User data:
D	Training dataset
M	Number of users sharing the grid systems
$d^{\left(i\right)}$	Data of the $i^{th}$ user
n	Number of samples in each $d^{\left(i\right)}$
$y_j^{\left(i\right)}\left(t\right)$	$j^{th}$ forecasting feature for the $i^{th}$ user at time t
$x^{\left(i\right)}(t-p)$	Past load consumption with p time sample lag for the $i^{th}$ user
${\overline{F}}^{\left(i\right)}(t-p,t)$	Past information set for the $i^{th}$ user with the window between $(t-p)$ and t.
${\overline{y}}_I^{\left(i\right)}$	Time-invariant vector containing time-invariant features for the $i^{th}$ user
${\overline{y}}_V^{\left(i\right)}\left(t\right)$	Time-varying vector containing time-varying features for the $i^{th}$ user
${\overline{Y}}_V^{\left(i\right)}$	Time-varying set containing time-varying vectors for the $i^{th}$ user
Clustering:
$N_C$	Number of clusters
${\widehat{u}}_k\left({\overline{y}}_I^{\left(i\right)}\right)$	Membership of the $k^{th}$ cluster with respect to the time-invariant features of
	the $i^{th}$ users
${\widehat{v}}_k$	Centre of the $k^{th}$ cluster
$\overline{V}$	Set of cluster centres
$V_{pc}$	Fuzzy partition coefficient
${\mathcal{d}}_{ik}$	the $\overline{A}$ Norm distance between ${\overline{y}}_I^{\left(i\right)}$ and the $k^{th}$ cluster centre
$\overline{A}$	Positive definite $n\times n$ weight matrix
$m_f$	Weighting exponent of the fuzzy clustering algorithm
${\widehat{p}}_j$	Index vector indicating the time-invariant vectors in the $j^{th}$ cluster
$O_j$	Number of elements in the $j^{th}$ cluster
Deep learning:
$\mathrm{\Theta }$	Deep neural network model
W	Weights of the DNN model
${\overline{h}}_t$	Short-term state of the long short-term memory network
${\overline{c}}_t$	Long-term states of the LSTM
${\overline{f}}_t$	Forget gate of the LSTM
${\overline{i}}_t$	Input gate of the LSTM
${\tilde{c}}_t$	Input node of the LSTM
${\overline{o}}_t$	Output gate of the LSTM
${\mathrm{CNN}}_i$-Head	CNN head for the ${(C+1)}^{th}$ time-varying feature in the CNN framework