DS--ElectricityPriceForcasting-Project

The future development of the world power industry and the application of power science research are focused on reforming power marketization. The main content of the reform is to compete in different levels of power generation, transmission, distribution, and sales. Electricity prices affect the operation of the entire electricity market and are extremely important to every market participant. Each participant trades in the electricity market based on the price of electricity. In the market competition, if the electricity price is accurately predicted in advance, it can be in a favorable position to obtain more benefits. However, due to the unique characteristics of electricity and the uncertainty of market and bidding strategies, electricity price forecasts have become more complex than power load forecasting. Predicting electricity prices is a prediction of future power prices based on predicted energy demand, temperature, sunlight, fuel cost, precipitation, and other relevant elements. Market Clearing Price (MCP) is the equilibrium price in an electrical market with no shortage or surplus. In contrast, forecasting the MCP is critical for maintenance scheduling, planning, bilateral contracting, resource reallocation, and budgeting. While there have been several contributions to energy price forecasting over the last two decades, it possibly lacks a comprehensive strategy for assessing new predictive algorithms. There are several different strategies for short-term, midterm, or long-term forecasting of the electricity MCP available today, but relatively little work has been done on one model working either for short-term and midterm, or midterm and long-term or for short-term and long-term forecasting of the electricity MCP. This study proposes long-term forecasting in terms of the time series of hourly prices by using an LSTM model based on the information in the previous values of the time series can be used to predict future values. Thus, the primary aim of the study is to predict the short-term, mid-term, and long-term forecasting values using the same model.