The proliferation of photovoltaic (PV) power generation in power distribution grids induces increasing safety and service quality concerns for grid operators. The inherent variability, essentially due to meteorological conditions, of PV power generation affects the power grid reliability. In order to develop efficient monitoring and control schemes for distribution grids, reliable forecasting of the solar resource at several time horizons that are related to regulation, scheduling, dispatching, and unit commitment, is necessary. PV power generation forecasting can result from forecasting global horizontal irradiance (GHI), which is the total amount of shortwave radiation received from above by a surface horizontal to the ground. A comparative study of machine learning methods is given in this paper, with a focus on the most widely used: Gaussian process regression (GPR), support vector regression (SVR), and artificial neural networks (ANN). Two years of GHI data with a time step of 10 $\min$ are used to train the models and forecast GHI at varying time horizons, ranging from 10 $\min$ to 4 $\mathrm{h}$. Persistence on the clear-sky index, also known as scaled persistence model, is included in this paper as a reference model. Three criteria are used for in-depth performance estimation: normalized root mean square error (nRMSE), dynamic mean absolute error (DMAE) and coverage width-based criterion (CWC). Results confirm that machine learning-based methods outperform the scaled persistence model. The best-performing machine learning-based methods included in this comparative study are the long short-term memory (LSTM) neural network and the GPR model using a rational quadratic kernel with automatic relevance determination.

Microgrids (MGs) and networked (interconnected) microgrids (NMGs) are emerging as an efficient way for integrating distributed energy resources (DERs) into power distribution systems. MGs and NMGs can disconnect from the main grid and operate autonomously, strengthen grid resilience, and help mitigate grid disturbances and maintain power quality. In addition, when supported by sophisticated and efficient management strategies, MGs and NMGs have the ability to enhance power supply reliability. However, their deployment comes with many challenges, in particular regarding the efficient management of DERs. That is why a survey of recent advances in the smart management—the term refers to a variety of planning and control tasks—of MGs and NMGs is presented in this paper. It aims at establishing a picture of strategies and identifying trends in methods. The reader is provided with an in-depth analysis of a variety of papers recently published in peer-reviewed journals: the way the methods are used and the common issues addressed by the scientific community are discussed. Following this analysis, one can especially observe that (1) model-based predictive control (MPC) is emerging as a competitive alternative to conventional methods, in particular in voltage and frequency regulation and DER management (2) due to their ability to handle complex tasks, data-driven strategies are getting more and more attention from the scientific community (3) game theory (GT) is a very good candidate for efficient management of complex systems as NMGs (4) MPC and artificial intelligence are increasingly being used for proper MG islanded operation or to manage electric vehicles (EVs) efficiently.