Search

Stochastic unit commitment is an efficient method for grid operation in the presence of significant uncertainties. An example is an operation during a predicted hurricane with uncertain line out-ages. However, the solution quality comes at the cost of substantial computational burden, which makes its adoption challenging. This paper evaluates some possible ways that machine learning can be used to reduce this computational burden. First, a set of feasibility studies is conducted. Results suggest that using machine learning as an assistant to the stochastic unit commitment solver is more advantageous than using it as a standalone solver. In particular, the machine learning model is trained to facilitate solving the problem by determining the unnecessary constraints that can be removed from the original problem without affecting the final accuracy. The variables that can be used as input features/predictors or outputs for the machine learning model are determined through feasibility studies. Then, an algorithm to train and utilize a machine learning model is proposed. The method is tested on a 500-bus synthetic South Carolina system. Various test cases show an average reduction in solution time by more than 90% by using the trained machine learning model to assist the stochastic unit commitment solver. [ABSTRACT FROM AUTHOR]

• A novel two-stage formulation for AC optimal transmission switching problems. • A Generalized Benders Decomposition based algorithm to solve the problem. • Be able to handle grid uncertainties in optimal transmission switching problems. • Guaranteed convergence and accuracy for the AC optimal transmission problems. • Numerical results on the IEEE 118-bus system and South Carolina 500-bus system. Optimal transmission switching is proposed in recent years to optimize the power system operational cost in deterministic studies. With the rapid growth of renewable generations, the grid uncertainties have greatly increased, which cannot be ignored in the decision-making of optimal transmission switching problems. This paper proposes a novel two-stage stochastic optimization formulation with a convex relaxation for AC optimal transmission switching problems. A generalized Benders decomposition based algorithm, including an inner loop and an outer loop, is proposed to solve the AC optimal transmission switching problem with grid uncertainties. The optimal switching plan and the expected system cost will be found in the iterative calculation without any sacrifice of accuracy. Numerical studies on the IEEE 118-bus system and the South Carolina 500-bus confirm the effectiveness of the proposed decomposition approach in solving the AC optimal transmission switching problems with grid uncertainties. The scalability analysis shows the proposed approach is efficient in dealing with a large number of scenarios. [ABSTRACT FROM AUTHOR]