The computation of alternative paths for point-to-point shortest paths on time-dependent road networks has numerous practical applications. Despite its importance, there has been a lack of research in the literature addressing alternative paths in time-dependent road networks. In this paper, we present an innovative algorithm designed to generate high-quality alternative paths in a time-dependent context. Our approach leverages an existing time-dependent bidirectional A* algorithm. We first introduce an efficient method for gathering candidate alternative paths by identifying intersections between forward and backward searches. We then present a filtering approach for these candidate paths to ensure that only the highest quality alternatives are returned to the user. Simulation results confirm that our approach achieves good latency performance, returns optimal time-dependent paths, and provides high-quality alternative paths.

Searching for directions is one of the most used features of map applications. This paper shares our vision on how Direction Services will change, with LLM-based chat assistants rapidly becoming an integral part of the underlying path search mechanism. We anticipate an influx of more complex, conversational route planning sessions, where users colloquially describe route-related preferences as if they were talking to their personal chauffeur. We envision future systems able to support asks like "avoid the East River tunnel", "take the bridge", or "find me a scenic route around the lake, oh and by the way, I'm driving the EV today". At present, popular map search engines fail in even simple, yet very natural preferences, such as 'take me from A to B via road C'. The reason is mainly twofold, inadequate query understanding and lack of mechanisms in routing to satisfy this type of preferences. The here proposed solution is a novel treatment of routing, one which casts it into an end-to-end 2-layer relevance framework. The framework is capable of performing query understanding for route queries with complex preferences and intents. It treats routes as richly annotated documents and the routing engine, in addition to performing optimization, acts (1) as a retriever of route documents that match the user intent and (2) as a ranker that ranks route candidates not just by a simple time-distance cost model, but by inferring the importance of many variables, some derived from explicitly stated preferences and others identified as relevant through data-driven methodology.

Map search engines compute the estimated time of arrival (ETA) from location A to location B by first performing local routing-engine optimization over a network of road segments. Once the optimal route candidates are identified their ETA is reevaluated with global post-routing ETA (PostETA) models capable of correcting multiple accumulated local biases. Sequence models have emerged as the state of the art post-routing ETA predictors, however, they are usually applied as regressors fitting a single ETA value. Here we demonstrate that a route can have very different travel times for different drivers even when measured at approximately the same starting time. Fitting a distribution then, instead of a single value, and returning to users both an expectation over ETA together with a confidence range is more accurate and informative. We propose a novel PostETA system including a set of sequence-to-sequence attention models capable of fitting the route ETA distribution. On a data set of over a hundred thousand user trips we demonstrate that the system achieves accuracy comparable to that of regression models, providing in addition an accurate estimate for the variance of the ETA prediction.

Randomly perturbing networks during the training process is a commonly used approach to improving generalization performance. In this paper, we present a theoretical study of one particular way of random perturbation, which corresponds to injecting artificial noise to the training data. We provide a precise asymptotic characterization of the training and generalization errors of such randomly perturbed learning problems on a random feature model. Our analysis shows that Gaussian noise injection in the training process is equivalent to introducing a weighted ridge regularization, when the number of noise injections tends to infinity. The explicit form of the regularization is also given. Numerical results corroborate our asymptotic predictions, showing that they are accurate even in moderate problem dimensions. Our theoretical predictions are based on a new correlated Gaussian equivalence conjecture that generalizes recent results in the study of random feature models.

In this paper, we develop a robust three dimensional tomographic imaging framework to estimate the ionospheric electron density using ground-based total electron content (TEC) measurements from GPS receivers. In order to increase the sampling rate of the domain, we incorporate into the tomographic measurements the TEC readings observed from low-angle satellites that fall outside of the target ionospheric domain. We discount the proportion of the TEC measurements that originate outside of the target domain using the simulation-based NeQuick2 model as reference. We also employ a diffusion kernel regularization function to robustify the reconstruction against errors in the NeQuick2 model. Finally, we demonstrate through simulations that our framework delivers superior reconstruction of the ionospheric electron density compared to existing schemes. We also demonstrate the applicability of our approach on real TEC measurements.

Conventional cloud radio access networks assume single cloud processing and treat inter-cloud interference as background noise. This paper considers the downlink of a multi-cloud radio access network (CRAN) where each cloud is connected to several base-stations (BS) through limited-capacity wireline backhaul links. The set of BSs connected to each cloud, called cluster, serves a set of pre-known mobile users (MUs). The performance of the system becomes therefore a function of both inter-cloud and intra-cloud interference, as well as the compression schemes of the limited capacity backhaul links. The paper assumes independent compression scheme and imperfect channel state information (CSI) where the CSI errors belong to an ellipsoidal bounded region. The problem of interest becomes the one of minimizing the network total transmit power subject to BS power and quality of service constraints, as well as backhaul capacity and CSI error constraints. The paper suggests solving the problem using the alternating direction method of multipliers (ADMM). One of the highlight of the paper is that the proposed ADMM-based algorithm can be implemented in a distributed fashion across the multi-cloud network by allowing a limited amount of information exchange between the coupled clouds. Simulation results show that the proposed distributed algorithm provides a similar performance to the centralized algorithm in a reasonable number of iterations.

Recent studies on cloud-radio access networks (CRANs) assume the availability of a single processor (cloud) capable of managing the entire network performance; inter-cloud interference is treated as background noise. This paper considers the more practical scenario of the downlink of a CRAN formed by multiple clouds, where each cloud is connected to a cluster of multiple-antenna base stations (BSs) via high-capacity wireline backhaul links. The network is composed of several disjoint BSs' clusters, each serving a pre-known set of single-antenna users. To account for both inter- cloud and intra-cloud interference, the paper considers the problem of minimizing the total network power consumption subject to quality of service constraints, by jointly determining the set of active BSs connected to each cloud and the beamforming vectors of every user across the network. The paper solves the problem using Lagrangian duality theory through a dual decomposition approach, which decouples the problem into multiple and independent subproblems, the solution of which depends on the dual optimization problem. The solution then proceeds in updating the dual variables and the active set of BSs at each cloud iteratively. The proposed approach leads to a distributed implementation across the multiple clouds through a reasonable exchange of information between adjacent clouds. The paper further proposes a centralized solution to the problem. Simulation results suggest that the proposed algorithms significantly outperform the conventional per-cloud update solution, especially at high signal-to-interference-plus- noise ratio (SINR) target.

The cloud-radio access network (CRAN) is expected to be the core network architecture for next generation mobile radio systems. In this paper, we consider the downlink of a CRAN formed of one central processor (the cloud) and several base station (BS), where each BS is connected to the cloud via either a wireless or capacity-limited wireline backhaul link. The paper addresses the joint design of the hybrid backhaul links (i.e., designing the wireline and wireless backhaul connections from the cloud to the BSs) and the access links (i.e., determining the sparse beamforming solution from the BSs to the users). The paper formulates the hybrid backhaul and access link design problem by minimizing the total network power consumption. The paper solves the problem using a two-stage heuristic algorithm. At one stage, the sparse beamforming solution is found using a weighted mixed 11/12 norm minimization approach; the correlation matrix of the quantization noise of the wireline backhaul links is computed using the classical rate-distortion theory. At the second stage, the transmit powers of the wireless backhaul links are found by solving a power minimization problem subject to quality-of-service constraints, based on the principle of conservation of rate by utilizing the rates found in the first stage. Simulation results suggest that the performance of the proposed algorithm approaches the global optimum solution, especially at high signal-to-interference-plus-noise ratio (SINR).