A large-scale integration of photovoltaic (PV) systems can degrade the stability of the power grid. Therefore, it is important to accurately predict the short-term output power generated from PV systems to achieve better grid power distribution and allocation. For this reason, a short-term PV power prediction model that uses the data collected from temperature sensors, irradiance sensors, and other relevant sensors was proposed, in which an improved dragonfly algorithm (IDA) was applied to optimize the support vector machine (SVM). First, the output power curves of PV systems under sunny, cloudy, and rainy conditions were analyzed to determine the input variables of the prediction model, which included temperature, relative humidity, and solar radiation intensity. Second, the original dragonfly algorithm in the optimization process was improved, and then, this IDA was utilized to optimize the parameters of SVM, enhancing the predictive capability of the model. Finally, the IDA-optimized SVM (IDA-SVM) model was applied to predict the PV output power. Test performance results demonstrated that the average absolute percentage errors of IDA-SVM were 2.42, 5.96, and 7.44% for sunny, cloudy, and rainy days, respectively, outperforming other comparative models. The performance results showed that the proposed model can not only improve the stability of PV integration, but also effectively increase the penetration rate of PV energy and enhance the reliability of power system operation.