Johannesburg, 16 Sep 2016
Utilities companies play a key role in the delivery of services to citizens, and it is one they could improve significantly were they to employ better analytics. This is the view of SAS South Africa, which suggests that while there is little that can be done about the current drought, better planning could assist in substantial improvements in water usage. In addition, effective analytics could forewarn authorities the next time there is the prospect of a drought of this nature.
The same can be said for Eskom's delivery of power - analytics offers the opportunity for more effective forward planning around power stations, not to mention better day-to-day control around the issues of supply and demand.
While South Africa's electricity travails are lengthy and well documented, the current drought has brought SA's water issues into stark focus as well. It is clear that solving the challenges presented by these issues will require a lot of work from a partnership, management and infrastructure planning perspective, but the aggregation of all available data - combined with effective analytics - can have a huge impact on the delivery of these critical services.
According to Kroshlen Moodley, GM for Public Sector at SAS South Africa, it is possible for Eskom to make use of advanced analytics to significantly improve decision-making in a proactive manner. Currently, the big data it gathers from power plants, transformers, generators and other machinery only reflects events that have already happened. This means that decisions are taken based only on historical data, which often proves ineffective.
"Advanced analytics can have a massive impact in this area," says Moodley, "as the big data gathered from Eskom's machinery, as well as data around area usage and other variables, can be plugged into a statistical model. This will enable Eskom to predict future scenarios based on a set of events that have already occurred. Such proactive decision-making will not assist with regulating supply, it will also help Eskom to plan its maintenance schedule more effectively."
He explains that using analytics to forecast demand and supply, such as by analysing information from smart meters to determine how much energy a particular area needs, should allow the electricity provider to forecast how much demand is likely to grow. In this way, it can better manage generating capacity to meet demand.
"Furthermore, when there is a gap in demand, analytics can help Eskom to make better decisions in terms of introducing other electricity sources into the energy mix, to help close the gap. Analysing weather, seasonal and geographic information, as well as the variables for each alternative energy source, will enable Eskom to make informed decisions on how to create the optimal generation and supply scenario. This could mean including wind energy from coastal regions and solar energy from inland areas in the mix, for example."
Eskom can also responsibly manage and communicate planned outages, he says. Eskom would be able to consider variables such as critical operation times for certain industries and traffic flow, information that could then be combined with insights gathered from smart meter monitoring, allowing it to plan how best to supply energy at different times of the day, in a way that minimises impact on businesses and citizens.
"It is all about assisting the company to make better-informed decisions; choices that will save time and money, while optimising processes and resource allocation. Advanced analytics enables this to happen."
As far as water management goes, Moodley suggests that advanced data analytics can assist with water management by delivering a high level view to those in charge. Such a view would encompass water sources and treatment plants, the distribution network and usage, as well as overarching legislature and weather and demand-versus-supply analysis, providing a holistic view of the current situation.
"To be truly effective in helping to solve SA's water challenges, the use of analytics needs to encompass not only the issue of supply, but also treatment, distribution, and even policy management."
By analysing historical weather data, such as that around the recurring El Ni~no phenomenon, and coupling this with normal rainfall data, Moodley points out that it would have been possible to predict the current drought with relative accuracy five years ago.
"This would have given the authorities time to plan for water shortages, by making better decisions on how to supplement supply and prioritise infrastructure development."
With regard to water quality, he indicates that sensors installed at source points, treatment plants and reservoirs will be able to provide a constant stream of data - known as event stream processing - which, when analysed, can reveal certain patterns in water quality.
For example, fluctuations in microbial data could suggest that there is a problem at the water source. Action could be taken immediately to prevent irreversible contamination of the source.
"Advanced data analytics can also be used to reduce the amount of water lost by predicting where losses are likely to occur based on demand, such as a new residential development that will have to be served by ageing infrastructure. Sensors also supply information on assets, such as when they were last serviced, how old they are and when a certain part was replaced. This information produces patterns that indicate the normal functioning of an asset. Thus, an anomaly in the pattern may indicate a problem."
"Using this information, municipalities should be able to perform predictive plant maintenance, thereby reducing downtime and maintaining quality."
Moodley suggests that analytics can even help government better understand population growth and the effect that new residential and industrial developments could have on supply and demand. This information, he says, combined with weather data, can help government decide where to build new catchment areas.
"The case for powerful analytics systems, which aggregate data and can help government make better-informed decisions about critical infrastructure like electricity and water, is clear. The benefits of utilising advanced analytics to turn the current reactive approach into a proactive one are obvious, and should lead to much more effective provision of these basic services. This, in turn, will go a long way towards demonstrating not only government's commitment to, but also its ability to provide effective service delivery to its people," he concludes.
Share