Python-Based Application Development for Electrical Base Price Estimation and Bidding Based on Consumption Data for Microgrids

In today's energy sector, determining unit electricity prices according to the amount of electricity is of critical importance. The supply-demand balance in the electricity market is among the factors that directly affect economic stability and sustainability. While the amount of energy plays an important role in terms of economic and environmental sustain ability, accurate prediction of changes in the amount of electricity and the reflection of these changes on prices is of great importance for both energy companies and consumers. This study aims to develop an application for estimating and quoting electricity prices, which is of critical importance. For this purpose, it is investigated the effectiveness of LSTM (Long Short-Term Memory) models, which can predict future values with high accuracy based on past information in time series data, in forecasting the amount of electricity and prices. Accordingly, the future amount of electricity was estimated by relating temperature and amount of electricity data using LSTM models. In addition, the base price for the next period was estimated by correlating the unit dollar-based base electricity price with dollar-based gold, annual inflation, USD/TRY, and Brent Oil parities. Finally, the amount of data from different companies was used to estimate the amount of data for the next period and offers were created by adding the profit rate to the base prices estimated according to this data. The application is supported by a user-friendly, uncomplicated interface, allowing users to make forecasts at certain time intervals. In addition, according to the data, profit rates are calculated for different companies, and price offers are presented. In this way, a tool that will be very important in making strategic decisions for energy companies and will help in making price decisions has been developed.