The basic Grey Wolf Optimizer (GWO) algorithm is easy to fall into local optimum, which leads to low search precision. In order to solve the problem, an Improved GWO (IGWO) was proposed. On the one hand, the position vector updating equation was dynamically adjusted by introducing weighting factor derived from coefficient vector of the GWO algorithm. On the other hand, the probabilistic disturbance strategy was adopted to increase the population diversity of the algorithm at later stage of iteration, thus the ability of the algorithm for jumping out of the local optimum was enhanced. The simulation experiments were carried out on multiple benchmark test functions. The experimental results show that, compared with the GWO algorithm, Hybrid GWO (HGWO) algorithm, Gravitational Search Agorithm (GSA) and Differential Evolution (DE) algorithm, the proposed IGWO can effectively get rid of local convergence and has obvious advantages in search precision, algorithm stability and convergence speed.