Electrical networks of transmission system operators are mostly built up as isolated networks without access to the Internet. With the increasing popularity of smart grids, securing the communication network has become more important to avoid cyber-attacks that could result in possible power outages. For misuse detection, signature-based approaches are already in use and special rules for a wide range of protocols have been developed. However, one big disadvantage of signature-based intrusion detection is that zero-day exploits cannot be detected. Machine-learning-based anomaly detection methods have the potential to achieve that. In this paper, various such methods for intrusion detection in substations, which use the asynchronous communication protocol International Electrotechnical Commission (IEC) 60870-5-104, are tested and compared. The evaluation of the proposed methods is performed by applying them to a data set which includes normal operation traffic and four different attacks. While the results of supervised and semi-supervised machine learning approaches are rather encouraging, the unsupervised and signature-based methods suffer from general bad performance and had difficulties to detect some attacks.