VEHICLE DATA ANALYZATION USING POWER BI

1
Akanksha Tambitkar, 2Rutuja Phadatare, 3Vaishnavi Pol, 4Prof. Samita Patil
1,2,3
Department of Computer Engineering, University of Mumbai, Shivajirao S. Jondhale College of Engineering

Maharashtra

Abstract
Autonomous vehicles have been invented to increase the safety of transportation users. These vehicles can sense their
environment and make decisions without any external aid to produce an optimal route to reach a destination are the
future smart vehicles anticipated to be driver less, efficient and crash avoiding ideal urban vehicles of the future. To
reach this goal automakers have started working in this area to realize the potential and solve the challenges currently
in this area to reach the expected outcome. Autonomous vehicles have been invented to increase the safety of
transportation users. These vehicles can sense their environment and make decisions without any external aid to
produce an optimal route to reach a destination. But there are difficulties to analyze the energy consumption, vehicle
specific power, power consumption etc. To overcome the difficulties, we are creating Vehicles Data Analyzation. It is a
big data application for autonomous vehicles, where vehicle data is sent several times per second, permitting fine-grained
and near real-time analysis of vehicle status and operating behavior. We focus on typical streaming applications and
present implementations using power BI. We compare the different architecture of autonomous vehicular systems which
include speed, vehicle specific power, actual power consumption, energy consumption. So, our aim to show the analysis
of fine-features inbuilt in vehicular system.
Keywords: - Energy consumption, Vehicle specific power, Power consumption, Longitude and Latitude,

I. INTRODUCTION

A fully autonomous vehicle can be defined as a car which is able to perceive its environment, decide which route to take to its destination,
and drive it. The number of autonomous vehicles is increasing strongly so we need to do proper analyzation of autonomous vehicles
data. In today’s world the autonomous vehicles generate up to 25 gigabytes of data and this number goes up to 3600 gigabytes every
hour. Many useful evaluations can be done from vehicle data to evaluate and improve for e.g.: Times (ms), Latitude (deg), Longitude
(deg), Altitude (m), Vehicle Speed. Handling and processing this vast amount of generated data is a big challenge. To provide data-
driven services, it is vital to have computational systems that can deal with this huge volume of data, analyze and process it to extract
meaningful insights. First, we aim to show the potential of fine-grained analysis in terms of show how to compute energy consumption,
power consumption, calculate the distance from longitude and latitude, calculating vehicle specific power. For analyzing all this data,
we have uses POWER BI platform. It is a data visualization dashboard which convert data from different sources for e.g.-Excel
workshop, CS file, XML etc. Power Bi help to excess our data instantly with less manual work. It handles a huge amount of Data and
automatically get connected with it.

www.ijres.org
• Problem Statement: The problem is when it’s come to handling and processing the vast amount of data which is generated
by autonomous vehicles. The existing system of the autonomous vehicles generate up to only 25 gigabytes of data. It only
records the individual data or the batch set of data. It does not consider such fine-grained analysis, nor discussed basic
architecture of autonomous vehicles.
Our main objective of the project is to visualized the “AUTONOMOUS VEHICLE DATA”, which would be user
friendly, secure and easy to visualized. The evaluation can be done from the autonomous vehicles data for
examples:
Energy Consumption - Calculating the used energy data.
Power Consumption – It is used to calculate the power required by a particular vehicle.
Vehicle Specific Power – It estimates the power in kilowatt and time in hours.
According to the evaluation issues there should be a proper data visualization before buying a autonomous
vehicles. Generally, people do not visualize the data properly due to improper data creation. So, data visualization
is very important.

• Proposed System: Our system work on creating Vehicles Data Analyzation. It is a big data application for autonomous
vehicles, where vehicle data is sent several times per second, permitting fine-grained and near real-time analysis of vehicle
status and operating behaviour.
We focus on typical streaming applications and present implementations using power BI. We compare the different architecture
of autonomous vehicular systems which include speed, vehicle specific power, actual power consumption, energy consumption.
It uses 3G, 4G, 5G wireless technology.
So, our aim to show the analysis of fine-features inbuilt in vehicular system. So, we use POWER BI platform for data
visualization. It is a data visualization dashboard which convert data from different sources for e.g.-Excel workshop, CS file,
XML etc. Power Bi help to excess our data instantly with less manual work.

