Sari95

Description This model applies Long Short-Term Memory (LSTM) architecture to predict energy consumption over a 48-hour period using historical energy usage and weather data from 2021 to 2023. Model Details Model Type: LSTM Data Period: 2021-2023 Variables Used: 1. LSTM with Energy consumption data and weather data 2. LSTM with Energy consumption data and two additional variables: 'LastgangMovingAverage' and 'LastgangFirstDifference' Features The model uses a sequence length of 192 (48 hours) to create input sequences for training and testing. Installation and Execution To run this model, you need Python along with the following libraries: - `pandas` - `numpy` - `matplotlib` - `scikit-learn` - `torch` - `gputil` - `psutil` - `torchsummary` Steps to Execute the Model: 1. Install Required Packages 3. Preprocess the Data According to the Specifications

Linear Regression Model for Energy Consumption Prediction Description This linear regression model predicts energy consumption based on meteorological data and historical energy usage from 2021 to 2023. It utilizes time series data from a transformer station to forecast future energy demands. It is built using the `statsmodels` library in Python and incorporates both time-based and weather-related variables to enhance prediction accuracy. Model Details - Model Type: Linear Regression - Data Period: 2021-2023 - Variables Used: - `Lastgang`: Energy consumption data - `Hour`: Hour of the day - `DayOfWeek`: Day of the week - `LastgangMovingAverage`: Moving average of energy consumption - `LastgangFirstDifference`: First difference of energy consumption Features The model splits the data into training and testing sets, with the last 192 data points (equivalent to 48 hours at 15-minute intervals) designated as the test dataset. It defines target variables (`Lastgang`) and explanatory variables including hourly and daily patterns as well as derived features from the consumption data. The dataset includes preprocessed features such as scaled energy consumption (`Lastgang`), and time-related features (`Hour`, `DayOfWeek`). Installation and Execution To run this model, you need Python along with the following libraries: - `pandas` - `numpy` - `matplotlib` - `statsmodels` - `sklearn` To execute the model: 1. Load your dataset into a pandas DataFrame. 2. Ensure that the data is formatted according to the specifications mentioned in the model details. 3. Run the script provided in the `PredictionLinear-Regression.ipynb` notebook.