A Comparative Analysis of LSTM and Bi-LSTM for Forecasting Energy Consumption in Albania

Paper Details

Authors: Lamani L.; Leka E.; Aliti A.; Harizaj M.; Kreka K.

DOI: 10.18421/TEM151-06

Journal: TEM Journal

Year: 2026

Publisher: UIKTEN - Association for Information Communication Technology Education and Science

Document Type: Article

Open Access: All Open Access; Gold Open Access

Cited by: 0

Abstract

– Energy consumption forecasting is becoming an integral component of AI systems for energy management, policy planning, and the optimization of distribution systems – especially in regions with growing demand, such as Albania. This study offers a comparative analysis of two deep learning architectures: Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) for the purpose of forecasting energy consumption. Both models were trained to predict energy consumption using hourly consumption data from 2010 to 2025. The results indicate that the Bi-LSTM model surpasses the LSTM model, attaining marginally greater accuracy owing to its capacity to capture both antecedent and subsequent temporal dependencies. These models provide critical insights for enhancing energy planning strategies and can substantially optimize electricity management at both the household and national scales. © 2026 Luis Lamani et al.; published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 License.

Keywords

Bi-LSTM; energy consumption forecasting; energy exchange; LSTM; neural network; python

Read Paper Back to Search