EE 461 Post 3: Feature Engineering

 

Week 8 Progress: Feature Engineering

Objectives For Week 8

  • Engineer new features for model improvement
  • Compare Techniques with original data

Tasks Completed

  • Feature creation: Five Key Engineered Features - Lagged Bill This is used for predicting the current or the next months billed power or consumed power by utilizing the previous months data. - 12 Month Rolling Average This uses the average of the last 12 months data to simply smooth out any irregularities. - System Efficiency Summarizes the efficiency by comparing the generation with consumption(billed). - Demand Growth Rate This represents the growth rate of the demand in percentage. In order words, how fast the demand changes. - Seasonal Encoding This represents the different weather patterns which in this case will be summer and winter(slightly colder period in Tonga) by using sine and cosine.

  • PCA on engineered features (dy/dx plots)

    Figure 1: PCA on the Feature Sets

  • CCA on engineered features (dy/dx plots) 

    Figure 2: CCA on Feature sets.

Comments

Post a Comment

Popular posts from this blog

EE 461 Final Post II: Load Forecasting for Tonga Power Limited

  Technical Results Data Visualizations Cleaned data of any outlier or ambiguity. Table 1 : A subset of the 222x4 dataset. No. Samples Dataset Variables GENERATED SENT OUT MONTH Tmp2m (C') 1 4399713 4321268 7 23.5701 2 4503448 4422164 8 23.8409 3 4386093 4291216 9 24.3952 4 4559317 4438567 10 24.3477 5 4332707 4218030 11 25.8833 6 4473349 4378796 12 25.9076 7 4739349 4611365 1 27.3127 8 4558099 4435805 2 27.6036 9 4737354 4629863 3 27.8743   Table 1 is a subset table...
Read more

EE 461 Post 7: Final Generation Scheduling

Image
Generation Scheduling Data Preparation Load Data before normalization: original_data = data; Get normalization parameters (calculated by MATLAB): original_mean = mean(original_data) original_std = std(original_data) Normalized predictions: normalized_preds = ARIMA_36_Months_Prediction{:,:} After selecting ARIMA as our best model to use, then a 36 months data is then transposed to a column vector. Using z-score to denormalize the normalized predicted data denormalized_preds = (normalized_preds * original_std) + original_mean denormalized_preds(:, [2:10]) = [] Preparing for generation scheduling by changing the predicted load forecast from kWh to MWh. Monthly Loads = Using MW for simplified load scheduling calculation. Calculating estimated normalized load demand power.   Monthly Loads = This is to calculate the estimated monthly load demand power. Seasonal Factors: Sunlight hours, wind speed, and wind factor were also incorporated since they wil...
Read more

EE 461 Post 1: Data Familiarization and Visualization

Image
  EE461-Special-Topics-AI-Project-Load-Forecasting- This project focuses on applying advanced machine learning and dimensionality reduction techniques to forecast electricity load demand for Tonga Power Limited (TPL). Accurate load forecasting is vital for: Ensuring grid stability Managing renewable integration (solar, wind, BESS) Improving energy efficiency Supporting future planning initiatives in Tonga Weeks 2–6 Progress: Data Familiarization and Visualization Objective Understand the historical electrical load data from Tonga Power Limited (TPL) Preprocess the data: handle missing values, normalize, and clean inconsistencies Visualize datasets to observe patterns, trends, and anomalies Begin dimensionality reduction (PCA) Tasks Completed Mapping generation sites  Figure 1: Map of generation sites This image is provided to show the pinpoints of the location of the 10 power stations. The imagery was built/made using the inbuilt "geoscatter" command and using 'topographi...
Read more