Increasing penetration of plug-in electric vehicles (PEVs) has a substantial impact on the operation of power distribution networks. Given the fast-growing load demands from PEVs and unmatched infrastructure investment in transformer and feeder capacity, the PEV charging is subjected to both spatially and temporally security constraints beyond which the network failure may occur. This paper proposes a game-theory-based distributed charging control method to coordinate large-scale PEVs without compromising the security of the distribution network. Under a noncooperative game framework, a price-driven charging model is designed to minimize the cost of each individual PEV customer while satisfying the network loading constraints. Then, a Newton-type method is developed to find a better Nash equilibrium of the game model at a superlinear convergence rate. Furthermore, an accelerated gradient method is proposed to tackle the subproblem for each user's best response. The update of the user's best response is implemented in a distributed way in order to protect user's privacy. The convergence rate of the proposed algorithms is rigorously proved. The effectiveness and efficiency of the proposed methods are tested on the IEEE 13-bus system.
Accurate forecasting of the hotel accommodation demands is extremely critical to the sustainable development of tourism-related industries. In view of the ever-increasing tourism data, this paper constructs a deep learning framework to handle the prediction problem in the hotel accommodation demands. Taking China’s Hainan province as an empirical example, the internet search index is used from August 2008 to May 2019 to forecast the overnight passenger flows for hotels accommodation in Hainan Province, China. Forecasting results indicate that compared to benchmark models, the constructed forecasting method can effectively simulate dynamic characteristics of the overnight passenger flows for the hotel accommodation and significantly improve the forecasting performance of the model. Forecasting results can provide necessary references for decision-making in tourism-related industries, and this forecasting framework can also be extended to other similar complex time series forecasting problems.
24 October 2023 in IEEE Transactions on Automatic Control
This article examines an online distributed optimization problem over an unbalanced digraph, in which a group of nodes in the network tries to collectively search for a minimizer of a time-varying global cost function while data are distributed among computing nodes. As the problem size becomes large, it will inevitably suffer from the communication bottleneck since each node that exchanges messages potentially transmits large amounts of information to its neighbors. To handle the issue, we design an online stochastic gradient algorithm with compressed communication when the knowledge of the gradient is available. We obtain the regret bounds for both nonconvex and convex cost functions, which can reach almost the same order of classic distributed optimization algorithms with exact communication. To resolve the scenario when the information of gradients is not accessible, a bandit version of the previous algorithm is then proposed. Explicit regret bounds of the bandit algorithm are also established for both nonconvex and convex cost functions. The result reveals that the performance of the bandit-feedback method is almost close to that of the gradient-feedback method. Several numerical experiments corroborate the main theoretical findings obtained in this article and exemplify a remarkable speedup when compared to existing distributed algorithms with exact communication.