Use of Data Analytics to foster Energy Efficiency
Workshop on Low GradeWHU for PaliTextile Industry Cluster,
PACE-DTechnical Assistance Programme, 12th August, 2014
Umesh Bhutoria,Founder & CEO, E-Cube Energy
About Us
๏‚— E-Cube Energy is one of the emerging players in energy efficiency domain working
with energy intensive industries to help them develop and implement sustainable
energy efficiency practices.
๏‚— Largest portfolio in the Textile Industry with over 10 Lac Spindle capacity under
management.
๏‚— In less than 2 years of operation developed first of its kind cloud based Energy
Information Management and Analytics Portal EnView.
๏‚— Established saving potential of over 15 Million Units/Year across 8 textile units.
๏‚— Developed Normalization and Energy Forecasting Models for Textile and Iron
& Steel Industry.
๏‚— Thought leaders in energy efficiency domain focusing on Energy Data Analytics.
Released a white paper on Indian perspective on Energy Data Analytics
PaliTextile Cluster
๏‚— One of the biggest industrial clusters in Rajasthan.
๏‚— Most of the industries are Dyeing, Finishing/Processing units.
๏‚— Significant thermal energy consumption and thereby an opportunity to recover Low
Grade Heat and optimize overall energy consumption pattern.
๏‚— Availability of quality data/information has been identified as biggest challenge in
driving energy efficiency.
Ref: Pali Textile Cluster, under BEE SME Programme
Challenges-Textile Energy Efficiency
Need for perspective shift on driving
Energy Efficiency?
How can Data help?
Performance
Assessment
Baseline vs
Actual Energy
Data
Explore
avenues for
further energy
saving/
optimization
Forecasting
Models/
Normalization
Case Study- Process Optimization
๏‚— One of the units had a 12 TPD Dye House. Product mix mainly comprised
Polyester,Acrylic,Viscose, Carded Cotton, Combed Cotton.
๏‚— Their actual steam consumption was deviating significantly in comparison to the
Budgeted Consumption.
๏‚— We looked at their steam consumption and production data (some 300 data
sets),developed forecasting model and SKG indexes for all product types.
SKG Index SKG ABP
Polyester 3.55 4
Viscose 6.62 7
Acrylic 3.89 3.3
Carded cotton 14.61 7.5
Combed cotton 10.00 7.5
Case Study- Normalization
PV V P Electric
ity in
MkWh
UKG
(Actual)
Baseline 11.32% 33.72% 54.97% 38.02 2.79
Compliance 22.24% 26.20% 51.56% 43.58 2.85
% Change 10.92% -7.51% -3.41% 14.62% 2.15%
35.00
36.00
37.00
38.00
39.00
40.00
41.00
42.00
43.00
44.00
0.00%
10.00%
20.00%
30.00%
40.00%
50.00%
60.00%
Baseline Compliance
BaselineVs Compliance Period
Electricty in mkWh Yarn A Yarn B Yarn C
Case Study- Normalization
PV V P
UKG Index 3.56 3.30 2.37
Calculated UKG
Contribution for
Baseline
0.403 1.113 1.303
Calculated UKG
Contribution for
Compliance
0.792 0.865 1.222
Expected Change in
UKG attributed to
Product Mix
2.13%
Actual Change in
UKG
2.15%
Change in UKG
attributed to factor
other factors
0.02%
Case Study- Performance
Assessment
800
900
1000
1100
1200
1300
1400
1500 19-03-2014
21-03-2014
23-03-2014
25-03-2014
27-03-2014
29-03-2014
31-03-2014
02-04-2014
04-04-2014
06-04-2014
08-04-2014
10-04-2014
12-04-2014
14-04-2014
16-04-2014
18-04-2014
20-04-2014
22-04-2014
24-04-2014
26-04-2014
28-04-2014
30-04-2014
02-05-2014
04-05-2014
06-05-2014
08-05-2014
10-05-2014
12-05-2014
14-05-2014
16-05-2014
18-05-2014
20-05-2014
22-05-2014
CD Energy/ Day Analysis
Total kWh
High
Low
Case Study- Performance
Assessment
