AI-ENABLED SMART GRID OPTIMIZATION WITH RENEWABLE ENERGY INTEGRATION FOR LOAD SHEDDING REDUCTION IN PAKISTAN’S POWER NETWORK

Abstract

Pakistan's electricity sector continues to experience persistent load shedding due to inefficient grid management, aging transmission infrastructure, increasing electricity demand, and limited integration of renewable energy resources. Recent advances in artificial intelligence (AI) offer significant opportunities to modernize power systems through intelligent grid optimization, predictive analytics, and automated energy management. This study examined the effect of AI-enabled smart grid optimization on load shedding reduction by investigating the mediating role of renewable energy integration and the moderating role of grid infrastructure readiness within Pakistan's power network. A quantitative, explanatory, and cross-sectional research design was employed. Primary data were collected from 392 electrical engineers, power system managers, renewable energy specialists, and utility professionals using a structured questionnaire based on validated measurement scales. The proposed conceptual framework was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings indicated that AI-enabled smart grid optimization significantly enhanced load shedding reduction by improving electricity forecasting, intelligent load balancing, predictive maintenance, and operational efficiency. AI-enabled smart grid optimization also exerted a significant positive effect on renewable energy integration, while renewable energy integration significantly reduced load shedding by improving electricity availability and grid stability. Furthermore, renewable energy integration partially mediated the relationship between AI-enabled smart grid optimization and load shedding reduction. The results also revealed that grid infrastructure readiness positively moderated the relationship between renewable energy integration and load shedding reduction, indicating that modern digital infrastructure strengthens the effectiveness of renewable energy deployment. Grounded in the Technology–Organization–Environment (TOE) Framework, the study contributes to the literature by providing an integrated model explaining how AI technologies, renewable energy integration, and infrastructure readiness collectively improve electricity reliability in developing economies. The findings offer practical implications for policymakers, electricity utilities, and renewable energy developers by emphasizing investments in AI-driven smart grids, digital infrastructure, and renewable energy systems to achieve a resilient, sustainable, and low-carbon power network in Pakistan