Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Knowledge Engineering and Data Science

Exploring LSTM-based Attention Mechanisms with PSO and Grid Search under Different Normalization Techniques for Energy demands Time Series Forecasting Pranolo, Andri; Zhou, Xiaofeng; Mao, Yingchi; Pratolo, Bambang Widi; Wibawa, Aji Prasetya; Utama, Agung Bella Putra; Ba, Abdoul Fatakhou; Muhammad, Abdullahi Uwaisu
Knowledge Engineering and Data Science Vol 7, No 1 (2024)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um018v7i12024p1-12

Abstract

Advanced analytical approaches are required to accurately forecast the energy sector's rising complexity and volume of time series data.  This research aims to forecast the energy demand utilizing sophisticated Long Short-Term Memory (LSTM) configurations with Attention mechanisms (Att), Grid search, and Particle Swarm Optimization (PSO). In addition, the study also examines the influence of Min-Max and Z-Score normalization approaches in the preprocessing stage on the accuracy performances of the baselines and the proposed models. PSO and Grid Search techniques are used to select the best hyperparameters for LSTM models, while the attention mechanism selects the important input for the LSTM. The research compares the performance of baselines (LSTM, Grid-search-LSTM, and PSO-LSTM) and proposes models (Att-LSTM, Att-Grid-search-LSTM, and Att-PSO-LSTM) based on MAPE, RMSE, and R2 metrics into two scenarios normalization: Min-Max, and Z-Score. The results show that all models with Min-Max normalization have better MAPE, RMSE, and R2 than those with Z-Score. The best model performance is shown in Att-PSO-LSTM MAPE 3.1135, RMSE 0.0551, and R2 0.9233, followed by Att-Grid-search-LSTM, Att-LSTM, PSO-LSTM, Grid-search-LSTM, and LSTM. These findings emphasize the effectiveness of attention mechanisms in improving model predictions and the influence of normalization methods on model performance. This study's novel approach provides valuable insights into time series forecasting in energy demands.
Co-Authors Adam Al Hakim Agustiningrum, Tessana Aisyah, Shifak Ajar Pradika Ananta Tur Aji Prasetya Wibawa Al Hakim, Adam Ali Zuraina Alsulami, Naif Daifullah Amaliah R. Nggilu Amaliawati, Shafira Ananda, Anisa Rizky Andri Pranolo Ani Susanti Ani Susanti Arifiana Tri Wulandari Arifiana Tri Wulandari Arina Athiyallah Arlischa Ardinengtyas Armin, Diah Safithri Aulia Mufida Izzatul Mahfiana Ayudia Fauziah Azwar Abbas Azzahra Fayoris Hafiza Ba, Abdoul Fatakhou Bao, Dat Baskoro, Cahyo Beliarita, Liza Bella Nusa Bahari Cahyo Baskoro Candradewi Wahyu Anggraeni Cindi Martina Marbun Devi Martha Astuti Dewi Musfika Santi Dewi, Nuria Punjastala Dhei Klaudiya Efit Eriani Eka Dhermawati Eko Purwanti Elmawaddah Ersya Ema Puspitasari Eriani, Efit Estrella T Arroyo Fahmi Fahmi Fajriati Astuti Fatimah Setiani Garini, Selza Azzahra Gendroyono , Gendroyono Hadijah Hadijah Hafiza, Azzahra Fayoris Hana Amri Solikhati Hardika, Bunga Hatmanto, Endro Dwi Hatmanto, Endro Dwi Iin Inawati Iin Inawati Ikmi Nur Oktavianti Ilahude, Fidya Felinda Indriani Indriani Indriani Indriani Khusnawati, Khusnawati Konipa, Monica Gita Kusdaryono, Junianto Bayu Leky, Abdul Majid S Mao, Yingchi Marilou D. Tino Miyarti Miyarti Muh Mahrup Zainuddin Sabri Muhammad, Abdullahi Uwaisu Nafi’ah, Aisyah Umi Nguyen, Tran Thi Hoang Nikmah Sistia Eka Putri Nur Fatimah Nurul Amalia Zahruni Nurul Fadilah Okta Widia Sari Palaguna, Suhendri Pamastu Narpaduita Pasha, Nariza Ayu Pegiawan Basopi Pratita Pawestri Radzuan, Noor Raha Mohd Rika Junianti Rika Junianti Rina Febriani Sarie Rinda Nuningtyas Risalatul Hanifah Hasibuan Rizkiya, Ani Rofiqoh Rofiqoh Rondiyah Rondiyah Sakti , Muhammad Muzakki Arya Sari, Dhian Marita Sari, Mariska Intan Sari, Yulnada Soviyah Soviyah Sri Sudarsi Sri Sudarsi Surono Surono Surono Sutri Windiarti Tio Moon Lofti Tri Rina Budiwati Utama, Agung Bella Putra Utama, Hasna Aisyah Iman Wahyu Rahmadhani Mardalis Widyaningtyas, Yulisa Yulnada Sari Yuyun Nailufer Zhou, Xiaofeng Zidni Ma’ruf Zuraina Ali Zuraina, Ali