1,309.94
1,029.06
280.88
- 200.00 400.00 600.00 800.00 1,000.00 1,200.00 1,400.00
CD Section Energy/Day Analysis
Diff in kWh
Avg kWh after optimisation
Avg kWh before optimisation
Case Study- Supply Side
Management
TIME AIR Required WATER Actual Flow
Optimised
Flow
SavingsVia
Optimisation
in KW (5%)
SavingsVia
Optimisation
as per
requirment
8:30 AM 68524.08 416.7 70000 70,000.00 0.00 -
9:30 AM 83580.69 444.07 70000 70,000.00 0.00 -
10:30 AM 72120.37 485.28 70000 70,000.00 0.00 -
11:30 AM 75014.99 534.11 70000 70,000.00 0.00 -
12:30 PM 78996 586.55 70000 70,000.00 0.00 -
1:30 PM 72712.78 608.88 70000 70,000.00 0.00 -
2:30 PM 66108.11 626.44 70000 70,000.00 0.00 -
3:30 PM 59403.46 619.61 70000 66,500.00 7.99 12.74
4:30 PM 56539.97 616.69 70000 66,500.00 7.99 19.13
5:30 PM 56539.97 616.69 70000 66,500.00 7.99 19.13
6:30 PM 56539.97 616.69 70000 66,500.00 7.99 19.13
Case Study- Supply Side
Management
50000
55000
60000
65000
70000
75000
80000
85000
90000
1 2 3 4 5 6 7 8 9 10 11
AIR Required
Actual Flow
Optimised Flow
Case Study- Supply Side
Management
13000
14000
15000
16000
17000
18000
19000
Total
High
Low
โ€œMetering tells whatโ€™s obvious whereas
Data Analytics predicts and tells us what
should have happenedโ€
How can you get started?
Select process/ problem
areas and its scope
Define Key Performance
Indicators "KPIs"
Identify data sources
Initate data accquistion
with time stamp
Analyse energy and
production/process
KPI based benchmarking/
trend analysis
Automatic Alerts/Offsite
reports, energy saving
projects
Implementation of
projects/ Highlight Best
Case Practices
ThankYou!
umesh@eetpl.in | 09831012510

Energy Data Analytics for #Textile Industry. PACE-D TA Programme for Textile Cluster,PALI

  • 1.
    Use of DataAnalytics to foster Energy Efficiency Workshop on Low GradeWHU for PaliTextile Industry Cluster, PACE-DTechnical Assistance Programme, 12th August, 2014 Umesh Bhutoria,Founder & CEO, E-Cube Energy
  • 2.
    About Us ๏‚— E-CubeEnergy is one of the emerging players in energy efficiency domain working with energy intensive industries to help them develop and implement sustainable energy efficiency practices. ๏‚— Largest portfolio in the Textile Industry with over 10 Lac Spindle capacity under management. ๏‚— In less than 2 years of operation developed first of its kind cloud based Energy Information Management and Analytics Portal EnView. ๏‚— Established saving potential of over 15 Million Units/Year across 8 textile units. ๏‚— Developed Normalization and Energy Forecasting Models for Textile and Iron & Steel Industry. ๏‚— Thought leaders in energy efficiency domain focusing on Energy Data Analytics. Released a white paper on Indian perspective on Energy Data Analytics
  • 3.
    PaliTextile Cluster ๏‚— Oneof the biggest industrial clusters in Rajasthan. ๏‚— Most of the industries are Dyeing, Finishing/Processing units. ๏‚— Significant thermal energy consumption and thereby an opportunity to recover Low Grade Heat and optimize overall energy consumption pattern. ๏‚— Availability of quality data/information has been identified as biggest challenge in driving energy efficiency. Ref: Pali Textile Cluster, under BEE SME Programme
  • 4.
  • 5.
    Need for perspectiveshift on driving Energy Efficiency?
  • 6.
    How can Datahelp? Performance Assessment Baseline vs Actual Energy Data Explore avenues for further energy saving/ optimization Forecasting Models/ Normalization
  • 7.
