Garuda - Garba Rujukan Digital

Adaptive Ensemble Learning for Enhancing Building Energy Consumption Prediction: Insights from COVID-19 Pandemic Energy Consumption Dynamics Handre Kertha Utama, Putu; Leksono, Edi; Nashirul Haq, Irsyad; Indrapraja, Rachmadi; Mahesa Nanda, Rezky; Friansa, Koko; Fauzi Iskandar, Reza; Pradipta, Justin
Journal of Engineering and Technological Sciences Vol. 57 No. 2 (2025): Vol. 57 No. 2 (2025): April
Publisher : Directorate for Research and Community Services, Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/j.eng.technol.sci.2025.57.2.2

Buildings account for approximately 40% of the total global energy consumption. Therefore, accurate prediction of building energy consumption is necessary to optimize resource allocation and promote sustainable energy usage. A key challenge in developing building energy consumption models is their adaptability to abrupt changes in consumption patterns owing to extraordinary events, such as the COVID-19 pandemic. Therefore, a two-layer ensemble-learning (EL) model incorporating sliding windows as input features is proposed. The model is a two-layer stacking EL consisting of two base learning methods: (1) support vector regression (SVR), and (2) random forest (RF). Temperature and humidity are included to account for the influence of weather conditions on energy consumption. The proposed model is deployed to forecast building energy consumption both before (November 2019) and during (May – October 2020) the COVID-19 pandemic and is compared with a single machine learning model. The results demonstrate that the EL model outperforms the SVR and RF methods, providing excellent prediction accuracy even during the pandemic when significant changes in energy consumption patterns occurred. The findings also highlight the effectiveness of sliding windows as input features for improving model adaptability. Additionally, the analysis reveals that temperature is more prominent than humidity for improving prediction accuracy.

Comparasion of HVAC Energy Consumption Prediction in an Academic Building using LSTM and DNN Hadi Christian; Koko Friansa; Justin Pradipta; Irsyad Nashirul Haq; Edi Leksono
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 11 No 1 (2024): Jurnal Ecotipe, April 2024
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v11i1.4488

Energy consumption information is a collection of information obtained from datasets that is useful for making decisions for energy conservation. In this paper, we proposed a modern approach based on LSTM and DNN. While many researchers have employed these methods for predicting energy consumption, this paper seeks to compare their efficacy to determine which is superior. The comparative analysis in question employs accuracy metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2) values. Furthermore, the accuracy metric outcomes indicate that the LSTM method surpasses the DNN approach in terms of the R-squared (R2) value, with respective scores of 0.931 and 0.782. Meanwhile, for other accuracy metrics, the DNN method outperforms LSTM. Nevertheless, the performance of the two proposed methods is excellent, as evidenced by the R-squared (R2) value exceeding 0.75, which aligns with modeling standards observed in numerous research studies.

Performance Optimization of Battery Balancing System Based on Multiwinding Transformer and Single Inductor with Fuzzy Logic Control Method Yusiran, Yusiran; Leksono, Edi; Haq, Irsyad Nashirul; Ayumurti, Andini Jinggan
Journal of Applied Science and Advanced Engineering Vol. 3 No. 2 (2025): JASAE: September 2025
Publisher : Master Program in Mechanical Engineering, Gunadarma University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59097/jasae.v3i2.60

In this study, a modular battery balancing topology based on a single inductor and multi-winding transformer is proposed. In particular, the voltage equalization topology based on this modular balancer consists of cell-level equalization based on a multi-winding transformer and module-level equalization based on a single inductor. A control algorithm based on fuzzy logic (FLC) is applied to the module-level balancer with the difference between the module voltage and the module average voltage being used as the input variable and the duty cycle as the output variable. Meanwhile, the cell-level equalization utilizes a fixed duty cycle (FDC) control mechanism. The balancing process between cell and module level is done alternately so that this control method can be used on non-uniform transformers. The balancing model and FLC design was created in Matlab/Simulink 2021a and experiments using 4 cells LG HG2 18560 3000 mAh battery were carried out to verify the performance of the balancing system. The experimental results show that the FLC method can save the balancing time between modules by 31.26% compared to the FDC method. Furthermore, the proposed control system is proven to optimize the energy transfer which can reach zero voltage gap (ZVG) below 5 mV with a relatively high efficiency around 86.95%..

