Enhancing profits of hybrid wind-battery plants in spot and balancing markets using data-driven two-level optimization

Nowadays, co-locate renewable power plants and energy storage systems, forming hybrid power plants (HPPs) have raised commercial interests. One popular configuration of HPP is the hybrid wind-battery plant (HWBP). This paper proposes a data-driven energy management system (DDEMS) for enhancing the profits of HWBPs in spot markets and balancing markets. The two-level scheme is adopted, where the first level models day-ahead optimal offering of energy in spot markets and the second level models imbalance energy settlement in balancing markets. Hybrid stochastic optimization and Wasserstein metric-based data-driven robust optimization are applied to model uncertainties associated with market prices and wind power, respectively. In addition, a novel parameter selection algorithm is proposed to determine the radii of Wasserstein ambiguity sets. Then, the two-level model is reformulated as single-level mixed integral linear programming. Simulation results from two different years show that the proposed parameter selection algorithm helps the DDEMS to find the trade-off between robustness and economy. In addition, the results also demonstrate that the proposed methodology is able to enhance the profits of HWBP in comparison with deterministic optimization and pure stochastic optimization.