Research On Dynamic Controller Placment Problem In Software Defined Vehicular Networks

With the continuous expansion of network architecture and communication range,energy costs in data center networks have increased dramatically.In a software-defined vehicle network（SDVN）,as the number of vehicles increases,the communication delay between vehicles and vehicle to the controllers rise sharply.This requires more controllers to provide communication service to minimize the latency.More controllers lead to high energy costs.Therefore,the number of controllers and their placement,the so-called controller placement problem（CPP）,should be addressed.The appropriate placement of controllers can decrease the energy cost,enabling green communication in SDVN.Although CPP has been studied for static networks,it has not been effectively solved in highly dynamic and complex networks.First,our proposed Minimum Controller Selection mechAnism（MOSA）can reduce the number of controllers and guarantee the coverage of the area.Besides,an Improved Multiobjective Artificial Bee Colony algorithm（IMABC）is proposed based on the original artificial bee colony algorithm.The IMABC can judge which controller should be switched on for data transmission based on real-time traffic flow.A route computation mechanism is proposed to evaluate the performance of our CPP scheme.Secondly,we design an intelligent UAV-aided controller placement scheme for SDVN.The vehicle positions are predicted by Bi-directional Long Short-Term Memory（Bi-LSTM）.A Dynamic Controller and UAV Placement mEchanism（DCUPE）is proposed to place controllers and relaying UAV with the predicted position.We also design an Improved aDaptive Artificial Bee Colony algorithm for solving the Traveling Salesman Problem（IDABC-TSP）which uses the moving UAV to collect traffic information while Bi-LSTM making the prediction.The above-mentioned controller placment scheme is evaluated based on the real geographic topology.The experimental results confirm that compared with other existing CPP schemes,our schemes can achieve a higher data packet transmission rate,which greatly reduces energy consumption while ensuring superior communication effects.