A data‐driven multi‐time scale robust scheduling model for a wind–hydro–thermal power system is presented in this study, according to the characteristic that wind power prediction accuracy increases with the decrease of the time scale. In day‐ahead scheduling, a generation plan is formulated with the target of minimising the total operating cost, and a data‐driven robust optimisation method based on the robust kernel density estimation (RKDE) is employed to deal with the uncertainty of wind power. That is, the distributional information of wind power is extracted by the RKDE from the big data, then the distributional information is incorporated into a data‐driven uncertainty set, and finally, a robust optimisation model is formed. During the intraday scheduling stage, the objective is to minimise the total water spillage in cascade hydropower stations and the adjustment cost of thermal units, and the task is to readjust the outputs of units based on the base outputs obtained by the day‐ahead scheduling, combined with the rolling forecast data of wind power and load. The real‐time scheduling is aimed at satisfying the power balance with minimum power adjustment. Finally, a test system is carried out to verify the efficiency and practicability of the proposed framework.

This study proposes a data‐driven distributionally robust framework for unit commitment based on Wasserstein metric considering the wind power generation forecasting errors. The objective of the constructed model is to minimise the expected operating cost, including the generating cost, start‐up and shut‐down costs, and also the reserve cost, which overcomes the shortcomings of the conventional model without optimising the reserve capacity. What is more important, different from the conventional robust optimisation methods, wind power big data is fully utilised in this model to construct the ambiguity set without any presumption about its probability distribution. This is realised by Wasserstein ball with an empirical distribution as the centre. Thus, the proposed robust model is actually data‐driven and can immunise the solutions against the worst‐case distribution in the ambiguity set. In addition, the scale of the historical data is very critical for this method, the larger the scale is, the smaller the ambiguity set is and the less conservative the result is. Numerical results and Monte Carlo simulations on a real 75‐bus system demonstrate the superiority of the proposed model.

Hybrid power plants (HPPs) combining multiple generation and/or storage sources behind a single connection point are becoming popular due to their capability to provide additional value for both plant owners and power systems compared to individual technology renewable power plants. However, the research on HPPs is still in nascent stage. This article comprehensively overviews utility‐scale HPPs (power plants ranging from hundreds of MW to GW scale). It primarily addresses HPPs that combine renewable sources such as wind and solar (PV technology) with electrical energy storage (ESS), all connected behind a single grid connection and operated as a unified power plant by a single operator. This article covers various aspects such as HPPs' potential benefits, research challenges, and opportunities related to their design, operation, and development, from both societal and HPP owners' perspectives. It briefly discusses the advantages of HPPs compared to individual renewable technology‐based power plants highlighting the potential added values of HPPs for owners, system operators, and society, while ensuring compliance with grid code requirements at the point of common coupling. The main focus is on identifying and clustering the research challenges associated with design and operation of HPPs. Topics such as energy management systems, sizing and siting, electrical design and control, uncertainties and forecasting, grid emulation and advanced testing, and multi‐energy system integration are elaborated and reviewed. This article demonstrates that significant research is urgently needed to enhance renewable generation flexibility and improve grid services. Addressing these challenges will accelerate the development and deployment of HPPs.

Since hybrid power plants (HPPs) play an intensive role in the energy supply balance of future energy systems, there is today increased attention on co-located wind–battery HPPs both in industry and academia. This paper proposes an energy management system (EMS) methodology for wind–battery plants participating in two sequential electricity markets, namely in the spot market (SM) and the balancing market (BM). The proposed and implemented EMS consists of day-ahead (DA) spot market optimization, hour-ahead (HA) balancing market optimization, and intra-hour re-dispatch optimization to allow HPPs to achieve energy arbitrage, to offer regulation power at the HA stage, and to reduce real-time imbalances. The optimization models used in the EMS incorporate an accurate battery degradation model and grid connection constraints. This paper presents a detailed case analysis of the profitability of HPPs in markets towards 2030 based on the proposed EMS. Furthermore, the value of intra-hour re-dispatch optimization in improving the feasibility of generation plans, as well as the impacts of overplanting on wind energy curtailment and battery degradation, is also investigated based on the proposed EMS.

In recent years, renewable hybrid power plants (HPPs) have experienced rapid expansion. Energy management systems (EMSs) are vital to these facilities, helping maximize economic returns for owners and shaping operational strategies across various time scales. However, a comprehensive review of advancements in this field is still lacking. This paper presents an in‐depth analysis of EMS research tailored for grid‐connected, utility‐scale renewable HPPs. It begins by outlining common HPP configurations, which form the foundation for EMS modeling. Five key EMS approaches are then discussed in detail, namely, rule‐based methods, mathematical optimization, model predictive control, deep reinforcement learning, and stochastic dynamic programming. Following that, the paper categorizes the types of market participation and uncertainties addressed by EMS, and it introduces several industrial EMS tools. Finally, the discussion highlights existing gaps in EMS research for HPPs. Overall, this paper provides cutting‐edge insights into EMS for HPPs, serving as a valuable resource for both researchers and industry professionals involved in HPP EMS development.