This study explores advanced multivariate models that incorporate non-climatic exogenous variables for very short-term photovoltaic energy forecasting. By integrating historical energy data from multiple photovoltaic plants, the research aims to improve the prediction accuracy of a target plant while addressing critical challenges in electric power systems (EPS), such as frequency stability. Frequency stability becomes increasingly complex as renewable energy sources penetrate the grid because of their intermittent nature. To mitigate this challenge, precise forecasting of photovoltaic energy generation is essential for balancing supply and demand in real time. The performance of long short-term memory (LSTM) networks and bidirectional LSTM (BiLSTM) networks was compared over a 5 min horizon. Including energy generation data from neighboring plants significantly improved prediction accuracy compared to univariate models. Among the models, multivariate BiLSTM showed superior performance, achieving a lower root-mean-square error (RMSE) and higher correlation coefficients. Quantile regression applied to manage prediction uncertainty, providing robust confidence intervals. The results suggest that incorporating an exogenous power series effectively captures spatial correlations and enhances prediction accuracy. This approach offers practical benefits for optimizing grid management, reducing operational costs, improving the integration of renewable energy sources, and supporting frequency stability in power generation systems.

In a centralized wholesale power system market scenario, the transmission and distribution constraints limit dispatch and require additional generation to support an integrated area known as Security Generation. This one must be covered in each area, and its cost transferred to the final users. The security generation cost gets higher when operation implicates the use of thermal power plants whose price equation depends on international fuels costs. This paper examines the consequences of a high reliance on thermal power plants. It focuses on scheduled reserves affecting electricity unit costs and the potential for constraints to lead to long-term consequences. The paper analyzes the security generation behavior based on reports and uses a real scenario to support simulations and decisions, evidencing monthly cost and an estimated CO2 emission. Results show the direct cost-saving potential of investing in renewable projects and technology. The paper can allow to replicate the analysis in comparable areas and regions with similar challenges.