Day: November 13, 2017

At a time when the global energy industry is undergoing dramatic change, South Australia could very well be the epicenter of innovation.

The South Australian government just announced plans for a solar power plant that will generate up to 150MW of electricity by using thousands of giant mirrors to direct sunlight to the top of a 227-meter thermal tower.

And earlier this year, Elon Musk made headlines with the news that his company will help build the world’s largest lithium ion battery to store renewable energy in the state.

You can also see this kind of innovative thinking at SA Power Networks – the utility responsible for operating and maintaining the electricity distribution network for the entire state of South Australia.

How Do You Energize a Mobile Workforce?

“The Australian energy market is going through a huge amount of change,” says Chris Ford, Chief Information Officer at SA Power Networks. “And as a result, every element of our company is being transformed.” This transformation includes taking advantage of mobile technologies and real-time analytics to help meet not only the demands of an evolving energy market, but also the challenges of a very large service area.

SA Power Networks employees maintain a territory that encompasses 178,000 square kilometers of some of Australia’s driest and remotest landscapes. Summers often bring scorching heat and damaging wildfires to the region.

“Some of our people won’t be in the office for five or six days on the trot,” notes Charlie Hollis, Manager of Procurement at SA Power Networks.

But SA Power Networks is using mobile technology to simplify daily operations for these remote personnel and the home office employees who support them. A good example is how SA Power Networks approves purchase requisitions and the 30,000 purchase orders the utility generates every year.

“We use a mobile app that streamlines the entire procure-to-pay process,” says Melissa Maio, SA Power Networks’ Purchasing Team Lead. “Our managers and field personnel can approve requisitions and purchase orders from anywhere using their mobile device.”

Delivering High-Energy Data

SA Power Networks also customized a mobile app based on SAP Work Manager to allow field personnel to gather service interval information and data from asset inspections in real time. These assets include 400 zone substations, 73,000 street transformers, 720,000 power poles, and 200,000 km of wires.

Previously, this information was captured at the site on a pad of paper and then entered into SA Power Networks’ business systems when field personnel returned to the office. Only then could the data be analyzed and acted upon.

In fact, providing all employees with the information they need to make quicker and more accurate decisions is a hallmark of SA Power Networks’ IT strategy. The utility, for example, is now using the SAP HANA platform to perform advanced analytics on live data as well as historic and demographic data. Company leadership believes this insight will help them respond better to emergencies such as brushfires and storms and manage the overall network more effectively.

“Predictive analytics is really key to us moving forward,” says Ford. “We currently have pilots underway designed to help us predict exactly where we will need to repair lines in certain storm situations.”

A Look Ahead

Innovation continues to be a priority in the energy industry down under.

Australian news reports there are currently more than 50 large-scale renewable energy projects under construction across the country. And in South Australia, SA Power Networks is determined to keep pace with the progress.

“We have been looking at robotics and machine learning to identify areas where we might improve the efficiency of certain tasks even further,” says Ford, citing one final example.

One thing, however, isn’t changing.

Regardless of how the energy is generated, delivering electricity to the 1.7 million people of South Australia will remain the singular mission of SA Power Networks.

Hear more from Chris Ford and the leaders of SA Power Networks in this video.

Please follow me on Twitter @JohnGWard3.

This story originally appeared on SAPVoice on Forbes. http://bit.ly/2zAhEUK #SAP #SAPCloud #AI

Source: SAP

This was an ASUG BITI webcast given by SAP

Figure 2: Source: SAP
Recommend modeling iwth PAL – algorithms are implemented in server, where data resides, see much better performance

Figure 3: Source: SAP

PAL is for data scientists

Credit card data, which customer is credit worthy (classification)

Predicting house prices based on characteristics such as # of rooms, using regression

Cluster similar customers to do targeted marketing campaigns

Time dependent models, sequential pattern modeling to issue coupons

Figure 4: Source: SAP
Color coding indicates investments

Figure 5: Source: SAP
Training the model for random forest modeling

Figure 6: Source: SAP
Model scoring PAL code with confidence level

Figure 7: Source: SAP
Other options include integration with R
Connect from R studio, connect from ODBC

Figure 8: Source: SAP

R integration looks like a stored procedure

Figure 9: Source: SAP
Build models in TensorFlow and call in HANA – like a stored procedure

On the HANA side, you have the Application Function Library

With SPS02 – create the EML/AFL – interfaces between HANA and TensorFlow server

On the right side, build and train TensorFlow and upload to TensorFlow server, and then consume from HANA side

Connect through a Google Remote Function call

TensorFlow Serving Server can run in same box in HANA in development; should be separate in production

Scope is for scoring

Figure 10: Source: SAP

Train the model in TensorFlow

Figure 11: Source: SAP
Step 1 create remote source, host and port of TensorFlow server

Next map the model to the remote source; insert test model

Next – any config changes get applied immediately

Then check all connections are working before start using in the application

Figure 12: Source: SAP

Generate the EML in HANA and then call procedure using the input and output table

Figure 13: Source: SAP

Machine learning in HANA end to end; depends on type of use case

Machine learning is not just developing models, but how do these models get optimized and in a scalable real-time way

Figure 14: Source: SAP
Customer churn prediction with PAL to build a model

You can grow decision trees, output is the class

In PAL, you have fine grained control

Figure 15: Source: SAP

First step is to train the model, populate the parameter table

Figure 16: Source: SAP

Create table to store model

Capture variable importance with a table

Store the out of bag erorr

Store confusion matrix of the model

Figure 17: Source: SAP
Train the model, call the function

Decision trees are stored in PMML format

Out of bag error, the variable importance

Confusion Matrix is also output

Only 3 out of 14 cases did the model predict inaccurately

Figure 18: Source: SAP

Now built the model, want to predict the churn, and will customer to be retained

Create the parameter table
Create the results table for the results of scoring

Prediction and confidence

Used PAL to train the model and then use it to predict scenarios

Figure 19: Source: SAP

Could also build using Web IDE

Figure 20: Source: SAP

Push execution close to data

Figure 21: Source: SAP

Think of performance in terms of batch and real-time

SP02 enhancements

Real time prediction with SPS01

Figure 22: Source: SAP

Decisions need to happen in real time

Figure 23: Source: SAP

The model can remain in memory

Figure 24: Source: SAP

Partitioning – score in parallel

Ability to do large batch style processing in parallel

Figure 25: Source: SAP

Streaming analytics engine to take input from a variety of sources

Figure 26: Source: SAP

Train data as they arrive
Predict in real time

Figure 27: Source: SAP
A summary of a jam-packed webcast

Upcoming ASUG webcasts:

Oct 19 An exciting new future for SAP BusinessObjects Web Intelligence

Oct 26 Overall SAP Analytics strategy and direction 

Oct 31 What’s new in SAP BI Mobile and Roadmap

Nov 7 Cross-Solution Analytics with SAP Analytics Cloud

Nov 9 What’s New in SAP Lumira 2.0

Nov 20 What’s new in Analysis Office 2.6?

Nov 28 – Introduction to SAP Data Hub 

Nov 30 Refresh Expert Streams on Predictive Factory

Dec 5 – Update on Conversion Tools for SAP BW/4HANA

Dec 12 Best Practices for Automated Analytic

  http://bit.ly/2zAck3H #SAP #SAPCloud #AI