${\mathcal{L}}_b$	Index of the number N of BSs.
${\mathcal{L}}_i$	Index of the number $K_i$ of information users.
${\mathcal{L}}_e$	Index of the number $K_e$ of active energy users (EUs).
${\mathcal{L}}_e^{\left[\mathrm{idle}\right]}$	Index of the number $K_e^{\left[\mathrm{idle}\right]}$ of idle EUs.
$P_n^{\left[\mathrm{Tx}\right]}$	Total transmit power at the n-th RRH.
$P_n^{\left[\mathrm{circ}\right]}$	Hardware circuit power consumption at the n-th RRH.
$P_{\mathrm{CU}}^{\left[\mathrm{circ}\right]}$	Hardware circuit power consumption at the CU.
$P_n^{\left[\mathrm{Tmax}\right]}$	Maximum transmit power allowance of the n-th RRH.
$P_{\mathrm{CU}}^{\left[\max \right]}$	Maximum power provision by the grid at the CU.
$\mathcal{T}$	Index of the number T of time slots.
$\mathcal{F}$	Index of the number F of frames within a time slot.
$\mathcal{K}$	Index of the number K of trials within a frame.
$B_n^{\left[\mathrm{ahead}\right]}$	Amount of energy purchased from the day-ahead
	market (Arm).
$B_n^{\left[\mathrm{spot}\right]}$	Amount of energy to be purchased from the spot-market.
$S_n$	Amount of excessive energy to be sold back to the grid.
$E_n$	Amount of renewable energy generation at the n-th RRH.
$B_n^{\left[\mathrm{total}\right]}\left(k\right)$	Total energy cost of the n-th RRH at the k-th trial.
${\mathcal{E}}^{\left[\mathrm{total}\right]}=\{{\mathcal{E}}^1,\cdots ,{\mathcal{E}}^J\}$	All energy packages (arms) offered by the grid in the
	day-ahead market.
${\mu }_{n,p}^{[k,f,t]}=\mathcal{R}\left(B_n^{\left[\mathrm{ahead}\right]}\left(k\right)\right)$	Reward associated with arm $B_n^{\left[\mathrm{ahead}\right]}$ at the k-th trial of the
	f-th frame at the t-th time slot.
${\mathcal{A}}_k^{\left[\mathrm{set}\right]}=\{B_1^{\left[\mathrm{ahead}\right]}\left(k\right),\cdots ,B_N^{\left[\mathrm{ahead}\right]}\left(k\right)\}$	N energy packages purchased a day ahead at the k-th trial
	(super arm).
$\mathcal{R}\left({\mathcal{A}}_k^{\left[\mathrm{set}\right]}\right)$	Reward for the super arm ${\mathcal{A}}_k^{\left[\mathrm{set}\right]}$ at the k-th trial.
${\mu }_{\mathbf{n}}^{[\mathbf{k},\mathbf{f},\mathbf{t}]}=({\mu }_{n,1}^{[k,f,t]},{\mu }_{n,2}^{[k,f,t]},\cdots ,{\mu }_{n,J}^{[k,f,t]})$	Reward vector for the n-th RRH
${\widehat{\mu }}_{\mathbf{n}}^{[\mathbf{f},\mathbf{t}]}=({\widehat{\mu }}_{n,1}^{[f,t]},{\widehat{\mu }}_{n,2}^{[f,t]},\cdots ,{\widehat{\mu }}_{n,J}^{[f,t]})$	Estimated mean reward vector
${\overline{\mu }}_{\mathbf{n}}^{[\mathbf{f},\mathbf{t}]}=({\overline{\mu }}_{n,1}^{[f,t]},{\overline{\mu }}_{n,2}^{[f,t]},\cdots ,{\overline{\mu }}_{n,J}^{[f,t]})$	Adjusted reward vector of individual arms
${\mathcal{R}}_t^{\left[\mathrm{acc}\right]}$	Accumulated reward at time slot t.
${\mathcal{Q}}_t$	Regret at time slot t.