The particle swarm optimization (PSO) algorithm, in which individuals collaborate with their interacted neighbors like bird flocking to search for the optima, has been successfully applied in a wide range of fields pertaining to searching and convergence. Here we employ the scale-free network to represent the inter-individual interactions in the population, named SF-PSO. In contrast to the traditional PSO with fully-connected topology or regular topology, the scale-free topology used in SF-PSO incorporates the diversity of individuals in searching and information dissemination ability, leading to a quite different optimization process. Systematic results with respect to several standard test functions demonstrate that SF-PSO gives rise to a better balance between the convergence speed and the optimum quality, accounting for its much better performance than that of the traditional PSO algorithms. We further explore the dynamical searching process microscopically, finding that the cooperation of hub nodes and non-hub nodes play a crucial role in optimizing the convergence process. Our work may have implications in computational intelligence and complex networks.

Particle swarm optimization (PSO) is a nature-inspired algorithm that has shown outstanding performance in solving many realistic problems. In the original PSO and most of its variants all particles are treated equally, overlooking the impact of structural heterogeneity on individual behavior. Here we employ complex networks to represent the population structure of swarms and propose a selectively-informed PSO (SIPSO), in which the particles choose different learning strategies based on their connections: a densely-connected hub particle gets full information from all of its neighbors while a non-hub particle with few connections can only follow a single yet best-performed neighbor. Extensive numerical experiments on widely-used benchmark functions show that our SIPSO algorithm remarkably outperforms the PSO and its existing variants in success rate, solution quality and convergence speed. We also explore the evolution process from a microscopic point of view, leading to the discovery of different roles that the particles play in optimization. The hub particles guide the optimization process towards correct directions while the non-hub particles maintain the necessary population diversity, resulting in the optimum overall performance of SIPSO. These findings deepen our understanding of swarm intelligence and may shed light on the underlying mechanism of information exchange in natural swarm and flocking behaviors.

As revolutionary technologies that can actively change the communication link signal, intelligent reflecting surface (IRS) and unmanned aerial vehicle (UAV) have emerged as reliable, economical and convenient wireless communication solutions for a variety of practical scenarios. Therefore, this paper focuses on an IRS empowered UAV downlink communication network, where the dynamic UAV establishes a cascade link via IRS to provide signal enhancement services for multiple users. Considering constraints of transmit power, flight speed and area at the UAV and the reflecting constraints at the IRS, the block coordinate descent (BCD) method based on resource allocation, reflecting design and trajectory optimization is adopted to maximize the sum-rate of all users. The proposed problem is converted by using quadratic transformation and Lagrangian dual transformation. Then applying for the approximate linear method and Iterative Rank Minimization (IRM) to optimize the transmit power of UAV and phase shift of IRS respectively. Since additional reflection propagation paths by IRS, the complexity of the channel model makes the trajectory design difficult. To tackle this problem, this paper proposes a UAV trajectory optimization method based on enhanced reinforcement learning with the fixed initial location and destination. In the end, the convergence of the proposed scheme is effectively verified by simulations. Moreover, abundant simulation comparisons between the proposed scheme and other benchmark schemes demonstrate the validity and high performance gains of the proposed algorithm.

Particle swarm optimization (PSO) aims at finding the optimum point in a high-dimension solution space by simulating the swarming and flocking behaviors in nature. Recent empirical studies of reconstructing the hidden interaction networks in flocking birds and schooling fish found that individuals play different roles in group decision making. An outstanding question is whether the performance of PSO can be improved by incorporating these empirical findings. Here, we systematically explore the impact of the heterogeneity of interaction network and individual’s learning strategies to find that the corresponding network-based algorithm, network-based heterogeneous particle swarm optimization (NHPSO), significantly outperforms other PSO based and non-PSO-based comparative algorithms on our experiments with 18 test functions. Our further analysis of the information exchange among the particles reveals that learning from low-degree particles in the middle period of evolution is crucial for the swarm to achieve the global optimum. These results offer a new framework to improve the performance of swarm optimization and demonstrate the applicability of network science in designing optimization algorithms. Finally, the universality of NHPSO is demonstrated on an emerging application, the unmanned aerial vehicle communication coverage.

This paper is concerned with the efficient movement control of multiple drone-cells for communication coverage. Although many works have been developed to cope with this problem, few of them have investigated the three-dimensional (3-D) continuous movement control of multiple drone-cells. In this paper, a problem of 3-D continuous movement control of multiple drone-cells is formulated with an objective of maximizing the energy-efficient communication coverage of drone-cell networks, while preserving the network connectivity. To mitigate this challenging problem, an energy-efficiency and continuous-movement-control algorithm (E $^2$ CMC), which is based on an emerging deep reinforcement learning (DRL) method, is proposed. In E $^2$ CMC, an energy efficiency reward function considering the energy consumption, the {sum of quality-of-service (QoS) requirements of users} as well as the coverage fairness is first designed. Next, E $^2$ CMC learns to adjust drone-cells' locations continuously by interacting with an environment in a sequence of observations, actions, and rewards. Further, E $^2$ CMC will reduce the reward drastically as long as the networks are disconnected. Simulation results verify the superiority of the proposed learning algorithm on deploying multiple drone-cells to provide the communication coverage.