Resumen de Forecasting and Advanced Smart Grid Modeling to Enhance Electricity Infrastructure Resilience in Iraq
Morteza Rahman Mkhailef Al-Darraji
This dissertation addresses the pressing challenge of electricity supply and demand management in Iraq, a country whose energy sector is beset by infrastructural damage, insufficient investment, and increasing demand due to population and economic growth. The study is driven by the significant discrepancy between the rapidly growing energy demand, which has increased from 11,000 MW in 2007 to 16,000 MW in 2013, and reached approximately 30,000 MW recently. The inadequate production of electricity, exacerbated by successive wars and neglect, is a key focus. This study focuses on the Iraqi Electricity Power Grid (IEPG) and employs advanced modeling and artificial intelligence techniques to address the challenges arising from the recent surge in electricity demand. It examines forecasting energy demand and supply, assesses the network’s current performance, and proposes robust models for its enhancement.
The study uses an unprecedented dataset from 2019 to 2021 provided by the Iraqi Ministry of Electricity to predict electricity demand and supply over various horizons (24, 48, 72, and 168 hours ahead). This dataset, combined with various advanced forecasting models, such as linear regression, XGBoost, random forest, long short-term memory (LSTM), temporal convolutional networks (TCN), and multilayer perceptron (MLP), aims to achieve the most accurate predictions possible. The results show that linear regression is more effective in demand forecasting, while XGBoost excels in supply predictions. This comprehensive evaluation highlights the necessity of using a multifaceted approach to enhance forecasting accuracy in Iraq's complex energy landscape.
This work represents a pioneering effort in applying complex network (CN) concepts to model the IEPG network. Using two datasets, it offers a novel perspective on the intricate grid of generation power stations, ultra-high-voltage stations, high-voltage substations, and their interconnections via transmission lines. The employment of Gephi software and CN analytics enables sophisticated visualization and analysis of the network. The proposed models and scenarios, each with distinct focuses, such as rehabilitating idle stations, expanding the network, reinforcing transmission lines, and integrating solar power, are evaluated to discern optimal strategies for bolstering Iraq’s electricity infrastructure. Furthermore, the thesis explores the relationship between climate variables and energy demands by clustering 15 Iraqi cities according to temperature, power supply, and demand profiles using self-organizing maps (SOM), the K-means algorithm, and consensus clustering. This innovative approach highlights significant regional variations in energy profiles, suggesting tailored policy interventions and reinforcing the critical role of climatic factors in shaping energy requirements.
The findings have significant implications for energy policy and planning in Iraq, contributing to the broader discourse on sustainable energy management in post-conflict settings. The proposed forecasting models and CN-based analyses provide valuable tools for policymakers and engineers to address the challenges of energy supply, demand management, and infrastructure development, ultimately aiming to improve the quality of life of the Iraqi population through enhanced energy security and economic growth.
