SMART TRAFFIC MANAGEMENT USING CLOUD COMPUTING
ABSTARCT :
Traffic big data has brought many opportunities for traffic management applications. However several challenges like heterogeneity, storage, management, processing and analysis of traffic big data may hinder their efficient and real-time applications. All these challenges call for well-adapted distributed framework for smart traffic management that can efficiently handle big traffic data integration, indexing, query processing, mining and analysis. In this paper, we present a novel, distributed, scalable and efficient framework for traffic management applications. The proposed cloud computing based framework can answer technical challenges for efficient and real-time storage, management, process and analyse of traffic big data. For evaluation of the framework, we have used Open Street Map (OSM) real trajectories and road network on a distributed environment. Our evaluation results indicate that speed of data importing to this framework exceeds 8000 records per second when the size of datasets is near to 5 million. We also evaluate performance of data retrieval in our proposed framework. The data retrieval speed exceeds 15000 records per second when the size of datasets is near to 5 million. We have also evaluated scalability and performance of our proposed framework using parallelisation of a critical pre-analysis in transportation applications. The results show that proposed framework achieves considerable performance and efficiency in traffic management applications.
EXISTING SYSTEM :
? A new approach to service allocation, derived from the existing cloud and grid computing approaches, was created to address the unique needs of ITS traffic management.
? Intelligent Transportation Systems (ITSs) aim to improve existing road networks capacity, reduce travel times, fuel consumption, increase safety of all traffic participants and deliver traffic relevant information to the drivers.
? Design an improved traffic management scheme to address the identified weaknesses of existing methods.
DISADVANTAGE :
? All these problems call for well-adapted distributed framework for TMS that can efficiently handle big traffic data integration, indexing, query processing, mining and analysis.
? To face this issue, an important traffic analysis named map matching has been developed.
? The main drawback of this platform is using central server and lack of fault tolerance, elasticity and high availability. The main goal of the framework is answering to traditional TMS drawbacks that has discussed earlier.
PROPOSED SYSTEM :
• In architecture of the proposed model, to reduce the load on cloud computing servers, processing and storage sources are placed on mid-layer between cloud computing servers and final user.
• The genetic algorithm is used for optimal distribution of load between local servers and cloud servers in proposed model as a meta-heuristic algorithm.
• This purpose can be realized only with an appropriate architecture and effective use of all components of traffic management system.
ADVANTAGE :
? Low-latency data storage and access: the framework should contain an efficient and flexible tool for data gathering and management for massive traffic data with high performance and low latency.
? However like every other high level abstraction, using hive needs additional computation which leads to lower performance of the system.
? Data processing and analysis: with this tremendous valuable big data, real-time query processing, analysis and data mining in traditional frameworks is a time consuming inefficient task.
|