With the ongoing transformation of electricity generation from large thermal power plants to smaller renewable energy sources (RESs), such as wind and solar, modern renewable power systems need to address the new challenge of the increasing uncertainty and complexity caused by the deployment of electricity generation from RESs and the integration of flexible loads and new technologies. At present, a high volume of available data is provided by smart grid technologies, energy management systems (EMSs), and wide-area measurement systems (WAMSs), bringing more opportunities for data-driven methods. Deep reinforcement learning (DRL), as one of the state-of-the-art data-driven methods, is applied to learn optimal or near-optimal control policy by formulating the power system as a Markov decision process (MDP). This paper reviews the recent DRL algorithms and the existing work of operational control or emergency control based on DRL algorithms for modern renewable power systems and control-related problems for small signal stability. The fundamentals of DRL and several commonly used DRL algorithms are briefly introduced. Current issues and expected future directions are discussed.
Since the development of renewable power generation, Sub/Super-Synchronous Control Interac-tion (SSCI), has attracted wide attention. Sub/super-synchronous oscillation (SSO) belongs to the category of small signal stability, and its characteristics are closely related to the operation mode and controller parameters in power grid. The operation mode of renewable power system changes frequently, a method to construct controller parameter stability region (PSR) is proposed for online assessment of the matching degree of controller parameters in power grid under current operation mode. Based on Gerschgorin disk theorem (GDT), eigenvalue distribution range of the system state matrix is estimated, thus the feasible value set of the controller parameter is deduced through small signal stability criterion. The stability margin evaluation index is proposed for guiding the prevention and control of SSO. Specifically, the preconditions of the application of the GDT on the PSR construction are discussed, and a construction method of transition matrix is proposed for the PSR construction. Furthermore, to reduce the conservativeness of PSR, an extension method for PSR is given. Finally, the validity of the proposed method is verified by a realistic benchmark. The efficiency of the proposed method is highlighted by comparing with the point-wise eigenvalue calculation of the state matrix.