Effective prescriptive maintenance only becomes possible after the accumulation and integration of multiple data sources over an extended period. Inference models should understand both normal and abnormal equipment performance in various conditions, such as extreme weather, during incorrect operation, or when adjacent parts are degraded. For many smaller organisations or those deploying new equipment, the necessary volume of data will not be available without the assistance of equipment manufacturers. Moreover, even manufacturers will not have sufficient data on interaction with complementary equipment. This provides an opportunity for large operators to sell their own inference models as a new revenue stream. For example, an electrical grid operator in North America can partner with a similar, but smaller organisation in Europe to provide operational data and maintenance recommendations. Similarly, telecom providers, regional transportation providers, logistics companies, and smart cities will find industry players in other geographies that they do not naturally compete with.
Employing multiple sensors. Baseline conditions and failure signatures are improved using machine learning based on feeds from multiple sensors, such as those that monitor vibration, sound, temperature, pressure, and humidity. The use of multiple sensors makes it possible to not only identify potential failure but also the reason for it and can therefore more accurately prescribe a solution to prevent an outage.
Data assessment and integration. Prescriptive maintenance is most effective when multiple data sources are unified as inputs. Identify the location of these sources, such as ERP systems, time series on site, environmental data provided externally, or even in emails or on paper. A data fabric should be considered to ensure insights can be extracted from data no matter the environment it resides in.
Automated action. Reduce the potential for human error or delay by automatically generating alerts and work orders for resource managers and service staff in the event of anomaly detection. Criticality measures should be adopted to help prioritise maintenance tasks and reduce alert noise.
IoT is also being used for predictive maintenance and in enhancing employee safety. Smart sensors can monitor parameters such as vibrations, temperature and moisture, and detect abnormal behaviours in equipment – helping field workers to make maintenance decisions in real-time, enhancing their safety.
GIS is being used to get spatial data and map project distribution plans for water, sewage, and electricity. For instance, India’s Restructured Accelerated Power Development & Reforms Program (R-APDRP) government project involves mapping of project areas through GIS for identification of energy distribution assets including transformers and feeders with actual locations of high tension and low tension wires to provide data and maintain energy distribution over a geographical region. R-APDRP is also focused on reducing power loss.
Transparency and Efficiency using Blockchain
Blockchain-based systems are helping the Utilities industry in centralising consumer data, enabling information sharing across key departments and offering more transparent services to consumers.
Energy and Utilities companies are also using the technology to redistribute power from a central location and form smart contracts on Blockchain for decisions and data storage. This is opening opportunities for the industry to trade on energy, and create contracts based on their demand and supply. US-based Brooklyn Microgrid, for example, is a local energy marketplace in New York City based on Blockchain for solar panel owners to trade excess energy generated to commercial and domestic consumers. In an initiative launched by Singapore’s leading Power company, SP Group, companies can purchase Renewable Energy Certificates (RECs) through a Blockchain-powered trading platform, from renewable producers in a transparent, centralised and inexpensive way.
Blockchain is also being used to give consumers the transparency they demand. Spanish renewable energy firm Acciona Energía allows its consumers to track the origin of electricity from its wind and solar farms in real-time providing full transparency to certify renewable energy origin.
Intelligence in Products and Services using AI
Utilities companies are using AI & Automation to both transform customer experience and automate backend processes. Smart Meters, in itself, generate a lot of data which can be used for intelligence based on demographics, usage patterns, demand and supply. This is used for load forecasting and balancing supply and demand for yield optimisation. It is also being leveraged for targeted marketing including personalised messages on Smart Energy usage.
Researchers in Germany have developed a machine learning program called EWeLiNE which is helping grid operators with a program that can calculate renewable energy generation over 48 hours from the data taken from solar panels and wind turbines, through an early warning system.
Niche providers of Smart Energy products have been working with providing energy intelligence to consumers. UK start-up Verv, as an example, uses an AI-based assistant to guide consumers on energy management by tracing the energy usage data from appliances through meters and assisting in reducing costs. Increasingly, Utilities companies will partner with such niche providers to offer similar services to their customers.
Utilities companies have started using chatbots and conversational AI to improve customer experience. For instance, Exelon in the US is using a chatbot to answer common customer queries on power outages and billing.
While the predominant technology focus of Utilities companies is still on cost optimisation, infrastructure management and disaster management, the industry is fast realising the power of having an interconnected system that can transform the entire value chain.
For more insights from our AI Research, click below