A novel computational paradigm for scheduling of hybrid energy networks considering renewable uncertainty limitations

Numerous developing countries are currently grappling with energy crises due to the current surge in global fossil fuels prices. This situation has prompted policymakers and cities administrator to urgently seek alternative power sources. Scientists worldwide are actively working on innovative computational methods to address the coordination challenges faced by hybrid power systems. Their objective is to optimize the utilization of environmentally friendly hybrid power sources, such as clean energy sources (CESs) like wind and solar power, within the framework of traditional hydro -thermal coordination. This research aims to examine how integrating CESs into conventional energy delivering hydro -thermal coordination model can minimize the significant costs associated with energy production. The proposed approach involves constructing a probabilistic model to represent the hybrid energy coordination problem. To handle uncertainties related to CESs, a technique known as point estimation is employed. This technique employs Weibull and Beta distribution functions to handle uncertain input variables associated with wind and solar power. The present study employs an optimization paradigm that integrates the black widow optimization (BWO) algorithm with the radial basis function neural network (RBFNN). This paradigm not only considers the uncertainties in the system but also adapts its parameters to attain an optimum balance among the exploration as well as exploitation phase. Within the context of advancing energy transition the outcomes of our simulations demonstrate a significant achievement. The incorporation of CESs into the hydro -thermal coordination problem yields a substantial 10 percent reduction in operational costs and an impressive 64 percent decline in emissions. The convergence curves of the proposed scheme reveal that the presented hybrid computing paradigm quickly converges to the optimal solution, attaining the best global optimum solution. Three case studies have been conducted, in Case Study -I, the best attained optimal cost and emissions are $3.6e4/day and 2.8e4 lb/day, respectively, with photovoltaic and wind energy costs at $1148/day and $3055/day, respectively. For Case Study -II, a complex function, emissions of 15887.42 lb/day and an energy production cost of $26072.89/day are achieved. For Case Study -III, the optimal cost of $26558/day and emissions of 12932 lb/day are acquired using the proposed approach. This valuable research contribution holds particular significance for the economic empowerment of developing nations. By diminishing their reliance on imported fossil fuels for energy generation, it paves the way for enhanced self-sufficiency. Moreover, the findings provide a well-defined pathway towards fostering sustainable and environmentally friendly energy production within urban settings. Additionally, the research highlights the transition from fossil fuel -dependent industries to the establishment of sustainable urban economies.