Picked from the software, topic, and level of “Class MPPT Solar Panel Fuzzy-Neural #6: Comparison of Efficiency, Tracking Time & Oscillation of All MPPT Methods”.
At most one email a week. Unfollow anytime with one click.
Transcript
The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.
Show transcript
Introduction
Here is the final result, Fuzzy-Neural MPPT combining Anvis guessing with Fuzzy refinement achieving an efficiency of about 99.8 percent, while PNO, INGKON, and standard Fuzzy are stuck around 89 percent. In 300 random shadow patterns, the difference is almost 15 percent. Let's start. Hello, welcome to the final episode of the Fuzzy-Neural Solar Panel MPPT series. We already have all the components. Panel Model, Partial Shading, Classic MPPT, Fuzzy, and Anvis. Today we are combining Anvis and Fuzzy into Fuzzy-Neural MPPT, then comparing all four methods thoroughly.
Step 1: Fuzzy-Neural Controller
Create a Fuzzy underscore neural dot pay file. The Anvis load function reads parameters saved in episode 5. The Fuzzy-Neural controller works in two stages. When irradiance changes, for example from the irradiance sensor of each module, Anvis immediately guesses the global peak voltage and jumps to that operating point. Then, the Fuzzy logic from episode 4 refines locally until it reaches the peak without oscillation.
Step 2: Efficiency, Tracking & Oscillation
Create a comparison dot pay file. All four methods are run on the same scenario. We measure energy efficiency, tracking time which is the number of steps until power reaches 99% of the final power, and oscillation in steady-state conditions. Run Fuzzy-Neural achieves an efficiency of about 99.8%, while the other three methods are around 89.1%. PNO and INGKON reach the final point the fastest, about three steps, but that final point is wrong under shading. Fuzzy and Fuzzy-Neural are almost without oscillation.
Step 3: Test 300 Random Shadow Patterns
One scenario is not enough, so we test 300 new random shadow patterns that Anvis has never seen. Each method is given 60 steps starting from 75 volts. PNO, INGKON, and Fuzzy on average only get about 84% of the global maximum power, and only about 57% of cases reach 99%. Fuzzy-Neural on average is almost 99%, and about 90% of cases reach the global peak.
Step 4: Comparison Graph
Let's take a look at the graph. Left graph. During shadowing, the red fuzzy-neural curve jumps to the dashed maximum global line, while other methods remain below it. Right graph, average on 300 random patterns, with the green fuzzy-neural bar significantly higher. Its weakness is that this method requires an irradiance sensor and training data that matches the panel being used. And that concludes this series, we have built a complete research on solar panel MPPT, including 1 diode model, partial shedding and bypass diode, PNO and incremental conductance, fuzzy logic, ANVIS with hybrid learning, up to fuzzy-neural MPPT and comprehensive comparison.
Done!
For further research, try estimating irradiance without a sensor, adding temperature as an input, testing on a larger area, or comparing with PSO MPPT. Thank you for following this series. Currently working on a thesis, dissertation, or research in the field of solar energy and renewable energy? Cerdas Inovasi Digital helps with the implementation of solar panel simulations, from 1 diode model, partial shedding, MPPT perturb and observe and incremental conductance, fuzzy logic, up to ANVIS, and also opens Python programming courses for electrical engineering. Want to master the entire series, from solar panel models to comparisons of all MPPT methods? All 6 episodes, complete with PDF step-by-step guides and source code, are available to premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with the 12-month package, or pay once Rp999.000 for lifetime access. Want just one class? Buy a single class with lifetime access. Subscribe now at the premium page cerdasinovasidigital.com Contact our WhatsApp or visit cerdasinovasidigital.com Thank you for watching, see you in the next episode.
Ask the class material
Type a question or keyword; we find the part of this episode that explains it and jump the video there.
My notes
Notes are saved with the current video time and are only visible to you.
Questions & answers
Stuck on a step? Ask here; the instructor and other learners can answer.
No questions yet.
Your instructor
Cerdas Inovasi Digital Team
Software developers, BIM & 3D engineers, and AI practitioners
53 video classes1,290 episodes
We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.
