A 5G Beam Selection Machine Learning Algorithm for Unmanned Aerial Vehicle Applications

Table 1

Simulation parameters and notations.

Notations	Specification
Beta parameters; successful; unsuccessful	Expected reward probability to be 50%
Reward probabilities	{0.0, 0.1, 0.2,…, 0.9}
Device-system bandwidth	1 GHz
	10 slot medical machines
	Expected reward probability is 10%
Solver execution times		10000 steps
	ε-Greedy algorithm
	UCB1 algorithm
	Thompson sampling
	Bayesian UCB algorithm
1^st and 2^nd solver times	500 steps
Multiarmed bandit approach	A combined approach
Simulator tool	MATLAB