Multi-objective combined heat and power with wind–solar–EV of optimal power flow using hybrid evolutionary approach

The proposed effort aims to investigate efficient power generation while minimizing emissions, voltage deviations, and maintaining transmission line voltage stability. The combined heat and power of economic dispatch (CHPED) system is incorporated in the IEEE-57 bus in this presentation to ensure the best possible power flow in the transmission line while meeting the load demand. It is crucial to incorporate renewable energy sources for efficient power generation because fossil fuel sources are evolving daily. The main contribution of the proposed work is firstly, to find optimal solution for optimal power flow (OPF)-based combined heat and power economic dispatch (CHPED) problem with wind, solar and electric vehicles (EVs). The target is to find out maximum utilization of renewable energy sources for economic power generation, less emission and reduced transmission losses with maintaining the permissible voltage deviation at load buses. Thus, a new approach of electric vehicle to grid has been adopted with wind–solar-CHPED-based OPF system for improving grid reliability and resilience. Secondly, there is a requirement to overcome the local optima problems having low convergence speed. This is obtained by employing a relatively new methodology, known as chaotic-opposition-based driving training-based optimization (DTBO) (CODTBO). Due to the presence of wind, solar, EVs uncertainties, valve point effect, and transmission losses, the system grew more complex. For three different test systems for CHPED-based OPF with and without RESs, the proposed CODTBO algorithm has been put to the test. Results from the tested DTBO, ODTBO approach and the proposed CODTBO have been compared. After integrating wind–solar–EVs with CHPED–OPF, the total fuel cost and emission are reduced by 3.48% and 5.1%, respectively, as well as L-index is improved by 21.6%. Hence, it has been proved that proposed CODTBO has the capability to easily cope up with nonlinear functions. After adding chaotic-oppositional-based learning (CO) with DTBO (CODTBO), the fuel cost is further reduced by 1.65% and computational time is improved by 45% as compared to DTBO. Henceforth, CODTBO has the better exploration capability and better searching ability as compared to DTBO. The above numerical analysis demonstrated the superiority of the suggested CODTBO technique over DTBO, ODTBO in terms of convergence rate and best-possible solution. Moreover, by doing statistical analysis on IEEE CEC 2017 benchmark functions, the robustness of the suggested CODTBO optimization technique has been assessed.