INTERPRETER -- Tool for non-technical losses detection
This article presents a tool for the detection of non-technical losses, which is being developed within the European INTERPRETER project. The tool employs a hybrid method based on feature detection from smart meter data and grid model analysis. This paper focuses on the grid model analysis, where voltage deviations between the grid model (digital twin) and real-world measurements at a low-voltage pilot site have been evaluated. Energy measurements from smart meters represent hourly mean power, while voltage measurements are instantaneous with uneven time intervals. Thus, measurements are not synchronous, which poses a major challenge for grid analysis. The proposed method focuses on daily mean, minimum, and maximum voltage and results show that deviations in daily minimum voltage are the most useful ones. A heatmap is developed, which helps the DSO expert to have a quick overview of all deviations of all meters in a certain time interval (1-day time step). A total of 6 locations have been identified where field inspections will be done.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
KUDO Interpreter Assist: Automated Real-time Support for Remote Interpretation
High-quality human interpretation requires linguistic and factual preparation as well as the ability to retrieve information in real-time. This situation becomes particularly relevant in the context of remote simultaneou…
Defining maximum acceptable latency of AI-enhanced CAI tools
Recent years have seen an increasing number of studies around the design of computer-assisted interpreting tools with integrated automatic speech processing and their use by trainees and professional interpreters. This p…
Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics
Tool-augmented LLMs are increasingly deployed as agents that interleave natural-language reasoning with executable Python actions, as in CodeAct-style frameworks. In deployment, these agents rely on runtime state that pe…
Electricity Theft Detection using Machine Learning
Non-technical losses (NTL) in electric power grids arise through electricity theft, broken electric meters or billing errors. They can harm the power supplier as well as the whole economy of a country through losses of u…
BIG-bench Machine LearningTD-Interpreter: Enhancing the Understanding of Timing Diagrams with Visual-Language Learning
We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a …
Synthetic Data Generation