Modeling and Simulation of Solar Power generation forecasting

Implementation Plan:

Step 1: Initially,we will collect and load data from “DKASC Alice Springs dataset”.

Step 2: Then, we pre process the data using Cubature Kalman Filtering algorithm technique to identify outliers and noise.

Step 3: Next, we train the data using TL-based HJDA and CNN framework to identify hierarchically-ordered and spatial features.

Step 4: Next, we implement Hybrid fuzzy-based MI-LSTM-based Adaptive Neuro Fuzzy Inference System mechanism for dynamic forcasting.

Step 5: Next, we optimize the data using Bayesian Optimisation Technique to improve accuracy.

Step 6 : Finally, we plot performance for the following metrics:

6.1 : Mean Absolute Error (MAE)
6.2: Root Mean Squared Error (RMSE)
6.3: Mean Absolute Percentage Error (MAPE)
6.4: Coefficient of Determination (R2)
6.5: Computational time

Software Requirements:

1. Development Tool: MatlabR2024a
2. Operating System: Windows 10 (64-bit)

Dataset Link:

Link : https://dkasolarcentre.com.au/download?location=alice-springs

Note:

1) If the proposed plan does not fully align with your requirements, please provide all necessary details—including steps, parameters, models, and expected outcomes—in advance.

2) Kindly ensure that any missing configurations or specifications are clearly outlined in the plan before confirming.

3) If there’s no built-in solution for what the project needs, we can always turn to reference models, customize our own, different math models or write the code ourselves to fulfil the process.

4) If the plan satisfies your requirement, Please confirm with us.

5) Project based on Simulation only.

We perform with an Existing Approach Ref 1 – Title: Solar Power Forecasting Using Deep Learning Techniques