Solving Bilevel Optimal Bidding Problems Using Deep Convolutional Neural Networks

Current state-of-the-art solution techniques for solving bilevel optimization problems either assume strong problem regularity criteria or are computationally intractable. In this article, we address power system of structure, commonly arising after the deregulation industry. Such predominantly solved by converting lower level into a set equivalent constraints using Karush–Kuhn–Tucker optimality conditions at an expense binary variables. Furthermore, in case is nonconvex, duality does not hold rendering single-level reduction inapplicable. To overcome this, propose effective numerical scheme based on bypassing completely approximation function that replicates relevant effect upper level. The constructed training deep convolutional neural network. procedure run iteratively to enhance accuracy. As study, proposed method applied price-maker energy storage optimal bidding considers ac flow-based market clearing results indicate greater actual profits achieved as compared less accurate dc representation.