II. METHODOLOGY

• Vehicle Edge Computing – It allow the vehicle for data processing and reduce unnecessary data transmission. Achieving the
connection smart vehicular layer and the cloud layer for this, we use wireless technology such as 3G and 4G. So, this way
vehicle edge computing is connected to edge computing.
• Edge Computing – It refer to the range of network and device at or near the user. Which is used for offering faster round trip
time. Connecting the edge computing and data Centre, there is a gateway which is used for the connection purpose.
• Gateway - A gateway is a network node used in communications that connects two networks with different transmission
protocols together.
• Data Centre – It processes and analysis the massive amount of data in real time which include autonomous vehicles data.
We have taken the data from Kaggle and store it in Hadoop database.
• Data visualization – It is graphical representations of information and data. We use POWER BI as visualization tool

www.ijres.org
• Block Diagram:

www.ijres.org
Hadware Used:

• Intel Processor: An Intel processor is a type of microprocessor produced by the Intel Corporation. It is the brain of a computer
and is responsible for processing data and instructions. It is 2.11GHz.

• 8GB RAM : Random-access memory is the main memory in a computer. It is much faster to read from and write to than
other kinds of storage, such as a hard disk drive (HDD). It is the hardware in a computing device where the operating system
(OS), application programs and data in current use are kept so they can be quickly reached by the device's processor.

• 476.96 GB Hard Disk Drive: Hard disk drive (HDD) is a type of data storage device that is used in laptops and desktop
computers. An HDD is a “non-volatile” storage drive, which means it can retain the stored data even when no power is
supplied to the device.

Software Used:

• Microsoft Windows 11 – It is the Latest version of windows operating system.

• POWER BI - It is a data visualization dashboard which convert data from different sources for e.g. Excel workshop, CS file,
XML etc. Power Bi help to excess our data instantly with less manual work.

• Excel Sheet – It is spreadsheet program from Microsoft.

• CSV FILE – It stands for COMMA SEPARATED VALUE, which is text file format that uses comma to separate a value.

• Hadoop Database - Hadoop is an open-source framework based on Java that manages the storage and processing of large
amounts of data for applications.

www.ijres.org
Flowchart of System:

www.ijres.org
 III. RESULT
1. The Key Point Indicators

2. Energy Consumption

www.ijres.org
3. Power Consumption

4. Attrition of Longitude and Latitude

www.ijres.org
5. Vehicle Specific Power

6. Battery Current and Battery Voltage of Autonomous Vehicles

www.ijres.org
7. Distance Coovered By Autonomous Vehicles

8. Time Driven in Hours and Speed in kilometer/hour

www.ijres.org
9. Count of Altitude in Meter

10.

www.ijres.org
 IV. CONCLUSION

Managing and understanding all the large amount of data is very difficult. So, Data Visualization is very important for
autonomous vehicles.

REFERENCES

[1] Christian Prehofer DENSO Automotive Germany Eching, Germany Shafqat Mehmood DENSO Automotive Germany and TU
Chemnitz Eching 2020. “Big Data Architectures for Vehicle Data Analysis”.

[2] G. M. Fetene, S. Kaplan, S. L. Mabit, A. F. Jensen, and C. G. Prato 2017. “Big data for estimating the energy consumption and
driving range of electric vehicles”.

[3] Dan Liu 2018. “Big data analytics architecture for Internet-of-vehicle Based on the Spark”.

[4] Alfredo Cabrera, William A Kitch David Freese 2017. “Data analyzation of autonomous electric vehicle on basis of energy
consumption”.

[5] Anthony Nassar, Amir Haroun, Francois Dessables 2020. “Data Architecture for autonomous vehicles”.

[6] T. Furuichi and K. Yamada, “Next generation of embedded system on cloud computing,” Procedia Computer Science, vol. 35, pp.
1605–1614,12 2014.

[7] S. Teerapittayanon, B. McDanel, and H.-T. Kung, “Distributed deep neural networks over the cloud, the edge and end devices,” in
2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). IEEE, 2017, pp. 328–339.

[8] D. Battulga, D. Miorandi, and C. Tedeschi, “Fogguru: a fog computing platform based on Apache flink,” in 2020 23rd Conference
on Innovation in Clouds, Internet and Networks and Workshops (ICIN). IEEE, 2020, pp. 156–158.

[9] O.-C. Marcu, A. Costan, G. Antoniu, and M. S. Perez-Hern ´ andez, “Spark ´ versus flink: Understanding performance in big data
analytics frameworks,” in 2016 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 2016, pp. 433–442.

[10] H. Lee, J. Oh, K. Kim, and H. Yeon, “A data streaming performance evaluation using resource constrained edge device,” in 2017
International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 2017, pp. 628–633.

[11] C.-F. Yeh, L.-T. Lin, P.-J. Wu, and C.-C. Huang, “Using on-board diagnostics data to analyze driving behavior and fuel
consumption,” in International Conference on Smart Vehicular Technology, Transportation, Communication and Applications. Springer,
2018, pp. 343–351.

[12] E. Ericsson, “Independent driving pattern factors and their influence on fuel-use and exhaust emission factors,” Transportation
Research Part D: Transport and Environment, vol. 6, no. 5, pp. 325–345, 2001.

www.ijres.org
www.ijres.org