Integration Advanced Artificial Intelligence (AI) Tools in Energy Management Systems in Enhancing Geographical Information and Decision Based System
| Author | Shahada, Aaed Khalil | |
|---|---|---|
| metadata.dc.contributor.department | University of Bahrain, College of Engineering, Department of Mechanical Engineering | |
| metadata.dc.date.accessioned | 2026-09-20T15:52:00Z | |
| Publication date | 2024 | |
| Degree level | Doctoral | |
| Abstract | Abstract: Effective energy management is crucial once related to constructing and licensing utilities, residential homes, and other civil structures. Due to the complexity of these interconnected and complicated processes, it has historically been challenging to appropriately manage these relationships. However, in recent years, artificial intelligence algorithms and models have been extensively utilized to help streamline and optimize energy management. To automate this process, a model using pretrained Deep Learning model is designed. Subsequent to training, validation and testing cycles were completed, 15 floorplans were inserted to the model and generated results in terms of decision-making. Manual calculations for identical floorplans were obtained by an expert engineer considering the length and the width for each floorplan using an AutoCAD file. The algorithm was designed to find out the areas in square meters of the outer surface of the floor plan for the opened surface such as windows or doors or for a solid surface such as block, concrete, steel, or wood. For attaining temperature deviation for buildings, hence, to calculate floor plan heat, real data temperature was downloaded which contain more than (1754 station) that send live temperature data each three hours of time. Heat gains were calculated for (15 floorplans) by using the data obtained earlier in the U-Values, outer surface areas and temperature deference’s. Results of the algorithm were verified by comparing the algorithm output and the manual calculation by the Engineering office. All the results obtained by the algorithm were very accurate when comparing them with the manual generation by the engineering offices making the process automated and eliminating human interference. The results indicated an error of (0.35%) for the actual dimension and (0.69%) in the heat gain calculation for the 15 floorplans once compared them with manual calculation. | |
| metadata.dc.identifier.other | Drupal node 3379 | |
| metadata.dc.identifier.other | https://digitalrepository.uob.edu.bh/en/dar/integration-advanced-artificial-intelligence-ai-tools-energy-management-systems-enhancing | |
| metadata.dc.identifier.uri | http://165.227.56.122/handle/123456789/7255 | |
| Language | en | |
| Link | https://digitalrepository.uob.edu.bh/en/_flysystem/fedora/2025-05/2025_integration_advanced_artificial_intelligence_ai_tools_in_energy_management_systems_in_enhancing_002.pdf | |
| Title | Integration Advanced Artificial Intelligence (AI) Tools in Energy Management Systems in Enhancing Geographical Information and Decision Based System | |
| Type | Doctoral Dissertation | |
| College | College of Engineering | |
| Department | Mechanical Engineering |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- node-3379-1-2025_integration_advanced_artificial_intelligence_ai_tools_in_energy_management_systems_in_enhancing_002.pdf
- Size:
- 11.31 MB
- Format:
- Adobe Portable Document Format