A Socio-Technical Approach to Load Forecasting for Super Smart Grids. A Multi-domain Attention-Based Neural Network

Super Smart Grids aim to provide large-scale, multi-zonal electricity access while dynamically balancing supply and demand. However, their implementation faces multidisciplinary challenges that range from ensuring grid stability to avoiding structural injustices in their design. Existing load forecasting approaches are unsuitable for Super Smart Grid planning or deployment due to an over-reliance on regional specificity, time-series data, and a lack of social understanding. This paper proposes to approach load forecasting as a hybrid problem composed of a mix between time-series power consumption and socioeconomic metrics, coupled with a novel deep learning algorithm that integrates Artificial Neural Networks and Luong's Attention Mechanism. First, two parallel Artificial Neural Networks are used to extract the main features of load demand behavior. Then, Luong's Attention Mechanism fuses both Artificial Neural Networks using an attention score function that dynamically selects the most relevant characteristics per sample to improve the generalization abilities of the model. The SHapley Additive exPlanations framework then interprets this algorithm to comprehend its load forecast decision-making thoroughly. Evaluated on 92 suburban zones in Australia, the proposed method achieves a Mean Absolute Percentage Error of 1.78%, outperforming Bidirectional Long-Short Term Memory, Long-Short Term Memory, and Recurrent Neural Network models. By merging high-resolution forecasting with socioeconomic awareness, this approach enhances demand and supply management, optimizes pricing strategies, and ensures equitable energy distribution—critical requirements for Super Smart Grids deployment. 2000 MSC: 68T10, 91D99, 37M10