Energy Storage Capacity Estimation via Modular Data Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurate battery capacity estimation in lithium-ion batteries is challenging due to irreversible physical and chemical changes, affecting their performance over time, which is critical for reliable energy storage management.
Innovation Solution
A system and method for managing energy storage system capacity by generating energy data, extracting it using a data storage module, aggregating data, estimating capacity through a capacity estimation module, and implementing corrective actions based on calculated inputs and outputs, including using machine learning platforms like Amazon SageMaker for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional battery capacity estimation methods are used, then the system structure remains simple, but the measurement precision of battery capacity deteriorates due to irreversible physical and chemical changes
Solution Approach 1:
The system segments the capacity estimation task into multiple components: data collection from multiple nodes, data aggregation processing, capacity estimation module with machine learning, and corrective action implementation. This segmentation allows each module to specialize in specific functions, improving overall measurement precision while managing complexity through modular architecture
Solution Approach 2:
The patent introduces intermediary components including data aggregation modules that process raw data before estimation, and machine learning models that act as intermediaries between raw measurements and capacity predictions. These intermediaries refine the estimation process, significantly improving measurement precision despite adding system complexity
2Reliability
If no corrective actions are implemented, then the device complexity remains low, but the reliability of energy storage management deteriorates due to battery degradation
Solution Approach 1:
The system implements continuous feedback loops where capacity estimation results inform corrective actions, which in turn affect future capacity measurements. The machine learning models are continuously refined based on observed deviations, creating a self-improving system that enhances reliability while the automated feedback mechanisms manage the complexity of implementing corrective actions
Solution Approach 2:
The system performs preliminary capacity estimation and identifies potential issues before they lead to failures. By proactively implementing corrective actions based on predicted capacity degradation, the system prevents reliability issues before they occur, managing complexity through preventive rather than reactive approaches
3Productivity
If detailed capacity monitoring and corrective actions are implemented, then the productivity of battery management improves, but the loss of time for data processing and analysis increases
Solution Approach 1:
The system implements periodic capacity estimation and corrective actions at optimized intervals rather than continuous monitoring. The machine learning models predict when re-estimation is necessary, allowing the system to maintain high productivity by acting only when needed, thus minimizing time loss while preserving management efficiency
Solution Approach 2:
The system performs preliminary data aggregation and preprocessing in the background before capacity estimation is needed. By preparing data structures and aggregating measurements in advance, the system reduces the time required for actual capacity calculation and corrective action implementation, maintaining high productivity while minimizing processing time loss
Data Source
AI summary
Systems and methods are disclosed for managing capacity of an energy storage system. In one implementation, a system includes at least one node configured to generate energy data; at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to: extract, using a data storage module, the energy data from the at least one node; ingest, using a data aggregation module, first data from the data storage module; estimate, using a capacity estimation module, a capacity of the at least one node by: importing second data from the data aggregation module; determining at least one input and at least one output configured to modulate a capacity determination; and determining the capacity of the at least one node based on the calculated at least one input and at least one output; and implement a corrective action for the energy storage system based on the estimated capacity.