No abstract

No abstract

Due to uneven space–time distribution of vehicles, Internet of Vehicles (IoV) has problems with load imbalance and low resource utilization of Base Stations (BSs) in the Coordinated Multi-Point (CoMP) communication scenario. This paper proposes a dynamic load balancing algorithm based on vehicle prediction. It is assumed that the number of vehicles arriving at the BSs obeys the segmented Poisson distribution to determine the current and predicted load statuses of BSs. First, analyze the load status of each BS and the location of users (vehicles). Then, screen out BSs whose load below the full load threshold as a switchable low-load cooperative cluster, which can convert interference signals into useful signals and reduce the interference between adjacent BSs. Finally, complete load balancing by redistributing the communication service of edge users through sharing channel information and user date among coordinated BSs. Because IoV is a dynamic network, the proposed algorithm runs dynamically in cycles. Simulation results show that the algorithm can perform balance the load of BSs well, the overload rates of BSs during the traffic off-peak period and peak period are reduced significantly, and the average information rate of users is greatly improved.

Conventional approaches for designing antennas are often time‐consuming and computationally expensive processes. In this letter, a time and resource‐efficient inverse design method for the multiparameter antenna is proposed which is capable of generating an effective dataset using the hybrid machine learning method. The proposed method filters the design variables and predicts the secondary variables based on the choice of primary design variables. The generated training dataset is used for the effective prediction of design variables based on multiple performance metrics. The proposed machine learning model utilized autoencoder for dimensionality reduction of multiple performance metrics and support vector regression is used for the prediction of design variables. To prove the effectiveness of the proposed model, a metasurface‐loaded low‐profile antenna is considered as a design example.