Dataset: IEC 61850 Data sets (SCD files) and their Metadata

This dataset contains a collection of IEC 61850 System Configuration Description (SCD) files extracted from substation automation and protection system projects. Each file follows the Substation Configuration Language (SCL) defined in the IEC 61850 standard and encodes detailed engineering metadata for intelligent electronic devices (IEDs), communication networks, and data models used in electric power substations.
The dataset was curated to support research and benchmarking in the areas of:
Cybersecurity of IEC 61850 Substation systems
Metadata from each file (Header, Substation, Communication, IED, and DataTypeTemplates sections) has been parsed and exported into corresponding JSON summaries to facilitate machine-readable search, indexing, and comparative analysis.
These files represent complete substation configurations (SCD) created using vendor-specific tools such as RTDS Configurator, SEL AcSELerator, and OMICRON IEDScout. Duplicate and structurally similar files have been identified and documented.
Researchers may use this dataset to explore schema variations, conduct cybersecurity experiments, validate SCL structures against IEC 61850 editions, develop interoperability frameworks, or train models for automated configuration management. Sensitive operational data has been excluded to maintain compliance with information-sharing and cybersecurity best practices.

This repository contains a curated collection of IEC 61850 Substation Configuration Description (SCD) files, generated and validated in controlled test laboratory environments.
The files reflect real-world substation automation and protection system configurations but do not represent live operational systems. They are provided to enable open research and experimentation within the power systems and cybersecurity domains.
Each file follows the IEC 61850 Substation Configuration Language (SCL) standard, which defines the XML-based structure for describing substations, devices, communication networks, and logical data models. To assist researchers, key metadata has been extracted and formatted as structured JSON summaries.
SCD Files – Complete substation configurations, including multiple IEDs, communication networks, and logical nodes.
JSON Metadata – Parsed metadata for each file, containing:

• Header details (version, revision, tool ID)
• Substation topology (if present)
• Communication parameters
• IED manufacturer and configuration info
• DataTypeTemplates summary (data model definitions)
  Purpose and Usage
  The dataset supports research in:
  Cybersecurity testing and resilience for substation communication networks
  Interoperability and standard compliance across vendor IEDs
  Machine learning and automation in configuration management
  Topology and semantic analysis of IEC 61850 data models
  Researchers and developers are encouraged to use this dataset for non-commercial academic and research purposes, especially in:
  Network intrusion detection and anomaly detection models
  Validation of secure communication architectures
  Training and testing of IEC 61850 configuration parsers
  License and Disclaimer
  This dataset is distributed under an open research license.
  You are free to use, modify, and share the files for research and educational purposes, provided that proper citation is given.
  Disclaimer:
  The files originate from simulated and test bed environments.
  No operational or confidential power system data is included.
  Use of this dataset is at your own discretion, and the maintainers assume no liability for derived work.