computation series.

[4]  Jizhong Zhu,et al.  Optimization of Power System Operation , 2009 .

[5]  M. M. Ardehali,et al.  Very short-term wind speed prediction: A new artificial neural network–Markov chain model , 2011 .

[6]  J. Ramos,et al.  State-of-the-art, challenges, and future trends in security constrained optimal power flow , 2011 .

[7]  Seyed Hossein Hosseinian,et al.  A new integrated approach for very short-term wind speed prediction using wavelet networks and PSO , 2007 .

[8]  A. Conejo,et al.  Market-clearing with stochastic security - part II: case studies , 2006, 2006 IEEE Power Engineering Society General Meeting.

[9]  J. Arroyo,et al.  Umbrella contingencies in security-constrained optimal power flow , 2005 .

[10]  Francois Bouffard,et al.  Identification of Umbrella Constraints in DC-Based Security-Constrained Optimal Power Flow , 2013, IEEE Transactions on Power Systems.

[11]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[14]  Mohammad Shahidehpour,et al.  The IEEE Reliability Test System-1996. A report prepared by the Reliability Test System Task Force of the Application of Probability Methods Subcommittee , 1999 .

[15]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.