Gridpocket - Version TSL - Big Data Platform Software
The deployment of smart meters in Europe and worldwide means appearance of unstructured energy data, that need to be stored, integrated, retrieved and analysed for which original high performance computer systems and algorithms have to be designed and evaluated. The energy data collected by metering infrastructure represents the biggest volume of smart grid energy-related data. In the domain of big data, it is a big challenge to store and manage these large volumes of data. In general data are cheap, but the value added information extracted from data is an article necessary to process and store. Big data architectures help to let machine understand and unveil the hidden association laws between data terms. Normally to assure this process, we store and manage large-scale structured or unstructured data in NoSQL databases, process in HDFS architecture or use cluster storage management.
TSL is able to provide the necessary smart grid analysis about :
- Clients consumption profile
- Baseline energy consumption
- Smart grid monitoring – performance and analytics
- Dissaggregation of clients energy consumption to discover heating or cooling energy usages
- Short term and long term load forecast for both utility managers and individual clients
The main tasks of BigData platform are to capture, communicate, aggregate, store and analyze big data to provide the statistical reporting for energy utilities and for further exploitation through energy applications developed by GridPocket and their partners.
Collecting, analyzing and managing smart metering data to create valuable information for customers is a complex and challenging task for Energy Utilities. Getting insights from the massive amount of meter data can produce substantial benefits for utilities- increase profit margins, optimize energy supply grid management and accelerate decision making process.
The architecture of cloud-computing big data platform enables the collection of energy data, clustering data, aggregation and more statistical analysis. It is connected to data collection platform built on oneM2M/ETSI M2M premises, which supports the high volume of connected devices and metering systems.
Scalable data analytics are necessary to assure an effective demand response management and peak load shifting for Energy Utilities. Statistical analysis of historical consumption (resampling, statistical summaries, aggregation, distance measure, variance, etc) developed by data scientists are the key to provide this necessary output.
The data cleaning for multiple formats, sources and technologies provides rich detail leading to value-added information. Sophisticated analytics can improve decision making and help to create new energy applications.
Big data uses cases in energy :
- Customer dashboard web applications
- Customer Segmentation
- Profiling consumption using internal and external factors (socio-demographics data, buildings information, weather data, electricity market)
- Public buildings open energy data
- Demand response management
- Peak load shifting
- Smart Grid balance
- Customers loyalty
- Consumption transparency
- Customer engagement
- Customer profiling
- Consumption analytics
- Machine to machine technology
- Programmable control