In this paper, a methodology for short-term forecasting of power generated by a photovoltaic module is reported. The method incorporates a nonlinear autoregressive with exogenous inputs (NARX) fed by the solar radiation and temperature times series, as well as an estimation of power time series obtained by implementing an ideal single diode model. This synthetic time series was validated against an actual photovoltaic module. The NARX model has been implemented in conjunction with the corrective vector multiplier (CVM) technique, which uses solar radiation under clear sky conditions to adjust the forecasting results. In addition, collinearity and the Granger causality tests were used to choose the input variables. The forecasting horizon was 24-h-ahead. The hybrid NARX-CVM model was compared to a nonlinear autoregressive neural network and persistence model using the typic forecasting error measures such as the mean bias error, mean squared error, root mean squared error and forecast skill. The results showed that the forecasting skills of the hybrid model are about 34% against the NAR model and about 42% against the Persistence model. The model was validated by blind forecasting. The results demonstrated evidence of the quality of the conformed forecasting model and the convenience of its implementation and building.

Microgrids with substantial incorporation of distributed renewable energy sources face challenges such as magnitude voltage rise, frequency variations, and power quality issues. A novel method is proposed to managing and controlling reactive power within microgrids with high integration of photovoltaic panels. The proactive dispatch is carried out for a few minutes in advance, using power forecast and the inverters of the photovoltaic installations as reactive energy providers. The goal is to stabilise voltage levels and reduce overall energy losses. Optimising reactive power poses a non‐convex problem. The presented method tackles this challenge by employing Conic approximations and Wirtinger calculus techniques to convert and frame the issue within a convex framework, simplifying its resolution. It primarily concentrates on fine‐tuning reactive power output from photovoltaic inverters to minimise overall losses and maintain stable magnitude voltage levels. To enable the reactive power dispatch, a Markov switching forecasting model that uses on‐site data, including sky imagery and other external variables, predicting active power generation every 6 minutes. The proposed technique is evaluated in a CIGRE test network, showing an average loss reduction between 14% and 66% for sunny and cloudy conditions with different levels of PV penetration, this while maintaining the steady state voltages in range.