As the world shifts toward sustainable energy, the use of Distributed Energy Resources (DER), particularly solar energy systems, is on the rise. However, this interconnectedness increases vulnerability to cyberattacks. Ensuring the security of these solar DER systems is crucial for a reliable energy future. This paper introduces a Network Intrusion Detection System (NIDS) specifically designed for solar DER applications. The approach utilizes advanced machine learning techniques that are more effective at detecting various types of attacks than traditional methods. An improved voting classifier was developed, combining multiple classifier models to enhance detection accuracy. The machine learning-based NIDS achieved 99.95% accuracy, 99.89% precision, and 100% recall for Denial-of-Service attacks. This approach successfully identifies different network intrusions, thereby strengthening the cybersecurity of solar DER systems. Implementing robust security measures can reduce the risks associated with solar energy networks, facilitating seamless integration into the sustainable energy landscape.