Autoencoder Virtual Meter Data for Smart Grid Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing smart meter systems in low-voltage networks face challenges in reliably and permanently accessing continuous time series of measurement data due to unstable mobile communication conditions, especially near high electrical fields.
Innovation Solution
A computer-implemented procedure using an autoencoder to translate time series data from one smart meter to another, creating a virtual time series to compensate for measurement failures and ensure seamless data availability, even under unstable transmission conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If smart meters are installed in low-voltage networks to collect measurement data, then measurement precision and data availability are improved, but reliability of data transmission deteriorates due to mobile communication disruptions near high electrical fields
Solution Approach 1:
The patent introduces an intermediary system consisting of a server and algorithm that mediates between smart meters and the central system. When a smart meter fails to transmit data, the server uses measurement data from neighboring smart meters and an algorithm to generate and supply substitute measurement data, thus ensuring continuous data availability despite transmission reliability issues
Solution Approach 2:
The patent creates a copy or substitute of the failed measurement data by using data from neighboring smart meters. The algorithm generates virtual measurement data that replicates what the failed smart meter would have transmitted, allowing the system to maintain complete data sets without requiring successful transmission from every individual smart meter
2Ease of operation
If smart meters transmit measurement data via mobile communication standards, then ease of operation and deployment are improved, but reliability deteriorates due to connection disruptions in high electrical field areas
Solution Approach 1:
The patent prepares for potential transmission failures in advance by implementing a backup mechanism. The server continuously receives data from multiple smart meters and stores it, so when a transmission failure occurs, the system can immediately supply substitute data from stored measurements or neighboring meters without interruption to the overall system operation
3Measurement precision
If comprehensive measurement data from all smart meters is required for intelligent grid control, then control precision is improved, but loss of information increases when individual smart meters fail to transmit
Solution Approach 1:
The patent merges measurement data from multiple sources to compensate for failures. When one smart meter fails, the system combines data from neighboring smart meters with algorithmic generation to create a complete data set, effectively merging multiple partial data sources into a comprehensive measurement picture that maintains control precision
Data Source
Figure 1
AI summary
A computer-implemented method for compensating for a measurement failure of a smart meter (2a-2d) in a low-voltage network (9), wherein time series of numerical measurement data are generated via a system (1) comprising the low-voltage network (9), at least a first smart meter (2a) which provides a time series of numerical measurement data of the first smart meter, a second smart meter (2b) which provides a time series of numerical measurement data of the second smart meter (2b1), as well as a processor (5) and a memory (4), wherein the processor (5) comprises an autoencoder (3) which is trained to translate time series of the first smart meter (2a) into time series of the second smart meter (2b), and wherein, in the event that the second smart meter (2b) has failed and does not provide a time series of numerical measurement data of the second smart meter (2b1), the time series of numerical measurement data of the second smart meter is generated. (2b1) in the memory (4) of the autoencoder (3),The time series of numerical measurement data from the first smart meter is replaced by a virtual time series of numerical measurement data from the second smart meter (2a1).