Chlorophyll a concentration is an important index of eutrophication, and simulation of chlorophyll a concentration is of great significance to the monitoring and control of lake eutrophication. The aim of the study is to explore a new method to build an effective model to simulate chlorophyll a concentration in Donghu Lake. Based on measured data of water quality indexes, ABC-SVM model for simulating chlorophyll a concentration is built by using Artificial Bee Colony (ABC) algorithm to improve Support Vector Machine (SVM). Moreover, accuracy, sensitivity and universality of the model are analysed. Modeling results show that the ABC-SVM model has high accuracy and good simulation effect, R2 and RMSE in testing process is 0.96 and 10.40 μg/L, ABC optimization increases R2 by 0.04 and reduces RMSE by 4.12 μg/L compared with SVM model. Sensitivity analysis results demonstrate chlorophyll a concentration is more sensitive to TP than other water quality indexes. In addition, universality analysis results reveal that ABC-SVM model has good universality and can be used to simulate the chlorophyll a concentration of Donghu Lake at different times. Overall, we have built an efficient simulation model, which provides a new idea and method for chlorophyll a concentration simulation.