Renewable Power Diagnostics via Virtual Model Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current monitoring systems for renewable energy systems, such as solar arrays, lack an inexpensive and reliable means to differentiate between environmental and system-related issues, making it difficult to quickly diagnose and address performance problems, leading to potential losses in energy generation and increased costs for service visits.
Innovation Solution
A method and system that utilize data servers, generation monitoring devices, and communication nodes to calculate and compare diagnostic variables, system coefficients, and energy generation across multiple renewable power systems, creating a Geographic Average to provide accurate and efficient diagnostics, reducing the need for costly sensors and enabling remote issue detection and remediation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring systems are used to track renewable energy system performance, then basic energy generation data can be collected, but the system cannot reliably differentiate between environmental factors and system-related issues, leading to inaccurate diagnostics
Solution Approach 1:
The patent creates a virtual model (digital twin) of the renewable energy system that replicates its behavior under various conditions. This virtual model is used to compare against actual performance data, enabling accurate differentiation between environmental factors and system issues without adding complex physical sensors. The copying approach allows diagnostic insights while maintaining simple physical monitoring infrastructure.
Solution Approach 2:
The patent introduces an AI-based intermediary layer that processes and interprets monitoring data. This intermediary analyzes patterns in energy generation data, weather information, and system parameters to distinguish between environmental variations and actual system problems. The intermediary translates raw data into actionable diagnostic information without requiring complex hardware modifications.
2Reliability
If complex sensors and monitoring devices are deployed to detect system issues, then diagnostic capability improves, but cost and system complexity increase significantly
Solution Approach 1:
Instead of deploying complex physical sensors, the patent creates a virtual replica of the system's expected performance. This digital model serves as a reference to compare against actual measurements, enabling reliable issue detection using simple, low-cost sensors. The copying approach substitutes computational complexity for physical complexity.
Solution Approach 2:
The patent replaces complex mechanical and physical sensing systems with an information-processing approach. AI algorithms analyze existing operational data and environmental information to detect system anomalies, substituting computational methods for physical sensing complexity. This reduces hardware requirements while improving diagnostic reliability.
3Loss of information
If extensive monitoring data is collected from multiple sources, then more information is available for diagnosis, but the ability to quickly identify specific issues is reduced due to data analysis complexity
Solution Approach 1:
The patent implements continuous feedback loops where the AI model constantly compares expected performance (from the virtual model) with actual performance data. This real-time feedback mechanism automatically identifies deviations and pinpoints specific issues without requiring manual analysis of extensive datasets. The feedback approach enables both complete information utilization and rapid diagnosis.
Solution Approach 2:
The system performs self-diagnosis through automated AI analysis that continuously monitors its own performance against the virtual model. The system automatically identifies issues, determines their severity, and suggests remediation actions without requiring external expert intervention. This self-service capability reduces both information loss and diagnosis time by enabling autonomous rapid assessment.
Data Source
AI summary
A method of measuring, monitoring and comparing power generation of at least two renewable power systems, comprising the steps of; providing at least two renewable power systems, at least one data server, at least one generation monitoring device in communication with at least one at premise renewable power system and at least one communication node in communication with at least one of renewable power system, generation monitoring device and data server, determining at least one diagnostic variable for each renewable power system and saving in the data server; determining at least one system coefficient for each renewable power system and saving in the data server; determining the energy generated by each renewable power system; wherein the data server determines comparative information based upon at least one of: background constant, diagnostic variable, system coefficient and energy generated to determine a comparative value of the renewable power system.