How to Fast Track Your Path to a Smart Grid by Leveraging the Analytics Value Chain

smart meterThe movement to a Smart Grid is a significant and growing trend in the industry, which expects to generate an 18%+ growth rate between now 2019 and create an overall market size of $118 billion.

The applications for advanced analytics for the Smart Grid have the potential for adding significant business value in a number of ways – revenue enhancement, operational efficiency, and reduced costs.

The maturity model approach and the analytics value chain methodology are two key tools available to help business operations manager in the utilities industry move seamlessly to this Smart Grid model.

Achieving the best possible outcomes depends on understanding the use cases across all the operations of the business. The scale of the utilities industry offers many opportunities where analytics can add significant business value to their operations.

Introducing the Three Maturity Models for Utilities Use Cases

Smart Grid use cases and applications vary in their potential to add business value. The use cases in the industry can be generally divided into three maturity models that represent increasing levels of value (see Figure 1 below).

maturity models of uses cases in the utilities industry

Figure 1: Business Value for Smart Grid Use Cases

1) Maturity Model I

In the Maturity Model I, the examples are improvements to basic infrastructure and operations in areas such as power security (preventing theft of power), quality of power, and enablement of consumer management over their power usage.

2) Maturity Model II

In the Maturity Model II, major operational efficiency or cost savings are achieved in the application and greater value is captured by implementing Smart Grid use cases that drive efficiencies across the full value chain of the business. Examples of this scenario include:

  • Increasing the range of power generation & storage options – this includes new renewable generation options like solar and wind, as well as new technologies to store and forward power to where it is needed most at any particular point in time.
  • Asset Optimization & Operations Efficiencies – major capital assets require prudent management to maximize ROI. Their scale means that small improvements can yield significant financial returns. Intelligent management of these assets can drive significant value.

3) Maturity Model III

In the last type of use case, Maturity Model III, the value generated goes far beyond basic operations or efficiency and drives major changes to the business value for the utilities company. These transformations typically take two forms:

  • New Products & Services – the Smart Grid enables the utilities to offer new services at both the wholesale and consumer level by providing deeper insights on capacity demand, issue identification, pricing options, and more. These new products and services represent value that was simply unavailable in a traditional utilities environment.
  • Self-Healing (Autonomic) Systems – another major source of value in a Smart Grid environment is the ability for new information and systems to identify (in real-time) problems in the core infrastructure and automatically address or “heal” them. This advanced level certainly requires new technology that can identify the patterns and information that are reliable indicators of issues and the automation tools to trigger related systems to make adjustments and changes to eliminate or mitigate the problem.

Traditional IT Architecture in Utilities Not Designed for Demands of a Smart Grid Model

Implementing the Smart Grid use cases and growing through the maturity models while maintaining normal ongoing operations is a major challenge. Dramatic changes to IT architecture in utilities are rarely possible, and innovation must be done via an evolutionary and overlay approach for basic computing infrastructure.

The computing and communications infrastructure of a typical utility is usually some variation of the overview depicted in Figure 2 below.

TRADITIONAL IT ARCHITECTURE IN UTILITIES

Figure 2. Traditional IT Architecture in Utilities (image recreated from Schneider Electric)

The core architecture is often considered the “single version of the truth.”  These architectures usually include real-time services such as feeder automation and substation automation as well as enterprise services.

Typical enterprise services include SCADA (Supervisory Control & Data Acquisition System), OMS (Outage Management System), ERP (Enterprise Resource Planning), GIS (Geographic Information System), and CRM (Customer Relationship Management).

This information is typically less time-sensitive than core grid operations. Both of these sets of information are then passed to the business applications that consume this data. This traditional architecture works reasonable well, but was not designed with the demands of a Smart Grid model in mind.

Leveraging existing systems and assets while implementing smart grid applications rapidly is truly a complex balancing act!

Applying the “Analytics Value Chain” Methodology

To address the challenges described above and meet the vision of a true Smart Grid, there is a need to unify and execute analytics in real-time across the analytics value chain (streaming, historical, predictive, and prescriptive) with relevant contextual and situational data that addresses the critical last step for timely outcomes.

As shown in Figure 3 below, this is then combined with the ability to take the next best action in any particular scenarios that creates the greatest value. The increasing value chain shows how each step in the process refines the data and adds more value and context.

IoT Analytics Value Chain

Figure 3: IoT Analytics Value Chain

  1. Ingesting data at speed and volume sets the stage for additional processing
  2. Real-time Streaming Analytics processes incoming streams of data from smart grid sensors and devices.
  3. This refined data is then correlated with contextual and historical data to provide a baseline for advanced analytics. Contextual data can include information like GIS (geographic information systems) data relating to a Smart Grid application.
  4. The next step is to predict failures, anomalies, or patterns using predictive analytics that are based on machine learning over historical and situational data such as external events like weather.
  5. The final step in the analytics value chain is to apply prescriptive analytics to determine the next best action to take. This next best action could be a wide variety of actions associated with lowering risks, addressing an outage, or spinning up a new generator.

The key point here is that specific actions based on a rich understanding of history and context must be taken NOW in order to capture that value.

While this high level vision of a new approach to analytics is logical and appealing, more advanced analytic tools are needed to achieve this ambitious goal for the Smart Grid environment.

The level of integration and performance inherent in this view are demanding, and existing platforms and tools will not suffice.

Get our White Paper to Learn More

advaned analytics for utilities white paper downloadTo see how this analytics value chain can be leveraged across all use cases in the maturity models, and how to accelerate the move to the Smart Grid, download our whitepaper.

Click here to download our white paper!

Comments are closed.