Hybrid Renewable Energy System with Intelligent Decentralized Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Renewable energy plants, particularly those with photovoltaic (PV) systems, face challenges such as frequency deviations due to high penetration renewables and low system inertia, along with stochastic uncertainty in energy generation, which existing technologies struggle to address effectively.

Innovation Solution

A hybrid renewable energy source system combining a PV system with a battery energy storage system (BESS) and intelligent decentralized controllers, utilizing a stacked autoencoder for weather parameter extraction and an LSTM recurrent neural network for forecasting, integrated with advanced graphical processing units and deep neural networks, to operate as a unified single power generation unit with grid-forming capabilities and stability controls.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If high penetration of renewable energy sources is used, then environmental sustainability is improved, but frequency deviations and system stability deteriorate due to low system inertia

Engineering Contradiction:

Improvesystem stabilityVSAvoidfrequency deviations

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent combines PV systems with BESS to form a hybrid renewable energy source system that operates as a unified single power generation unit. This merging allows the system to simultaneously provide renewable energy and inertial support, addressing frequency deviations while maintaining high renewable penetration.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary action by using LSTM-based forecasting to predict PV generation in advance, and pre-charging the BESS to provide immediate inertial response when frequency deviations occur, rather than reacting after the deviation happens.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If PV systems are used to increase renewable energy generation, then energy production is improved, but stochastic uncertainty in energy generation worsens

Engineering Contradiction:

Improveenergy generationVSAvoidgeneration predictability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements feedback through LSTM recurrent neural networks that continuously analyze weather parameters and PV generation data, providing predictive feedback about future generation levels. This allows the system to anticipate and plan for stochastic variations in PV output.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary action by using LSTM-based forecasting to predict PV generation in advance, allowing the BESS to be pre-charged or pre-discharged to compensate for predicted generation shortfalls or surpluses before they occur.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If hybrid renewable energy source systems with advanced controllers are implemented, then grid stability and forecasting accuracy are improved, but system complexity increases

Engineering Contradiction:

Improvegrid stabilityVSAvoidsystem architecture

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the control system into intelligent decentralized controllers at the inverter/converter level and a robust coordinated controller at the system level. This segmentation allows complex control functions to be distributed and managed in modular fashion, improving grid stability while making the overall system complexity more manageable.

Inventive Principle:

Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The hybrid system enhances flexibility, stability, and efficiency, providing rigid high-inertia power generation and accurate forecasting, thereby mitigating stochastic uncertainty and improving grid stability and resilience.

Implementation Method 1

extracting (e.g., by the processor) weather parameters from a local weather dataset using a stacked autoencoder

Methodology Applied

Scientific EffectAutoencoder neural network processing:

Implementation Method 2

executing (e.g., by the processor) a long short-term memory (LSTM) recurrent neural network model on the weather parameters to conduct forecasting of PV generation of the PV system

Methodology Applied

Scientific EffectLSTM recurrent neural network processing:

Implementation Method 3

A hybrid renewable energy source system can include a renewable energy source system (e.g., a photovoltaic (PV) system)

Methodology Applied

Scientific EffectPhotovoltaic effect: Photovoltaic Effect

Implementation Method 4

an energy storage system (ESS) (e.g., a battery energy storage system (BESS))

Methodology Applied

Scientific EffectElectrical energy storage in battery: Battery (electricity)

Data Source

PatentUS11626731B1Hybrid renewable energy source systems

Publication Date: 2023.04.11 FLORIDA INTERNATIONAL UNIVERSITY

AI summary

Hybrid renewable energy source systems and methods are provided. A hybrid renewable energy source system can include a renewable energy source system (e.g., a photovoltaic (PV) system) in conjunction with an energy storage system (ESS), such as a battery energy storage system (BESS). The hybrid renewable energy source system can include at least one intelligent decentralized controller at the inverter/converter level, feeding a robust coordinated controller, thereby allowing the hybrid renewable energy source system to operate as a unified single power generation unit (PGU).