Abstract: Regulation at the grid side always reduces the impact of voltage sag events in a wider range, but the operation mode of voltage sag control at the grid side has seldom been deeply studied. Therefore, a high-quality power supply operation mode for the power grid line reconstruction considering the outage probability of the sensitive equipment is proposed. Based on the three characteristics of sag amplitudes, durations and interruption states of the small sample monitoring data in the uncertain intervals of the voltage sag of each sensitive equipment, the production interruption probability of the equipment is evaluated through the support vector machine (SVM) probability output, and the interruption times of the sensitive equipment are accurately assessed. With the goal of maximizing the benefits of the power grid companies and the sensitive users, considering the effects of every line reconstruction technology, the proportion of service charges is calculated by using the Nash product optimal solution of the game theory. The multi-objective optimization model of the voltage sag line reconstruction is established considering the constraints of the interruption frequency and the economic constraints. The non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ) is used to solve the model and obtain the optimal reconstruction scheme. Taking the IEEE 33-bus system as an example, considering the two scenarios of the all users participating and the some users not participating in the reconstruction scheme, the economy and practicability of the high-quality power supply service mode proposed in this paper are verified.