With the rapid global proliferation of electric vehicles (EVs), their integration as a significant load component within power systems increasingly influences the stable operation and planning of electrical grids. However, the high uncertainty and randomness inherent in EV users’ charging behaviors render accurate load forecasting a challenging task. In this context, the present study proposes a Particle Swarm Optimization (PSO)-enhanced Long Short-Term Memory (LSTM) network forecasting model. By combining the global search capability of the PSO algorithm with the advantages of LSTM networks in time-series modeling, a PSO-LSTM hybrid framework optimized for seasonal variations is developed. The results confirm that the PSO-LSTM model effectively captures seasonal load variations, providing a high-precision, adaptive solution for dynamic grid scheduling and charging infrastructure planning. This model supports the optimization of power resource allocation and the enhancement of energy storage efficiency. Specifically, during winter, the Mean Absolute Error (MAE) is 3.896, a reduction of 6.57% compared to the LSTM model and 10.13% compared to the Gated Recurrent Unit (GRU) model. During the winter–spring transition, the MAE is 3.806, which is 6.03% lower than that of the LSTM model and 12.81% lower than that of the GRU model. In the spring, the MAE is 3.910, showing a 2.71% improvement over the LSTM model and a 7.32% reduction compared to the GRU model.

The emergence of autonomous vehicles offers the potential to eliminate traditional traffic lanes, enabling vehicles to navigate freely in two-dimensional spaces. Unlike conventional traffic constrained by physical lanes, autonomous vehicles rely on real-time data exchange within platoons to adopt cooperative movement strategies, similar to synchronized flocks of birds. Motivated by this paradigm, this paper introduces an innovative traffic flow model based on the principles of particle swarm intelligence. In the proposed model, each vehicle within a platoon is treated as a particle contributing to the collective dynamics of the system. The motion of each vehicle is determined by the following two key factors: its local optimal velocity, influenced by the preceding vehicle, and its global optimal velocity, derived from the average of the optimal velocities of M vehicles within its observational range. To implement this framework, we develop a novel particle swarm optimization algorithm for autonomous vehicles and rigorously analyze its stability using linear system stability theory, as well as evaluate the system’s performance through four distinct indices inspired by traditional control theory. Numerical simulations are conducted to validate the theoretical assumptions of the model. The results demonstrate strong consistency between the proposed swarm intelligent model and the Bando model, providing evidence of its effectiveness. Additionally, the simulations reveal that the stability of the traffic flow system is primarily governed by the learning parameters $c_1$ and $c_2$, as well as the field of view parameter M. These findings underscore the potential of the swarm intelligent model to improve traffic flow system dynamics and contribute to the broader application of autonomous traffic systems management. In addition, it is worth noting that this paper explores the operational control of an AV platoon from a theoretical perspective, without fully considering passenger comfort, as well as “soft” instabilities (vehicles joining/leaving) and “hard” instabilities (technical failures/accidents). Future research will expand on these related aspects.