Energy Consumption Prediction Concepts

Sandeep Marshall presents a project on predicting household energy consumption using sensor data and weather reports. The project aims to balance electricity supply and demand to prevent blackouts. Data from a Belgian building is analyzed, focusing on temperature and humidity. Feature engineering and PCA reduce data dimensions. Various regression models are tested, with Extra Trees Regressor performing best. The study concludes that time of day significantly affects energy use, and PCA effectively reduces feature dimensions without performance loss.

Why is predicting energy consumption important for maintaining grid stability?

• To reduce electricity bills

• To prevent blackouts and maintain frequency

• To increase the lifespan of appliances

• To improve weather forecasting

What is the primary source of data for predicting energy consumption in this project?

• Historical electricity bills

• Social media activity

• Sensor data from a building

• Manual surveys

What is the target variable in the dataset used for this project?

• Temperature

• Wind speed

• Humidity

• Total energy consumption

What does PCA help achieve in the context of this project?

• Reduce the dimensionality of the feature set

• Enhance the resolution of the data

• Increase the number of features

• Improve the accuracy of the sensors

How are temperature and humidity levels inside and outside the building correlated?

• Not correlated

• Positively correlated

• Identically correlated

• Negatively correlated

During which time sessions is energy consumption at its peak?

• 3 PM to 10 PM

• 11 AM and 6 PM

• 6 AM to 3 PM

• 10 PM to 6 AM

What is the significance of dividing the dataset into different time sessions?

• To improve sensor accuracy

• To enhance data security

• To identify patterns in energy consumption

• To reduce data size

Which model performed best in predicting energy consumption?

• Random Forest

• Support Vector Regression

• Lasso Regression

• Extra Trees Regressor

What was the effect of hyperparameter tuning on the model's performance?

• Significant improvement

• No significant effect

• Decreased performance

• Increased model complexity

What conclusion was drawn about the relationship between temperature, humidity, and energy consumption?

• They are the most important features

• They are irrelevant to the study

• They have little to no correlation with energy consumption

• They are highly correlated with energy consumption