Audit Energi Menggunakan Intensitas Konsumsi Energi untuk Konservasi Energi di Gedung Kampus Faniama, Virara; Hanadi; Christian, Hadi; Tomoyahu, Syafril; Pradipta, Justin; Nashirul Haq, Irsyad; Leksono, Edi
Jurnal Otomasi Kontrol dan Instrumentasi Vol 16 No 1 (2024): Jurnal Otomasi Kontrol dan Instrumentasi
Publisher : Pusat Teknologi Instrumentasi dan Otomasi (PTIO) - Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/joki.2024.16.1.6

Energy auditing is an essential step in optimizing energy use in commercial buildings. This research explores the application of energy auditing with the Energy Consumption Intensity method to improve energy efficiency in campus buildings. Considering the changes in occupancy and activity patterns in the university environment can provide a comprehensive insight into the associated energy consumption patterns. The audit analyzed the building's energy consumption and identified potential energy savings to improve energy efficiency. Energy data was collected and analyzed to evaluate the building's energy performance. Recommended energy conservation measures include updating the lighting system, optimizing the cooling system, and improving the efficiency of equipment use. This research recommends that campus building managers adopt sustainable practices in energy management, which can lead to reduced operational costs and lower environmental impacts. Thus, the energy audit approach with the IKE method is a relevant and effective strategy for achieving energy conservation goals in the university environment. Based on the analysis, the latest IKE for Labtek V is 38.01 (2021), while the IKE for Labtek VI is 16.75 (2021), showing inefficiency of energy use in both buildings inefficient.

A A Low-Cost MQTT-Based IoT Framework for Real-Time Monitoring of Battery Energy Storage Systems Ari Hasan Asyari; Irsyad Nashirul Haq; Rina Mardiati
JITCE (Journal of Information Technology and Computer Engineering) Vol. 10 No. 1 (2026): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Electricity consumption continues to increase in line with population growth and the rising demand for energy. However, this trend is inversely proportional to the availability of electrical energy resources, particularly those supporting clean energy. One of the renewable energy sources is solar power generation, which utilizes solar radiation. In practice, solar power systems cannot operate optimally under cloudy conditions or during nighttime. Therefore, a Battery Energy Storage System (BESS) plays a crucial role in providing a reliable and continuous energy supply over a certain period. In addition, BESS requires proper monitoring to assess its operational condition. This study presents the development of an IoT-based real-time monitoring system for BESS using the MQTT communication protocol. An ESP32 module is employed as the internet gateway (publisher), while a cloud-based compute engine functions as the subscriber. The proposed system enables real-time monitoring of key parameters, including voltage, current, power, temperature, as well as battery charging and discharging states, which are stored and visualized in a cloud database. The results demonstrate that the developed prototype is capable of publishing and subscribing energy storage data effectively, with a sensor accuracy error of approximately 1%. The overall system achieves an average response time of 1.41 seconds, indicating reliable real-time performance.

A A Low-Cost MQTT-Based IoT Framework for Real-Time Monitoring of Battery Energy Storage Systems Ari Hasan Asyari; Irsyad Nashirul Haq; Rina Mardiati
JITCE (Journal of Information Technology and Computer Engineering) Vol. 10 No. 1 (2026): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jitce.10.1.8-22.2026

Electricity consumption continues to increase in line with population growth and the rising demand for energy. However, this trend is inversely proportional to the availability of electrical energy resources, particularly those supporting clean energy. One of the renewable energy sources is solar power generation, which utilizes solar radiation. In practice, solar power systems cannot operate optimally under cloudy conditions or during nighttime. Therefore, a Battery Energy Storage System (BESS) plays a crucial role in providing a reliable and continuous energy supply over a certain period. In addition, BESS requires proper monitoring to assess its operational condition. This study presents the development of an IoT-based real-time monitoring system for BESS using the MQTT communication protocol. An ESP32 module is employed as the internet gateway (publisher), while a cloud-based compute engine functions as the subscriber. The proposed system enables real-time monitoring of key parameters, including voltage, current, power, temperature, as well as battery charging and discharging states, which are stored and visualized in a cloud database. The results demonstrate that the developed prototype is capable of publishing and subscribing energy storage data effectively, with a sensor accuracy error of approximately 1%. The overall system achieves an average response time of 1.41 seconds, indicating reliable real-time performance.

Title

Found 16 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 16 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 16 Documents
Search