Algorithm 1. The two-stage method developed for the advanced AI k-means clustering-integrated RBF-ANN over fog-cloud analytics in this study.

• Use k-means clustering on a training dataset collected onsite, $\Im ={\left\{X_k{,}^{}{d}_k\right\}}_{k=1}^Q$, to heuristically determine the center and spread parameters of each Gaussian basis function of the RBF-ANN of Equation (1). ↬ Require the values of the number of cluster centers c and a small constant of the tolerance ε to be specified. ↬ Randomly initialize the c cluster centers, where c has been specified. l ← 0 ↬ Repeat     Compute the c cluster centers using Equation (8).     Update the hard c-partition space U using Equation (9).   l ← l + 1   Until    ||U(l+1) − U(l)|| is less than the specified small tolerance ε. ↬ Return the resulting c cluster centers with the hard c-partition space for $\Im$. ↬ Center the Gaussian basis functions of Equation (1) at the returned c cluster centers. ↬ Compute the spread parameters of the centered Gaussian basis functions of Equation (1) using Equation (7).

• Use Equation (6) involving the SVD technique applied to the training dataset collected onsite, $\Im$, to train the RBF-ANN of Equation (1) characterized by k-means clustering. ↬ Train Equation (1), whose Gaussian basis functions were heuristically determined by k-means clustering applied to the training data points collected onsite using Equation (6) in the ThingSpeakTM cloud to get W. The well-trained RBF-ANN is then autonomously and automatically deployed onsite on the developed smart autonomous power meter prototype as edge analytics via the Internet for online load identification in DSM. In this study, the RBF-ANN facilitated with k-means clustering is developed over fog-cloud analytics.