Energy storage mitigates renewable energy curtailment by absorbing excess electricity generated during periods of high renewable output and low demand or grid constraints, then releasing it when demand is higher or grid capacity is available. . As the penetration of variable renewable energy increases, curtailment of solar PV generation will only increase. Since curtailment will almost always be cheaper than investing in new transmission capacity or new grid-scale storage, curtailed energy should be rewarded, so that PV investment. . curtailment is emerging as a common challenge facing a growing number of power systems. At its core, curtailment is a symptom of an insuficiently flexible power system. This reduces the need to limit renewable generation. .
[PDF Version]
This paper presents a variety of ML approaches combined with XAI to predict solar power generation, aiming to optimize energy management in smart grids. . Machine learning (ML) algorithms can provide highly accurate predictions, but their complexity often makes them difficult to interpret due to their black-box nature. Combining ML and Explainable Artificial Intelligence (XAI) makes these models more transparent and enables users to understand the. . This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts power generation rates based on environmental conditions. .
[PDF Version]
