Algorithm 4 Identifying an estimate of acceptable uncertainty

Require: Data ${\mathcal{D}}^{N(t)}=\{y_{\omega }^{N(t)},y_a^{N(t)}\},\forall t\in \{1,\dots ,T\}$, number of Monte Carlo samples L, maximum acceptable uncertainty $E_{max}$, threshold for minimum number of sequential estimates with acceptable deviation $n_{min}$. 1:$n\leftarrow 0$ 2:for $t\in \{1,\dots ,T\}$ do 3:    Obtain an estimate $\widehat{j}=j(\widehat{x})$ by solving the optimization problem (22) using the data ${\mathcal{D}}^{N(t)}$ and Algorithm 1. 4:    Obtain ${\widehat{j}}^{(t)}$ from (66). 5:    Compute the covariance matrix $P_x$ according to (57). 6:    Compute ${\mu }_z$ and $P_z$ according to the Monte Carlo method (62)–(65). 7:    Compute $\mathrm{SEQAD}(t^{\prime }),\forall t^{\prime }\in (t-n_{min}+1,t)$ as in (67). 8:    if ${\mu }_z+2\sigma <E_{max}$ AND $max\{\mathrm{SEQAD}(t^{\prime })\}<E_{max}$ then 9:        return ${\widehat{j}}^{(t)}$. 10:    end if 11:end for