    Case Study- ProcessOptimization ๏‚— One of the units had a 12 TPD Dye House. Product mix mainly comprised Polyester,Acrylic,Viscose, Carded Cotton, Combed Cotton. ๏‚— Their actual steam consumption was deviating significantly in comparison to the Budgeted Consumption. ๏‚— We looked at their steam consumption and production data (some 300 data sets),developed forecasting model and SKG indexes for all product types. SKG Index SKG ABP Polyester 3.55 4 Viscose 6.62 7 Acrylic 3.89 3.3 Carded cotton 14.61 7.5 Combed cotton 10.00 7.5
  • 8.
    Case Study- Normalization PVV P Electric ity in MkWh UKG (Actual) Baseline 11.32% 33.72% 54.97% 38.02 2.79 Compliance 22.24% 26.20% 51.56% 43.58 2.85 % Change 10.92% -7.51% -3.41% 14.62% 2.15% 35.00 36.00 37.00 38.00 39.00 40.00 41.00 42.00 43.00 44.00 0.00% 10.00% 20.00% 30.00% 40.00% 50.00% 60.00% Baseline Compliance BaselineVs Compliance Period Electricty in mkWh Yarn A Yarn B Yarn C
  • 9.
    Case Study- Normalization PVV P UKG Index 3.56 3.30 2.37 Calculated UKG Contribution for Baseline 0.403 1.113 1.303 Calculated UKG Contribution for Compliance 0.792 0.865 1.222 Expected Change in UKG attributed to Product Mix 2.13% Actual Change in UKG 2.15% Change in UKG attributed to factor other factors 0.02%
  • 10.
    Case Study- Performance Assessment 800 900 1000 1100 1200 1300 1400 150019-03-2014 21-03-2014 23-03-2014 25-03-2014 27-03-2014 29-03-2014 31-03-2014 02-04-2014 04-04-2014 06-04-2014 08-04-2014 10-04-2014 12-04-2014 14-04-2014 16-04-2014 18-04-2014 20-04-2014 22-04-2014 24-04-2014 26-04-2014 28-04-2014 30-04-2014 02-05-2014 04-05-2014 06-05-2014 08-05-2014 10-05-2014 12-05-2014 14-05-2014 16-05-2014 18-05-2014 20-05-2014 22-05-2014 CD Energy/ Day Analysis Total kWh High Low
  • 11.
    Case Study- Performance Assessment 1,309.94 1,029.06 280.88 -200.00 400.00 600.00 800.00 1,000.00 1,200.00 1,400.00 CD Section Energy/Day Analysis Diff in kWh Avg kWh after optimisation Avg kWh before optimisation
  • 12.
    Case Study- SupplySide Management TIME AIR Required WATER Actual Flow Optimised Flow SavingsVia Optimisation in KW (5%) SavingsVia Optimisation as per requirment 8:30 AM 68524.08 416.7 70000 70,000.00 0.00 - 9:30 AM 83580.69 444.07 70000 70,000.00 0.00 - 10:30 AM 72120.37 485.28 70000 70,000.00 0.00 - 11:30 AM 75014.99 534.11 70000 70,000.00 0.00 - 12:30 PM 78996 586.55 70000 70,000.00 0.00 - 1:30 PM 72712.78 608.88 70000 70,000.00 0.00 - 2:30 PM 66108.11 626.44 70000 70,000.00 0.00 - 3:30 PM 59403.46 619.61 70000 66,500.00 7.99 12.74 4:30 PM 56539.97 616.69 70000 66,500.00 7.99 19.13 5:30 PM 56539.97 616.69 70000 66,500.00 7.99 19.13 6:30 PM 56539.97 616.69 70000 66,500.00 7.99 19.13
  • 13.
    Case Study- SupplySide Management 50000 55000 60000 65000 70000 75000 80000 85000 90000 1 2 3 4 5 6 7 8 9 10 11 AIR Required Actual Flow Optimised Flow
  • 14.
    Case Study- SupplySide Management 13000 14000 15000 16000 17000 18000 19000 Total High Low
  • 15.
    โ€œMetering tells whatโ€™sobvious whereas Data Analytics predicts and tells us what should have happenedโ€
  • 16.
    How can youget started? Select process/ problem areas and its scope Define Key Performance Indicators "KPIs" Identify data sources Initate data accquistion with time stamp Analyse energy and production/process KPI based benchmarking/ trend analysis Automatic Alerts/Offsite reports, energy saving projects Implementation of projects/ Highlight Best Case Practices
  • 18.