Long-term policy guidance for sustainable energy transition in Nigeria: A deep learning-based peak load forecasting with econo-environmental scenario analysis

Nigeria faces critical challenges in managing electricity demand peaks and mitigating greenhouse gas emissions, underscoring the urgent need for a rapid, sustainable energy transition. This study offers long-term policy guidance aligned with Sustainable Development Goal 7 (SDG-7) to address electricity shortfalls and reduce carbon emissions. By integrating deep learning models, Strengths-Weaknesses-Opportunities-Threats (SWOT) analysis, the Analytical Hierarchy Process (AHP), and the Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (Fuzzy-TOPSIS), this research evaluates Nigeria's energy transition from economic, environmental, and policy perspectives. Scenario mapping explores four energy mixes: Scenario 1 (27.5 % renewable energy [RE], 72.5 % non-renewable energy [NRE]), Scenario 2 (35 % RE, 65 % NRE), Scenario 3 (50 % RE, 50 % NRE), and Scenario 4 (100 % RE). The proposed hybrid deep learning model demonstrates superior predictive accuracy, achieving an R2 of 0.99, 0.80, and 0.24 across 1-h, 1-day, and 1-week forecasts, respectively. Scenario 2 achieves a total annual cost (TAC) of US$106 million, a significant 51.5 % reduction compared to the most capital-intensive Scenario 4, which has a TAC of US$219 million. Scenario 2 also produces 27.9m kgCO2 emissions, representing a 0.79 % reduction from Scenario 1's highest emissions of 28.1m kgCO2. Furthermore, Scenario 2 offers a cost of energy of 0.0029 kWhUS$−1, reflecting a 12.1 % improvement in economic efficiency over Scenario 1. Subsequently, the integrated SWOT-AHP approach identified strategies to enhance Nigeria's RE transition across geopolitical zones. Thus, the proposed long-term policy guidance framework can serve as a tool to accelerate the transition to a sustainable energy future while addressing its energy shortfall.