18570086. Control of an Electricity Supply Network simplified abstract (Siemens AKtiengesellschaft)
Contents
Control of an Electricity Supply Network
Organization Name
Inventor(s)
Mathias Duckheim of Erlangen (DE)
Michael Metzger of Markt Schwaben (DE)
Control of an Electricity Supply Network - A simplified explanation of the abstract
This abstract first appeared for US patent application 18570086 titled 'Control of an Electricity Supply Network
The abstract describes a method for reinforced learning of an artificial neural network in the context of controlling a supply network based on measured values.
- The neural network determines control values for the supply network by analyzing measured values.
- The method involves setting control values to prevent limit value violations of measurement variables without tripping protective devices.
- Measured values associated with the control values are acquired for training the neural network.
Potential Applications: - Energy distribution systems - Industrial automation - Smart grid technology
Problems Solved: - Efficient control of supply networks - Preventing disruptions in the network - Optimizing energy usage
Benefits: - Improved network stability - Enhanced energy efficiency - Reduced downtime and maintenance costs
Commercial Applications: Reinforced learning technology for supply network control can be utilized in various industries such as energy, manufacturing, and infrastructure management, leading to more reliable and cost-effective operations.
Questions about Reinforced Learning of Artificial Neural Networks in Supply Network Control: 1. How does reinforced learning improve the efficiency of supply network control? 2. What are the key advantages of using artificial neural networks in this context?
Frequently Updated Research: Stay updated on the latest advancements in reinforced learning algorithms and applications in supply network management to ensure optimal performance and reliability.
Original Abstract Submitted
Various embodiments of the teachings herein include a method for the reinforced learning of an artificial neural network. The neural network uses measured values associated with a supply network to determine a plurality of control values for controlling the supply network. The method may include: determining a control value so at least one limit value of a measurement variable of the supply network is violated in a time range, wherein the time range is determined in such a way that protective devices of the supply network do not trip; acquiring at least one measured value associated with the control value; and training the neural network using the calculated control value and the acquired associated measured value.
