Robust prediction of extreme motions during wind farm support vessel (WFSV) operation is an important safety concern that requires further extensive research as offshore wind energy industry sector widens. In particular, it is important to study the safety of operation in random sea conditions during WFSV docking against the wind tower, while workers are able to get on the tower. Docking is performed by thrusting vessel fender against wind tower (an alternative docking way by hinging is not studied here). In this paper, the finite element software AQWA has been used to analyze vessel response due to hydrodynamic wave loads, acting on a specific maintenance ship under actual sea conditions. Excessive roll may occur during certain sea conditions, especially in the beam sea, posing a risk to the crew transfer operation. The Bohai Sea is the area of diverse industrial activities such as offshore oil production, wave and wind power generation, etc. This paper advocates a novel method for estimating extreme roll statistics, based on Monte Carlo simulations (or measurements). The ACER (averaged conditional exceedance rate) method and its modification are presented in brief detail in Appendix. The proposed methodology provides an accurate extreme value prediction, utilizing available data efficiently. In this study the estimated return level values, obtained by ACER method, are compared with the corresponding return level values obtained by Gumbel method. Based on the overall performance of the proposed method, it is concluded that the ACER method can provide more robust and accurate prediction of the extreme vessel roll. The described approach may be well used at the vessel design stage, while defining optimal boat parameters would minimize potential roll.