Time-dependent Decentralized Routing using Federated Learning

Wilbur, Michael; Samal, Chinmaya; Talusan, Jose Paolo; Yasumoto, Keiichi; Dubey, Abhishek

doi:10.1109/isorc49007.2020.00018

Cited by 9 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Millions of people rely on centralized, effective www.ijacsa.thesai.org route planning systems like Google Maps as a result of this. Algorithms for route planning have advanced along with the cloud settings in which they operate [15]. As current state-ofthe-art solutions are predicated on a shared memory paradigm, their deployment is constrained to data center multiprocessing scenarios.…”

Section: IImentioning

confidence: 99%

Utilizing Federated Learning for Enhanced Real-Time Traffic Prediction in Smart Urban Environments

Kumari,

Ulmas,

et al. 2024

IJACSA

View full text Add to dashboard Cite

Federated Learning (FL), a crucial advancement in smart city technology, combines real-time traffic predictions with the potential to enhance urban mobility. This paper suggests a novel approach to real-time traffic prediction in smart cities: a hybrid Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) architecture. The investigation started with the systematic collection and preprocessing of a lowresolution dataset (1.6 GB) derived from real-time Closed Circuit Television (CCTV) traffic camera images at significant intersections in Guntur and Vijayawada. The dataset has been cleaned up utilizing min-max normalization to facilitate use. The primary contribution of this study is the hybrid architecture that it develops by fusing RNN to detect temporal dynamics with CNN for geographic extraction of characteristics. While the RNN's recurrent interactions preserve hidden states for sequential processing, the CNN efficiently retrieves high-level spatial information from static traffic images. Weight adjustments and backpropagation are used in the training of the proposed hybrid model in order to enhance real-time predictions that aid in traffic management. Notably, the implementation is done with Python software. The model reaches a testing accuracy of 99.8% by the 100th epoch, demonstrating excellent performance in the results and discussion section. The Mean Absolute Error (MAE) results, which show a 4.5% improvement over existing methods like Long S hort Term Memory (LS TM), S upport Vector Machine (S VM), S parse Auto Encoder (S AE), and Gated Recurrent Unit (GRU), illustrate the efficacy of the model. This demonstrates how well complex patterns may be represented by the model, yielding precise real-time traffic predictions in crowded metropolitan settings. A new era of more precise and effective real-time traffic forecasts is about to begin, thanks to the hybrid CNN-RNN architecture, which is validated by the combined strengths of FL, CNN, and RNN as well as the overall outcomes.

show abstract

Section: IImentioning

confidence: 99%

Utilizing Federated Learning for Enhanced Real-Time Traffic Prediction in Smart Urban Environments

Kumari,

Ulmas,

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Nonetheless, deploying planning decisions directly in the cloud leads in communication latency, and at the same time, new collision trajectories are continuously generated due to multiple dynamic obstacles, which drastically reduces the decision window for route planning. For the purpose of solving this problem, the work in [106] deploys routing at the network edge of RSUs and assumes that access to external cloud servers is intermittent while compressing the search space as well as limiting the communication frequency of fog nodes, effectively reducing latency and memory requirements. In [107], the traffic data collected by each station is divided into distinct clusters, the road network is modeled as a time-dependent graph, and the enhanced A* algorithm determines the optimal route with the quickest travel time.…”

Section: Service Providingmentioning

confidence: 99%

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Zhu

Yin

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

“…We assume that for every query, q there exists an optimal sequence of grids, SG, from s to d. We assume that each RSU has a trained model for identifying the next best grid given a set of inputs: current grid, source, destination, and time. By recursively utilizing this model from the source until the destination, we generate the optimal sequence grid, SG [43].…”

Section: Queries and Tasksmentioning

confidence: 99%

“…1. This uses the source, destination and time parameter of the query as well as the Equivalent Grid Routing model (Ê) [43], to recursively identify the optimal grid sequence SG, from the source s to the destination d.Ê is a routing model used by Algo. 2, that predicts the best neighboring grid through which the shortest path likely resides for a particular route.…”

Section: Decentralized Route Planning Examplementioning

confidence: 99%

Route Planning Through Distributed Computing by Road Side Units

et al. 2020

Self Cite

View full text Add to dashboard Cite

Cities are embracing data-intensive applications to maximize their constrained transportation networks. Platforms such as Google offer route planning services to mitigate the effect of traffic congestion. These use remote servers that require an Internet connection, which exposes data to increased risk of network failures and latency issues. Edge computing, an alternative to centralized architectures, offers computational power at the edge that could be used for similar services. Road side units (RSU), Internet of Things (IoT) devices within a city, offer an opportunity to offload computation to the edge. To provide an environment for processing on RSUs, we introduce RSU-Edge, a distributed edge computing system for RSUs. We design and develop a decentralized route planning service over RSU-Edge. In the service, the city is divided into grids and assigned an RSU. Users send trip queries to the service and obtain routes. For maximum accuracy, tasks must be allocated to optimal RSUs. However, this overloads RSUs, increasing delay. To reduce delays, tasks may be reallocated from overloaded RSUs to its neighbors. The distance between the optimal and actual allocation causes accuracy loss due to stale data. The problem is identifying the most efficient allocation of tasks such that response constraints are met while maintaining acceptable accuracy. We created the system and present an analysis of a case study in Nashville, Tennessee that shows the effect of our algorithm on route accuracy and query response, given varying neighbor levels. We find that our system can respond to 1000 queries up to 57.17% faster, with only a model accuracy loss of 5.57% to 7.25% compared to using only optimal grid allocation. INDEX TERMS Distributed computing, Middleware, Transportation, Vehicle routing, Road side units I. INTRODUCTION Urban cities are growing at a rapid pace. This growth, bolstered by businesses, commerce, and opportunities, is bringing more and more people into these urban landscapes, putting a strain on the cities' limited infrastructure. For example, roads are faced with an influx of motorists resulting in heavy traffic, which makes living in cities unbearable. To meet the growing demands, cities and private companies are turning to data-intensive applications to make the most out of the limited resources. Companies such as Google, Apple, and Waze 1 created traffic-aware navigation apps that leverage crowd-sourced information and cloud environments. These applications allow users access to up-to-date routing information for their daily commutes. 1 https://www.waze.com/ Cloud environments running on centralized architectures can process data effectively for existing services, however, future use cases such as autonomous vehicles have their own challenges [1], such as requiring ultra-reliable low-latency communications [2]. These requirements expose the limitations of the cloud and call for a new architecture that better fits the requirements for real-time analysis and processing of city-level data. One way to resolve ...

show abstract

Time-dependent Decentralized Routing using Federated Learning

Cited by 9 publications

References 14 publications

Utilizing Federated Learning for Enhanced Real-Time Traffic Prediction in Smart Urban Environments

Utilizing Federated Learning for Enhanced Real-Time Traffic Prediction in Smart Urban Environments

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Route Planning Through Distributed Computing by Road Side Units

Contact Info

Product

Resources

About