Data Analytics in Smart Grids
Data analytics is now playing a more important role in the modern industrial systems. Driven by the development of information and communication technology, an information layer is now added to the conventional electricity transmission and distribution network for data collection, storage and analysis with the help of wide installation of smart meters and sensors. Smart grid is the power system embedded with an information layer that allows for two-way communication between the central controllers and local actuators as well as logistic units to respond digitally to urgent situations of physical elements or quickly changing of electric demand. The E.U. defined the smart grid as electricity networks that can intelligently integrate the actions of all users connected to it — generators, consumers and those that do both — in order to efficiently deliver sustainable, economic and secure electricity supplies. While the Microgrid which is a type of a standalone grid system is a small-scale distribution grid with distributed generation which provides electricity even during a grid failure by energy storages and load dispatch techniques. The increase of metering devices at smartgrids and the improvement of data analysis has paved the way for mitigating some of the unreliable challenges in our electric grid which now makes them a futuristic renewable energy technology that can replace the use of diesel fuel eliminating CO2 emissions.
High-resolution user consumption data can also be used for customer behavior analysis, demand forecasting and energy generation optimization. Predictive maintenance and fault detection based on the data analytics with advanced metering infrastructure are more crucial to the security of power system. Thus, the great progress of information and communication technology (ICT) provides a new vision for engineers to perceive and control the traditional electrical system and makes it smart. An embedded information layer into the energy network produces huge volume of data, including measurements and control instructions in the grid for collection, transmission, storage and analysis in a fast and comprehensive way. It also brings a lot of opportunities and challenges to the data analysis platform. With Advanced Metering Infrastructure(AMI),mass collection of data from smart meters, Phasor Measurement Units (PMUs),Remote Terminal Units (RTUs), Intelligent Electronic devices (IEDs) and centralized control systems (e.g. SCADA), get collected towards the network operators from the consumers. These data can be mainly divided into two categories: structured and unstructured data. Equipment parameters, load dispatch control, states of equipment are examples of structured data while weather and geographical data, customer service and web service data are examples of unstructured data The use of data analysis techniques today plays a significant role in improving the reliability and decision-making process in smartgrids while ensuring automatic control.
The smart grid is associated with a vast amount of data from various sources, including power system operation (generation, transmission, and distribution, customers, services and markets), energy commodity markets (electricity markets, gas, and oil), environment, and weather. Those data are characterised by a diversity of its sources, growth rate, spatio- temporal resolutions, and huge volume. It is anticipated that future power grids will generate heterogeneous data at a higher rate than ever. On the one hand, this vast amount of data creates several challenges for data handling, processing, and integration to a utility decision framework. On the other hand, these large datasets provide significant opportunities for better monitoring, control, and operation of electric grids. In particular, this can help electric utilities to make the system more reliable, resilient, and efficient. Therefore, big data analytics is perceived as a foundation to optimise all current and future smart grid technologies.
Data analytics in smart grid application is designed to identify hidden and potentially useful information and patterns within large datasets that can be transformed into actionable outcomes/ knowledge. It utilises various algorithms and procedures (e.g. clustering, correlation, classification, categorization, regression, and feature extraction) to extract valuable information from the dataset gotten from end user or electric utility companies. Depending on the potential use cases, the analytics involves one or more of the descriptive, diagnostic, predictive, and prescriptive analytics. Descriptive models are often used to describe operational behaviours of grid and customers, whereas diagnostic models analyse the operating conditions and decisions made by the grid operators. The diagnostic model is focused on identifying the causes for an event, thereby is suitable for taking remedial action. As the key objective of data analytics is to provide a preventive solution, predictive models are often necessary to forecast operating conditions and future decisions. Prescriptive analysis, on the other hand, is designed for providing longer term insights to utilities in making strategic operational and investment planning.
From the smart grid application perspective, data analytics can be categorised into four broad categories .
Event analytics primarily covers diagnosis/detection of the power systems events such as faults and outage managements. In addition, event analytics also encompass a descriptive analysis of prior power system events using various techniques (e.g. classification, filtering, and correlation). Detection of abnormal operating conditions including fault detection, system outage detection, detection of malicious attacks, and theft of electricity are some of the key application areas for event analytics.
State and operational analytics primarily include a combination of diagnostic, predictive, and perspective analytics; the key power system application of the state analytics includes state estimation system identification and grid topology identifications. The key power system applications for operational analytics include energy/load forecast, energy management and dispatch of resources.
Customer analytics also includes one or more of the descriptive, diagnostic, predictive, and perspective analytics depending on the specific applications and use cases. The key power system applications that falls under the customer analytics include customer classification, the correlation between consumer behaviour and energy consumption patterns and demand response.
Intelligent Data Collection Devices in Smart Grids
As many IoT systems, a typical smart grid consists of the following layers: the sensor network, the integration (or concentration), storage and processing, visualization. The main components of the system are power meters, climate sensors, the data integration component, the data warehouse server, the IoT platform, the asset management system with 2D and 3D visualization components. The devices are aimed at collecting datasets for intelligent control algorithms learning and assessment. Prospective applications (energy disaggregation, load forecasting, demand-side management, learning network structure from data, collaborative energy storage use) impose strong requirements on all its physical and logical layers: sensors, data collection, storage and processing, analysis and visualization. A combination of open-source IoT components and modern hardware are typically chosen to provide a convenient and cost-efficient solution.
Modern telecommunication industry provides many wireless and wired technologies, which can be used to build IoT network and transport infrastructure; most energy meters can be located in several switchboard rooms. Therefore, it is quite natural to build the economic solution using the cable infrastructure for wired communication, and taking into account the available interfaces with multiply media access that can be used to minimize wires. It is reasonable for a large building to connect sensors using low-power wide-area networks (LPWAN) and to power them with non-rechargeable batteries. Such an approach provides fast and easy deployment of sensors network at low cost.
Another important function is integration of the sensor and meters networks with the IoT platform. The data from the grid server and from energy meters are collected with simple custom scripts that implement the finite state machine paradigm on Node JS platform. For each subsystem and for each ethernet converter the data are collected with separate scripts that work in parallel. To collect the data, the script connects to the meters using TCP socket and LoRaWAn server using WebSocket protocol. The collected data is sent to the IoT platform using MQTT protocol. For visualization, several useful dashboards to monitor the climate and energy sensors are designed. A summary dashboard is used by the system maintenance crew for real-time monitoring of the energy system state. In summary, to collect datasets for promising IoT applications like the smart grid, the complex informational and communication systems should be deployed.
The Interdependency of Data Analytics and Cloud Computing
Cloud computing approach is a promising solution for computation intensive grid applications because it uses computational resources based on demand. Cloud computing has distinct advantages, such as scalability, flexibility, distributed computing, parallelisation, fast retrieval of information, interoperability, virtuality, and extensibility. Recently, cloud computing has been applied to energy conscious scheduling in smart grids. The deployment of cloud computing to smart grid brings several benefits, including increased fault tolerance and security due to multi-location data backup. Moreover, cloud computing helps utilities to realise flexibility, agility, and efficiency in terms of saving cost, energy, and resources. Many smart grid applications, including AMI, SCADA, energy management system, and distribution management systems, can be greatly benefited by the application of cloud computing approach.
A smart grid has the capacity of providing electricity even during a grid failure. Compared to traditional grids, these distribution systems have a significant challenge due to intermittent nature of renewable energy sources, providing protection and identifying the possible occurrence of islanding during an event of grid failure. With the growth of Advanced metering infrastructure (AMI) and sensor devices as IoT, equipment parameters, states of equipment, weather and geographical data can be collected.
The advancement in data mining and data analysis, enhancing how these data should be handled is apparent. They can be used in providing a reliable supply to consumers in grid planning and operations not limited to forecast and control but in protection, fault identification and data security and privacy areas too. Since smartgrids are becoming quite popular with a lot of data, it is timely to investigate most of the recent developments in deep learning structures for deploying artificial intelligence in a commercial scale.
