SMART COMMUNITY NEIGHBOURHOODSThe current electricity infrastructure lacks mechanisms to handle mass and concentrated energy demands primarily led by Electric Vehicles (EV) charging requirements. A potential mechanism to handle such surges during peak consumption hours without restructuring the grid is through integration of renewable micro energy sources at household or neighborhood levels. It becomes necessary to efficiently harness the potential of prosumers and develop tools to efficiently manage household/neighborhood energy production and consumption. Mechanisms are needed to pool upon the combined micro energy sources, integrate community level power storage units, predict production and consumption and allow sharing/trading of energy between households, neighborhoods and communities.
ICT based smart-solutions can be used to substantially address and resolve such challenges. Data driven decentralized energy systems can disrupt the existing simplex supply-demand market relationship between producers and customer. With supporting environment-friendly energy production and storage technologies, conventional end customers will be able to produce clean energy locally (e.g. solar energy micro-generation). It would allow them to either meet their own requirements or sell it back to the grid. Meanwhile, the EV batteries could also be added as additional resource to the local energy storage systems. Such resources will be able to store locally generated power and have the capability to spontaneously participate in balancing consumption fluctuations. It will be particularly applicable for fluctuating intensive loads (e.g. heating, charging) and to solve congestion problems.
These innovations in the energy ecosystem can be addressed through competence in what can be termed as a smart community neighborhood. Upstream suppliers like Distribution System Operators (DSO) and Transmission System Operators (TSO) need community level data insights to manage power distribution, transmission and integration of community level resources. This would enable them to guarantee reliable and safe operations. However, these data streams from homes in every community and its resources could be exponentially large. Therefore, a high information intensive data hub capable of addressing such large and diverse data streams is required. It should also provide responsive and near real time insights. Advancements in blockchain based techniques could record energy generated, shared or traded by prosumers and stored into a local or community level storage resource. Machine Learning techniques can be used to predict energy prosumption during peak periods between households, neighborhoods or communities.
Fog computing for real time monitoring and distributed microgrid resilience. We will study the role of fog computing for the smart energy system; and gain understanding on how fog computing can significantly improve the performance of the energy system.
Machine learning and deep learning for energy forecasting. Precise forecasting is very important for the stability of the future energy systems. We will study predictive analytics techniques for power stability, including regression, neural networks and other machine learning approaches for real-time and historical analytics. In addition, the renewable energy forecasting will be an important problem in this topic.
Blockchain solutions to created decentralized applications to allow local and community level energy trading. Creating systems to incentivize and improve adherence for households to participate in a smart community neighborhood.
Data security and privacy measure using anonymization, differential privacy to protect sensitive information about households. Smart Meter, appliance usage, micro production and consumption data from each household could reveal detail lifestyle information about individuals and households. It is necessary that proper security mechanisms are maintained to in any form of data storage, transfer or communication. Additionally, privacy preserving mechanism also needs to be established to balance data utility and data privacy.