Neural Network PV Array Topology Reconfiguration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Photovoltaic (PV) energy production is significantly reduced by partial shading and faulty modules in PV array systems, as existing connection topologies fail to optimize power output under varying conditions.

Innovation Solution

A cyber-physical system utilizing a multi-layer perceptron neural network to reconfigure the connection topology of PV arrays between series-parallel, total cross tied, honeycomb, and bridge link configurations based on measured irradiance profiles, optimizing electrical connections to maximize power output.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a fixed connection topology (series-parallel) is used in PV arrays, then the system structure is simple and easy to manufacture, but the power output is significantly reduced under partial shading conditions

Engineering Contradiction:

Improvepower outputVSAvoidconnection topology complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent implements dynamic reconfiguration of PV array connections by switching between series-parallel, total cross tied, honeycomb, and bridge link topologies based on real-time irradiance conditions. This dynamic adaptation allows the system to optimize power output under varying shading conditions while maintaining manageable complexity through automated control.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the electrical connection parameters (topology configuration) based on measured irradiance profiles. By detecting shading patterns and switching between predefined connection topologies, the system adapts its electrical parameters to maximize power extraction under different environmental conditions.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If the connection topology is reconfigured to optimize power output under partial shading, then the energy production increases, but the system complexity and control requirements increase

Engineering Contradiction:

Improveenergy productionVSAvoidtopology reconfiguration control

Core Design Contradiction:

ProductivityVSExtent of automation

Solution Approach 1:

The system uses irradiance sensors to detect shading patterns and feeds this information to a controller that automatically selects the optimal connection topology. This feedback mechanism enables automated adaptation to changing environmental conditions, maximizing energy production without requiring manual intervention while managing system complexity through intelligent control algorithms.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The PV array system performs self-optimization by automatically detecting its own operating conditions through irradiance measurement and autonomously selecting the appropriate connection topology. This self-service capability allows the system to adapt to partial shading conditions without external control, improving energy production while minimizing the need for complex external monitoring and control infrastructure.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11616471B2Systems and methods for connection topology optimization in photovoltaic arrays using neural networks

Publication Date: 2023.03.28 THE ARIZONA BOARD OF REGENTS ON BEHALF OF THE UNIV OF ARIZONA

AI summary

Various embodiments for a connection topology reconfiguration technique for photovoltaic (PV) arrays to maximize power output under partial shading and fault conditions using neural networks are disclosed herein.