Multi-Objective Optimization of Energy Systems in Smart Grid in Connection with Renewable Energy Communities Considering Source and Consumption Variability

In this project, we will develop a multi-objective and hybrid energy optimization framework for the optimum system cost and energy cost savings with a tolerable degree of customer discomfort. This framework will be based on artificial intelligence (AI) and artificial neural network (ANN) approaches for forecasting to track for maximum green energy production with the help of SG and REC. These goals and objectives will be achieved by utilizing optimization techniques like genetic algorithm (GA), binary particle swarm optimization, wind driven optimization, fuzzy logic, HGSO to acquire all sets of solutions. The compromise solutions will then be chosen using hybrid, decision-making, and multi-criteria techniques, such as Pareto-optimal, AHP and VIKOR approaches. Moreover, incentive-based DR programs are adopted to cope with the uncertainties resulting from power generation by RESs. In addition, SOs suggested DR programs and a proposal for the use of price-offer packages for consumers must be implemented. It is proposed to use a multi-objective scheduling model and recommend the Pareto criterion with nonlinear sorting based on fuzzy logic and heuristic algorithms. Lastly, comparing results between different pricing schemes will be done by adopting and merging time of use (ToU), inclined block rate, flat pricing, and day-ahead pricing.

Faculty Supervisor:

Muhammad Mazhar Ullah Rathore

Student:

Partner:

Università degli Studi di Roma Tor Vergata

Discipline:

Computer science

Sector:

Education

University:

Lakehead University

Program: