Optimizing a Hybrid Microgrid with Machine Learning
Author Information
Author(s): Duan Fude, Eslami Mahdiyeh, Khajehzadeh Mohammad, Basem Ali, Jasim Dheyaa J., Palani Sivaprakasam
Hypothesis
Can a fuzzy multi-objective framework optimize a hybrid microgrid to minimize energy losses, voltage oscillations, and power costs?
Conclusion
The study found that using forecasted data improved the optimization of a hybrid microgrid, but also led to increased annual energy losses and costs compared to real data.
Supporting Evidence
- The optimization reduced annual energy losses from 666,052 kW to 423,227 kW.
- Voltage deviations decreased from 0.0147 p.u to 0.0129 p.u.
- The cost of power purchased from the hybrid microgrid was reduced to $340,630.
Takeaway
This study shows how to make a power grid that uses solar and wind energy work better by using smart computer programs to predict energy needs.
Methodology
The study used a fuzzy multi-objective improved Kepler optimization algorithm (MOIKOA) and a multilayer perceptron artificial neural network (MLP-ANN) for forecasting.
Limitations
The study did not account for all possible uncertainties in renewable energy generation.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website