Driven by data: the new era of the energy sector

The deployment and use of new generation renewable energy generation alongside conventional means has triggered a major transformation process within the energy sector, in which not only the technology but also the business case is changing.

The traditional approach typically allows for reactive maintenance and fault management. Without a perfect knowledge of the systems' load capacity and health, critical infrastructure operations require oversized spares, spare parts, well-trained mobile troubleshooting and service teams for continuous operation. Unplanned outages and disruptions lead to lost production that disrupt schedules, which are especially critical during the summer when extreme weather conditions can keep the network operating at high power levels.

Green and diversified energy generation and storage assets allow greater flexibility to quickly manage consumption peaks and efficiently correct any disruptions, and the systems supporting these assets now almost invariably use modern IoT and IT tools to collect generation data, events, and to monitor and manage production.

However, the simultaneous use of traditional and new devices and approaches in energy networks has continued to preserve the occurrence of unplanned outages, disturbances, anomalies caused by extreme conditions and has not facilitated the cost-effective use of reserves.

Technical data warehouses, together with advanced predictive analytics systems, offer a solution to manage these unexpected and costly events, and provide an opportunity to reduce expensive oversized reserves and integrate them into active production.

For this reason, the use of technical data warehouses and the services they overlay increasingly appears to be a market-driven development for industry players.

It is possible to get off this train, but this will mean guaranteed business disadvantages in the short and medium term. The good news is that this train can be hopped on to take us to a more modern, next generation operating model with all its benefits.

What are these benefits and what does a technical data warehouse need to know, and how can we link it to enterprise systems?

The use and functionality of modern analytic-preventive systems based on a technical data warehouse gives the edge that is needed in this critical sector.

• Energy technical data warehouses collect data from various sources, such as:

• Electricity generation and consumption and related quality parameters

• Gas and oil consumption

• Renewable energy sources (solar, wind, hydro)

• Performance indicators for energy networks and distribution systems

• Environmental data such as weather information

Data can be collected using real-time sensors, smart meters and other monitoring systems. Data warehouses are able to handle large amounts of structured and unstructured data, which are stored and organised over a long period of time.

Using the collected data, supporting functionalities such as advanced alarm and case management event recording, data-based event replay and analysis capability, which can be used for prediction and prevention by energy service providers and energy communities to optimise their services, can be built up, based on pattern recognition using holistic models.

What elements can an analytical system based on a technical data warehouse (Asset Performance Management - APM) consist of beyond the usual data warehouse functionality?

Predictive monitoring based on a data model:

• Model-based validated templates - (e.g. engine start, valve timing start characteristics, power ramp-up characteristics, etc.)

• Event recording, evidence and reporting

• Performance monitoring

• Comprehensive case management and knowledge base building according to Continual Improvement principles

• Management and diagnostics of faults, alarms, alerts

• TUFF - Time Until Failure Foreceast

• Transient analysis and replay (capture and evaluation of high density data)

• Instrument comparison, benchmarking, analysis

Problem analysis:

• Digital Twins - Data- and behaviour-based virtual replica of physical objects (e.g. building, subnetwork, HMKE group) where events can be simulated and interventions tested.

• Interpretation of the correlation of signals, values in accordance with error reporting

• Predicted states of sensor signals vs. actual values

• Visualisation and contextualisation of received data

• Searching for roots and setting fault chains

• Building error probability models

• Back-testing corrective actions

• Risk level determination (Time to Failure Forecast)

• Compilation of fault management and remediation instructions

Incorporation of experience and multi-level comments and insights into the data model

AI:

• The use of AI/Machine Learning based on technical data warehouse data can significantly increase efficiency and have a significant impact:

• Trend detection - predictive error management

• Data-driven decision making

• Anomaly search and detection

The question often arises whether existing data warehouses full of economic data can be used to process and store data from production. The question is legitimate and the answer may not seem simple at first, but the criticality of the sector suggests that for security reasons it is advisable to keep production data completely separate.

In conclusion, a technical data warehouse with well-designed functionality provides the following benefits for the different actors in the sector:

Energy traders

• More accurate forecasts, schedules

• More optimal consumption patterns, loads

• Increased planning and operational efficiency

• Up-to-date grid connection point and load profile information

• Mapped network technical parameters and constraints

• More flexible management of existing control and reserve capacities

• Development of extensive decision support functions to optimise operations and improve market position

  • Public HMKE database

  • Price forecasting and risk management

  • Portfolio optimisation

  • Calculation of compensation linked to aggregators' activities

TSO

• Transfer of accurate network load patterns for regional planning

• Operational decision support

• Historical replay of anomalies

DSO

• Decision support functions - to optimise operations, improve market position

• Production forecast refinement

• Determine distributor smart tariff

• Provide distributor network resilience services

• More informed emergency response planning

• Optimisation of maintenance and network development

• Historical replay of anomalies

Aggregators

• More accurate compensation settlement service

• Development of HMKE forecasting and scheduling

Energy communities

• Energy sharing - accounting: providing static and dynamic accounts

• Optimisation of scheduling

• Develop energy sharing strategies

Customers - consumers, producers

• Availability of energy consumption and production data

• Customizable information package

Last but not least, it can be stated that data-driven planning of investments, reduction of OPEX costs on the farmer side, improvement of performance, production balance, OEE indicators on the production side, increase of system availability, increase of asset and system lifetime, early detection and elimination of failures on the maintenance side are all values that bring demonstrable savings to the technical data warehouse builder.