A novel data-based decentralized control algorithm based on value iteration for nonlinear interconnected DC microgrids. The nonlinearity of the system is illustrated through the inclusion of constant power loads. The proposed algorithm addresses unknown nonlinear dynamics and ensures voltage stability by integrating advanced techniques from nonlinear system control. Specifically, it combines three key components: (1) adaptive dynamic programming for nonlinear optimal control, (2) a decentralized framework for interconnected systems, and (3) integral reinforcement learning to handle unknown dynamics. By employing function approximators, the decentralized algorithm reduces computational complexity, enabling rapid deployment. Simulations on a three-sub-system interconnected DC microgrid demonstrate the algorithm’s effectiveness. Using linear function approximation, the approach successfully derives a stabilizing control solution for the microgrid.

Connected and Automated Vehicles (CAVs) are a transformative technology for intelligent transportation systems in smart cities and industrial environments. However, the integration of CAVs into highway on-ramp merging scenarios, which are critical infrastructural bottlenecks, faces significant challenges due to unpredictable Human-Driven Vehicle (HDV) behaviors such as spontaneous lane changes and non-compliant merging, which can disrupt conventional traffic sequencing. To address this, we propose a novel vehicle sequencing framework combining Proximal Policy Optimization (PPO) reinforcement learning with a Transformer architecture to encode temporal traffic patterns. Our dual-path decision mechanism dynamically balances sequence stability and real-time efficiency while mitigating HDV-induced uncertainties. Extensive simulations demonstrate superior performance across varying CAV penetration rates and traffic demands: our approach reduces time loss by up to 73%, increases throughput by up to 21.2%, and improves average speed by up to 89.8% compared to traditional First-Come-First-Serve (FCFS) and Minimal Switchover (MS) policies. Remarkably, our framework maintains a 5-10% performance advantage even in HDV-dominated scenarios, validating its practical feasibility for near-term deployment. This work establishes new benchmark for mixed-traffic coordination systems and offers a scalable solution to enhance transportation network efficiency during the transition to fully automated mobility.

We study an all-pay contest where players with low abilities are filtered prior to the round of competing for prizes. These are often practiced due to limited resources or to enhance the competitiveness of the contest. We consider a setting where the designer admits a certain number of top players into the contest. The players admitted into the contest update their beliefs about their opponents based on the signal that their abilities are among the top. We find that their posterior beliefs, even with IID priors, are correlated and depend on players' private abilities, representing a unique feature of this game. We explicitly characterize the symmetric and unique Bayesian equilibrium strategy and compare it with a contest that admits all players. We also discuss a two-stage extension where players with top first-stage efforts can proceed to the second stage competing for prizes.

Platooning connected and autonomous vehicles (CAVs) provide significant benefits in terms of traffic efficiency and fuel economy. However, most existing platooning systems assume the availability of pre-determined plans, which is not feasible in real-time scenarios. In this paper, we address this issue in time-dependent networks by formulating a Markov decision process at each junction, aiming to minimize travel time and fuel consumption. Initially, we analyze coordinated platooning without routing to explore the cooperation among controllers on an identical path. We propose two novel approaches based on approximate dynamic programming, offering suboptimal control in the context of a stochastic finite horizon problem. The results demonstrate the superiority of the approximation in the policy space. Furthermore, we investigate platooning in a network setting, where speed profiles and routes are determined simultaneously. To simplify the problem, we decouple the action space by prioritizing routing decisions based on travel time estimation. We subsequently employ the aforementioned policy approximation to determine speed profiles, considering essential parameters such as travel times. Our simulation results in SUMO indicate that our method yields better performance than conventional approaches, leading to potential travel cost savings of up to 38%. Additionally, we evaluate the resilience of our approach in dynamically changing networks, affirming its ability to maintain efficient platooning operations.

Truck platooning is a technology that is expected to become widespread in the coming years. Apart from the numerous benefits that it brings, its potential effects on the overall traffic situation need to be studied further, especially at bottlenecks and ramps. Assuming we can control the platoons from the infrastructure, they can be used as controlled moving bottlenecks, actuating control actions on the rest of the traffic, and potentially improving the throughput of the whole system. In this work, we use a tandem queueing model with moving bottlenecks as a prediction model to calculate control actions for the platoons. We use platoon speeds and formations as control inputs, and design a control law for throughput improvement of a highway section with a stationary bottleneck. By postponing and shaping the inflow to the bottleneck, we are able to avoid capacity drop, which significantly reduces the total time spent of all vehicles. We derived the estimated improvement in throughput that is achieved by applying the proposed control law, and tested it in a simulation study, with multi-class cell transmission model with platoons used as the simulation model, finding that the median delay of all vehicles is reduced by 75.6% compared to the uncontrolled case. Notably, although they are slowed down while actuating control actions, platooned vehicles experience less delay compared to the uncontrolled case, since they avoid going through congestion at the bottleneck.

In this paper, we address the issue of congestion in future Unmanned Aerial Vehicle (UAVs) traffic system in uncertain weather. We treat the traffic of UAVs as fluid queues, and introduce models for traffic dynamics at three basic traffic components: single link, tandem link, and merge link. The impact of weather uncertainty is captured as fluctuation of the saturation rate of fluid queue discharge (capacity). The uncertainty is assumed to follow a continuous-time Markov process. We define the resilience of the UAV traffic system as the long-run stability of the traffic queues and the optimal throughput strategy under uncertainties. We derive the necessary and sufficient conditions for the stabilities of the traffic queues in the three basic traffic components. Both conditions can be easily verified in practice. The optimal throughput can be calculated via the stability conditions. Our results offer strong insight and tool for designing flows in the UAV traffic system that is resilient against weather uncertainty.

Vehicle platooning is a promising technology that can lead to significant fuel savings and emission reduction. However, the macroscopic impact of vehicle platoons on highway traffic is not yet well understood. In this article, we propose a new fluid queuing model to study the macroscopic interaction between randomly arriving vehicle platoons and the background traffic at highway bottlenecks. This model, viewed as a stochastic switched system, is analyzed for two practically relevant priority rules: proportional (or mixed) and segmented priority. We provide intuitive stability conditions, and obtain bounds on the long-run average length and variance of queues for both priority rules. We use these results to study how platoon-induced congestion varies with the fraction of platooned vehicles, and their characteristics such as intra-platoon spacing and arrival rate. Our analysis reveals a basic tradeoff between congestion induced by the randomness of platoon arrivals, and efficiency gain due to a tighter intra-platoon spacing. This naturally leads to conditions under which the proportional priority is preferred over segmented priority. Somewhat surprisingly, our analytical results are in agreement with the simulation results based on a more sophisticated two-class cell transmission model.