Dynamic topology, fast-changing channels and the time sensitivity of safety-related services present challenges to the status quo of resource allocation for cellular-underlaying vehicle-to-vehicle (V2V) communications. In this paper, we investigate a novel federated multi-agent deep reinforcement learning (FedMARL) approach for the decentralized joint optimization of channel selection and power control for V2V communication. The approach takes advantage of both deep reinforcement learning (DRL) and federated learning (FL), satisfying the reliability and delay requirements of V2V communication while maximizing the transmit rates of cellular links. Specifically, we elaborately construct individual V2V agent implement by the dueling double deep Q-network (D3QN), and design the reward function to train V2V agents collaboratively. As a result, each agent individually optimizes channel selection and power level based on its local observations, including the instantaneous channel state information (CSI) of corresponding V2V link, the instantaneous co-channel interference from the cellular link, the previous channels selections of nearby V2V pairs, and the queue backlog at the V2V transmitter. Another important aspect is that we incorporate FL to alleviate the training instability problem induced by cooperative multi-agent environment. The local DRL models of different V2V agents are federated periodically, addressing the limitations of partial observability on the entire network status for individual agent, and accelerating the training process of multi-agent learning. Validated via simulations, the proposed FedMARL scheme shows superiority to the baselines in terms of the cellular sum-rate and the V2V packet delivery rate.

Train delay prediction can improve the quality of train dispatching, which helps the dispatcher to estimate the running state of the train more accurately and make reasonable dispatching decision. The delay of one train is affected by many factors, such as passenger flow, fault, extreme weather, dispatching strategy. The departure time of one train is generally determined by dispatchers, which is limited by their strategy and knowledge. The existing train delay prediction methods cannot comprehensively consider the temporal and spatial dependence between the multiple trains and routes. In this paper, we don’t try to predict the specific delay time of one train, but predict the collective cumulative effect of train delay over a certain period, which is represented by the total number of arrival delays in one station. We propose a deep learning framework, train spatio-temporal graph convolutional network (TSTGCN), to predict the collective cumulative effect of train delay in one station for train dispatching and emergency plans. The proposed model is mainly composed of the recent, daily and weekly components. Each component contains two parts: spatio-temporal attention mechanism and spatio-temporal convolution, which can effectively capture spatio-temporal characteristics. The weighted fusion of the three components produces the final prediction result. The experiments on the train operation data from China Railway Passenger Ticket System demonstrate that TSTGCN clearly outperforms the existing advanced baselines in train delay prediction.

Train delay prediction is a key technology for intelligent train scheduling and passenger services. We propose a train delay prediction model that takes into account the asynchrony of train events, the dynamics of train operations, and the diversity of influencing factors. Firstly, we consider train operations as discrete sequences of train events and propose a train arrival neural temporal point process (TANTPP) framework focused on predicting train delays that explicitly models the asynchrony of train events. Secondly, we introduce a multi-source dynamic spatiotemporal embedding method for the feature encoder in the TANTPP framework, which enhances the capability to capture the features of train operation networks. Thirdly, to better capture the distribution of train events in the TANTPP framework, we utilize a log-normal mixture hybrid method to learn the probability density distribution of train arrival events. Finally, the experimental result on real-world datasets demonstrates that the TANTPP model outperforms current state-of-the-art models, reducing the MAE by 10.85%, the RMSE by 9.8%, the RRSE by 3.78% and the MAPE by 10.11% on average. To the best of our knowledge, this is the first study to utilize neural temporal point processes to enhance train delay prediction.

High-speed train delay prediction has always been one of the important research issues in the railway dispatching. Accurate and interpretable delay prediction can enable staff to implement preventive measures and scheduling decisions in advance, and guide relevant departments to cooperate in completing complex transportation tasks, so as to improve rail transit operations, service quality, and the efficiency of train operation. This paper proposes a new interpretable model based on graph community neural network and time-series fuzzy decision tree. This model can well capture the influence of spatiotemporal characteristics, train community structure and multi-factor in high-speed train station delay prediction. Besides, the time series fuzzy decision tree based on multi-objective optimization and reduced error pruning can mine potential decision rules to improve the model's interpretability, transparency, and high reliability. Finally, we prove that the prediction effect of the proposed model is superior than the other 7 state-of-the-art models and our model is interpretable.

Background: Multi-source cross-project defect prediction (MSCPDP) attempts to transfer defect knowledge learned from multiple source projects to the target project. MSCPDP has drawn increasing attention from academic and industry communities owing to its advantages compared with single-source cross-project defect prediction (SSCPDP). However, two main problems, which are how to effectively extract the transferable knowledge from each source dataset and how to measure the amount of knowledge transferred from each source dataset to the target dataset, seriously restrict the performance of existing MSCPDP models. Objective: In this paper, we propose a novel multi-source transfer weighted ensemble learning (MASTER) method for MSCPDP. Method: MASTER measures the weight of each source dataset based on feature importance and distribution difference and then extracts the transferable knowledge based on the proposed feature-weighted transfer learning algorithm. Experiments are performed on 30 software projects. We compare MASTER with the latest state-of-the-art MSCPDP methods with statistical test in terms of famous effort-unaware measures (i.e., PD, PF, AUC, and MCC) and two widely used effort-aware measures (P_opt 20% and IFA). Result: The experiment results show that: 1) MASTER can substantially improve the prediction performance compared with the baselines, e.g., an improvement of at least 49.1% in MCC, 48.1% in IFA; 2) MASTER significantly outperforms each baseline on most datasets in terms of AUC, MCC, P_opt 20% and IFA; 3) MSCPDP model significantly performs better than the mean case of SSCPDP model on most datasets and even outperforms the best case of SSCPDP on some datasets. Conclusion: It can be concluded that 1) it is very necessary to conduct MSCPDP, and 2) the proposed MASTER is a more promising alternative for MSCPDP.

Ispitivanje pouzdanosti softvera znači ispitivanje softvera kako bi se provjerilo da li udovoljava zahtjevima pouzdanosti i kako bi se procijenio njegov stupanj pouzdanosti. Statistički temeljeno ispitivanje pouzdanosti softvera...