Use Cases

Smart Grid

Use Cases


Much of the “smarts” in the smart grid come from the ability to translate data into knowledge and the subsequent action to improve the grid efficiency. The smart grid data system lies solidly in advanced analytics techniques. easily incorporates analytics to the grid operations in areas like Condition Based Monitoring, User segmentation and Load demanding profiling. We qualify grid operators to quickly monetize their data analytics value.

Condition Based Monitoring

Smart Grid offers the possibility to remotely access any asset data with the goal of removing unneeded field trips, reducing consumer outages and ultimately reducing operation and maintenance costs. enables Utilities to move from time-based maintenance practices to equipment-condition based maintenance. Unlocking data from grid assets helps grid operators reduce the risk of overloading problematic equipment.

User Pattern Profiling

Advanced Metering Infrastructure (AMI) provides real-time energy usage data from any customer in the grid. Hidden customer behavior that repeats over time is overlooked with negative consequences for businesses.


Consumers and Industries can be profiled and grouped by consumption behavior. helps Utilities uncover customer behavioral patterns in massive amounts of data, to prevent fraud, deploy dynamic pricing modelling, and load demand forecasting, among others.


Communications Service Providers (CSPs) face an unprecedented competition to win consumer and enterprise business when infrastructure costs are increasing to keep up with extraordinary data demand by subscribers. 


Although they hold vast amounts of data about their network and subscribers, CSPs are not effectively managing it today. It has become more important than ever to monitor the instant changes in customer behavior, capture when and for how long a customer is impacted by poor QoE, provide accurate resolution timelines, and identify the causes driving the quality degradation.

Monitoring Anomaly detection, Root Cause Analysis and poor QoE

Frequently, a network anomaly is a sudden and often short-lived deviation from normal operation. Some anomalies can be deliberately caused by intruders, others might be purely accidental, and some can represent network malfunctioning, which impact subscriber QoE. Quick detection is needed to initiate a timely response.


By processing data at super high rates and detecting unknown network behavior, provides real-time network data at subscriber level to care agents and NOC personnel, which proactively detects network anomalies affecting subscriber QoE, and which identifies the root causes that characterize those anomalies.

Use Cases

Industrial IoT


The industrial IoT is experiencing a disruption caused by the new value creation made possible by massive volumes of data from connected sensors and the increased possibility to make automated decisions based on data observations. uses statistics to learn high fidelity models of any asset from its normal operating data. The model provides relevant information about the asset behavior, the causes for such behavior and predictions of its evolution.

Asset Condition Monitoring

To ensure a continued safe and efficient operation of any industrial equipment, it is essential that accurate online measurement information is available to operators, engineering and maintenance personnel. provides the capability to validate conditions based on statistic techniques to detect instrument degradation and diagnostics with higher accuracy and faster response times than prior techniques.

Predictive asset maintenance

Predictive diagnostic identifies a slow degradation as much as possible in advance of the failure itself. Slow but steady degradation can be indicative of a major failure in the near future with potentially serious consequences.


Such situations are complex to detect because the asset performance rarely suffers a big change. measures how the performance deviates from the expected values and predicts its evolution using advanced machine learning techniques.

Industrial Assets Performance Segmentation

Environmental conditions represent an impact on the equipment performance. Factors like temperature, air humidity, wind speed and direction significantly affect asset performance and life time. automatically segments assets into communities based on environmental similarities. This segmentation approach reduces the number of false positive alarms and provides highly accurate results.