Electricity generation is moving away from fossil fuels and toward renewable energy, which requires streamlined power distribution. Strategic modifications are essential to enhance the smart grid’s stability, safety, and efficiency. One such modification is replacing traditional multi-wire conductors with sector-shaped multi-wire cables, which utilize the available space more effectively. To facilitate this transition, we explore contactless measurements using fluxgate sensors and machine learning (ML) to predict symmetrical current flow from magnetic field data. Mathematical formulations, such as the Biot-Savart Law, are inadequate for sector-shaped multi-wire cables. On the other hand, employing noninvasive sensors and ML reduces unwanted power losses in current flow monitoring. Among the 18 ML regressors tested, K-Nearest Neighbor predicted the amplitude with an error of 0.015 A when tested on augmented data. The results of the experiments show that magnetic field reconstruction using ML is a worthy contender in our efforts to improve the smart power grid.