Electricity prices forecasting (EPF) has gained significant attention due to its relevance in various domains, such as optimizing energy management, electricity contract pricing, demand management, and informed decision-making. In this study, We have investigated the implementation of an EFP method in the local electricity market involving prosumers and suppliers, To achieve this, we propose a novel trend based approach that combines Bidirectional Long Short-Term Memory (BI-LSTM) for day-ahead electricity price forecasting with the k-means method for identifying off-peak and peak hours. To validate our methodology, we attempted to approximate the electricity prices of the local electricity market in Germany by introducing a variation factor that allowed us to consider additional costs added to the wholesale market price (such as taxes, supplier profits, etc.). we used real data from both "ENTSO_E transparency platform" and “EUROSTAT”, we also conducted extensive tests from 2019 to 2023. the model was trained using different subsets of data, and prediction time length. We also explored two clustering approaches with two k-mean configuration using a series of 24 and 12 hour, distinguishing between daytime and nighttime periods. This trend based approach enabled us to show that we can achieve a reasonable estimation of peak and off-peak hours,, with an average accuracy of 20 out of 24 correct clustered hours over a 5-year testing period, Despite the deviation observed between the actual and predicted values by BI-LSTM. However, we noticed that the increase in renewable energy sources, particularly solar and onshore wind, impacted the model's outcomes in 2020, especially in daytime, But in subsequent years such as 2022 and 2023, after retraining the model with data that accounts for the increasing influence of renewable energies, we observed improved accuracy and adaptability. The model became more capable of estimating Peak/Off-Peak Hours, even amidst the changing dynamics introduced by the intermittent nature of solar and onshore wind energy sources.