Business Intelligence and Data Analytics in Renewable Energy Sector

Group 5:
Bhargav Bhatt (20131008)
Darshit Paun (20131010)
Jalaj Malhotra (20131015)
Nisarg Shah (20131030)
Rohan Bharadwaj(20131043)
Vishal Nadgir (20131059)
Vikas Gupta (20131058)

• Overall Industry value chain
• Business intelligence
• Utilization of BI in each of the stages of value chain
• Benefits of BI
• Analytics
• Implementation analytic in each of the stages of
value chain
• Benefits of Analytics
• Products available in the market in BI & Analytic
space for this industry
• Process we propose for implementation BI & Analytic
solutions in the value chain

Introduction: Business
Intelligence

 Demand Intelligence
 Risk Intelligence
 Asset Intelligence
 Customer Service Intelligence
 Root Cause analysis
 Forecasting
 Strategy Planning
 Data visualization
 Market Opportunities
 Policy trend analysis
 Energy-focussed scenario modeling

 Analytics is the science of examining raw data with the purpose of drawing conclusions about that
information.
 Analytics is used to make better business decisions and to verify or disprove existing models or
theories.
 Mining sort through huge data sets using sophisticated software to identify undiscovered patterns
and establish hidden relationships.
 Analytics focuses on inference, the process of deriving a conclusion based solely on what is
already known by the researcher.
 The science is generally divided into:
 Exploratory data analysis (EDA), where new features in the data are discovered.
 Confirmatory data analysis (CDA), where existing hypotheses are proven true or false.
 Qualitative data analysis (QDA), conclusions are drawn from non-numerical data like words, photographs
or video.

Sophisticated analytics are enabling renewable energy companies
with deeper insight which helps them better manager the variable
nature of wind and solar, and more accurately forecast the amount of
energy that can be redirected into the power grid or stored.

 Provide customers with irradiance data for their location.
 Short-Term Photovoltaic Power Predictions (meteorological forecasts from
numerical weather prediction (NWP) models)
 Systematic Optimized Strategy for Solar Energy Supply Forecasting (hybrid of
weather and energy forecast models)
 Fault Detection of Large Amounts of Photovoltaic Systems
 Active solar monitoring
 Real-time Solar Energy Output tracking
 Real-time Energy Consumption monitoring
In-time Fault and Diagnosis Alerts
 Monthly regular Performance Report

 Wind turbines are big and expensive machines, so
keeping them running smoothly helps keeping their
operational cost down.
 The sensor data generated by the turbine can help
achieving this – by analysing it, you can spot potential
failures earlier.The longer the warning period before a
part fails, the better you can prepare for it.
Preventive maintenance saves you money when you
have:
1. Shorter downtime and less lost production
2. Better planning of people and materials
3. Cheaper repairs

•Wind Energy Prediction
•Meteorological mast data checks;
•Energy yield calculation using industry standard software tools;
•Calculations of shadow flicker, noise impact, etc;
•Fleet power curve surveys identifying abnormal performance,
underperformance, curtailment and other features indicated by SCADA data
including identification of changes in time and differences from turbine to
turbine;
•Detailed wind farm asset performance analysis against budget including
monthly or other breakdown of the component reasons for deviation from
budget such as availability, grid outage, wind conditions, over performance,
underperformance and curtailment, etc.;
•Energy yield impact estimation to evaluate the efficiency impact of particular
events such as blade cleaning or turbine parameter changes;
•SCADA data investigations to evaluate the impact of downtime due to
particular wind turbine component or outage types;
•LIDAR investigations in order to check whether the turbines are being
subjected to abnormal wind conditions causing significant underperformance,
due to complex terrain, nearby forestry or other reasons;

1.Security and Theft Detection
2.Preventive Equipment
Maintenance
3.Demand Response Management
4.Field Service Management
5.Real-Time Customer Billing &
Provisioning
How much demand for electricity
will there be and when?
Which transformer may blow next
week? (So let's perform
maintenance on it this week.)
Where should we set up new plant
to achieve the best results?
Which type of material is better for
manufacturing and why?

IHS company – Wind Energy
Products across the value chain.

IHS company – Emerging products
in the Renewable Energy Segment.

BI in a Wind Turbine by Siemens

IBM-Hybrid Renewable Energy
Forecasting" (HyRef) ::

Virtual Irradiance solar
analytics developed by Locus
Technologies
The Virtual Irradiance solar
analytics tool will combine NASA
satellite data, government weather
station data and data from Locus'
network of 40,000 systems which it
monitors in North America to
provide customers with irradiance
data for their location.
The tool provides data for a one
square kilometre location
anywhere in the continental United
States, in fifteen minute intervals.
Locus says that it is as accurate as
on-site weather sensors over a
one-month period.

 http://www.kwhanalytics.com/
 http://www.lavastorm.com/solutions/by-
industry/utilities/
 http://heliopower.com/predictenergy/
 http://www.geovisual-analytics.com/
 http://www-
03.ibm.com/press/us/en/pressrelease/41310.wss
 http://www.ibmbigdatahub.com/video/optimizing-
operations-countering-fraud-and-threats

Business Intelligence and Data Analytics in Renewable Energy Sector

More Related Content

What's hot (20)

Viewers also liked (8)

Similar to Business Intelligence and Data Analytics in Renewable Energy Sector (20)

More from Darshit Paun (17)

Recently uploaded (20)

Business Intelligence and Data Analytics in Renewable Energy Sector