Shobhit Singhal

Shobhit Singhal, Lesia Mitridati, Licio Romao

Renewable power sources have low marginal pro-duction costs, but may result in high balancing costs due to the inherent production uncertainty. Current day-ahead markets elicit only point production profiles and neglect the degree of uncertainty associated with each generating asset, preventing the market operator from accounting for balancing costs in day-ahead dispatch and ancillary service procurement. This increases total system costs and undermines market efficiency, especially in renewable-heavy power systems. To address this, we propose a new market clearing paradigm based on a two-stage mechanism, where producers report their production forecast distribution in the day-ahead stage, followed by the realized production in the real-time stage. By extending the Vickery-Clarke-Groves (VCG) payments to the two-stage setting, we show appealing properties in terms of incentive compatibility and individual rationality. An electricity market case study validates the theoretical claims, and illustrates the effectiveness of the proposed mechanism to reduce system costs.

Shobhit Singhal, Marta Fochesato, Liviu Aolaritei et al.

Wind power producers (WPPs) participating in short-term power markets face significant imbalance costs due to their non-dispatchable and variable production. While some WPPs have a large enough market share to influence prices with their bidding decisions, existing optimal bidding methods rarely account for this aspect. Price-maker approaches typically model bidding as a bilevel optimization problem, but these methods require complex market models, estimating other participants' actions, and are computationally demanding. To address these challenges, we propose an online learning algorithm that leverages contextual information to optimize WPP bids in the price-maker setting. We formulate the strategic bidding problem as a contextual multi-armed bandit, ensuring provable regret minimization. The algorithm's performance is evaluated against various benchmark strategies using a numerical simulation of the German day-ahead and real-time markets.

Varun Ramamohan, Shobhit Singhal, Aditya Raj Gupta et al.

Machine learning (ML) methods are used in most technical areas such as image recognition, product recommendation, financial analysis, medical diagnosis, and predictive maintenance. An important aspect of implementing ML methods involves controlling the learning process for the ML method so as to maximize the performance of the method under consideration. Hyperparameter tuning is the process of selecting a suitable set of ML method parameters that control its learning process. In this work, we demonstrate the use of discrete simulation optimization methods such as ranking and selection (R&S) and random search for identifying a hyperparameter set that maximizes the performance of a ML method. Specifically, we use the KN R&S method and the stochastic ruler random search method and one of its variations for this purpose. We also construct the theoretical basis for applying the KN method, which determines the optimal solution with a statistical guarantee via solution space enumeration. In comparison, the stochastic ruler method asymptotically converges to global optima and incurs smaller computational overheads. We demonstrate the application of these methods to a wide variety of machine learning models, including deep neural network models used for time series prediction and image classification. We benchmark our application of these methods with state-of-the-art hyperparameter optimization libraries such as $hyperopt$ and $mango$. The KN method consistently outperforms $hyperopt$'s random search (RS) and Tree of Parzen Estimators (TPE) methods. The stochastic ruler method outperforms the $hyperopt$ RS method and offers statistically comparable performance with respect to $hyperopt$'s TPE method and the $mango$ algorithm.