Jehad A. H. Hammad
Al-Quds Open University

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Forecasting electrical power consumption using ARIMA method based on kWh of sold energy Gianika Roman Sosa; Moh. Zainul Falah; Dika Fikri L; Aji Prasetya Wibawa; Anik Nur Handayani; Jehad A. H. Hammad
Science in Information Technology Letters Vol 2, No 1: May 2021
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/sitech.v2i1.637

Abstract

Customer demand for electrical energy continues to increase, so electrical energy infrastructure must be developed to fulfill it. In order to generate and distribute electrical energy cost-effectively, it is crucial to estimate electrical energy consumption reasonably in advance. In addition, it is necessary to ensure that customer demands can be met and that there is no shortage of electricity supply. This study aims to determine the estimated long-term electricity use with a historical Energy Sold (T1) database in kW accumulated over several periods from 2008 to 2017. The ARIMA method with the Seasonal-ARIMA (SARIMA) pattern is used in forecasting analysis. The ARIMA method was chosen because it is considered appropriate for forecasting linear and univariate time-series data. The results of this study indicate that the MAPE (%) error rate is relatively low, with a result of 7,966, but the R-Square reaches a value of -0.024 due to the lack of observational data.
An AI-driven framework for learning analytics and operational optimization in technology and vocational education: Bridging industrial engineering and informatics Heri Nurdiyanto; Leonel Hernandes; Jehad A. H. Hammad; Aktansi Kindiasari
Jurnal Pendidikan Vokasi Vol. 15 No. 3 (2025)
Publisher : ADGVI & Graduate School of Universitas Negeri Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jpv.v15i3.95617

Abstract

This study proposes an artificial intelligence (AI)-driven framework that integrates learning analytics with operational optimization to address the fragmentation between educational data and operational decision-making in technology and vocational education. Although vocational institutions increasingly adopt digital technologies, learning-related data are often analyzed separately from operational processes such as scheduling, task allocation, resource utilization, and process efficiency, despite their interdependence in teaching factory and practical learning environments. Drawing on perspectives from industrial engineering and informatics, the proposed framework integrates machine learning for analyzing learner performance and competency development with optimization techniques for supporting operational decision-making. The framework was designed to be adaptable across different vocational education contexts and was empirically evaluated in a technology-oriented vocational setting to assess its feasibility. The evaluation demonstrates the feasibility of integrating learner-related and operational information within a unified decision-support environment, enabling competency and performance information to inform decisions concerning practical tasks, scheduling, and resource allocation. Rather than positioning AI solely as a predictive or instructional tool, the framework conceptualizes it as a mechanism for connecting pedagogical and operational dimensions of vocational learning. This study contributes an interdisciplinary and system-oriented perspective on AI adoption in vocational education, providing a foundation for more integrated, context-sensitive, and data-informed decision-making in teaching factory and practical learning environments.