Niharika Singh - Postdoctoral Researcher & AI Consultant | Reinforcement Learning Expert

Research-oriented Approach

Her research work is focused on exploring grounds of positive transformation in the world using Machine Learning (ML) (Specialise in Reinforcement Learning (RL)) based innovative programming techniques.

-Research EXperience-

Project: Data Protection Protocols and approaches in cloud computing

The project was to study a cloud computing environment and provide privacy to the highly sensitive electronic data. To achieve the goal, we categorized the privacy-preserving approaches into four categories, i.e., privacy by cryptography, privacy by probability, privacy by anonymization and privacy by ranking. Four methodologies were proposed based on these categories and their performance was compared. Methodologies were focused on the fact that the mechanisms should be developed to deploy efficient auditing and accountability mechanisms that anonymously monitor the utilization of data records and track the provenance to ensure the confidentiality of the data.

Project: Digital Control System for Electrical Gas District Cooling (GDC)

GDC is a green energy based power plant system. The project aimed to make this GDC autonomous by maintaining a synchronization between the electrical and communication system of the electronic grid. Also, to improve continuity and reliability of services by ensuring the plant produces optimum power. The GDC provides ease of operation and minimum maintenance to the equipment connected by encouraging efficient power distribution and utilization. Another aspect is the standardization of the system components and communication for maximizing interconnectivity support and minimizing stockholding while providing safety to the personnel during operation and maintenance of the plant.

Project: Grid Management using Multi Agent System in Microgrid”

The communication network in Microgrid is a very complex and time-variant system that needs to reserve network resources to count on several possible situations of failure resulting in limited recovery ability and inefficient resource utilization. The network link failure can lead to imbalance network load, increased packet loss ratio, higher network recovery delay. The project was focused to enhance the intelligence of microgrid networks using a routing-oriented multi-agent system and reinforcement learning (RL) while performance assessment is carried out using network performance metrics. Network performance is analyzed for the small, medium and large scale microgrids using the IEEE reliability test systems.

CousCOUS-university of Helsinki

In the fight against climate change and coping with pressures arising from urbanization, cities worldwide provide solutions for modifying air pollutant emissions and thermal comfort. The project answers to possible challenges of air quality by helping cities plan climate-healthy urban areas, considering future traffic flows and population structures alike. It combines the fields of artificial intelligence, atmospheric and social sciences to an unprecedented extent and therefore advances the state of scientific research in all disciplines involved. The project provides decision-makers and city planners globally with novel, relevant information and tools for creating future sustainable cities. The consortium utilizes and analyzes high-resolution data from various sources, including population, climate and traffic data, and works tightly both together as well as in co-operation with relevant stakeholders.