Knowledge enhanced framework for managing electricity generation and consumption in micro smart grids using Heronian mean MCDM approach

With globalization and outsourcing trends, new and modern industrial enterprises frequently rely on a wide network of suppliers to construct sophisticated electricity generation and consumption. To maintain efficient production planning and scheduling, integration, and coping with the wide range of data from electricity generation to consumption management in a micro-smart grid has become increasingly critical. To manage the above dilemma, first, we develop circular intuitionistic uncertain linguistic models with basic laws. Secondly, we design four different types of techniques based on the above model, called the "arithmetic Heronian mean", "weighted arithmetic Heronian mean", "geometric Heronian mean", and "weighted geometric Heronian mean" models, with a few basic properties. Moreover, for the evaluation of the electricity generation and consumption management in a micro-smart grid, we construct a valuable and dominant model of the "multi-attribute border approximation area comparison" technique for derived approaches. Additionally, we discuss case studies for the proposed theory, which covers the usage of electricity generation and consumption in a micro-smart-grid for node classification, scenario classification, and link prediction. Finally, our solution will be ranked with the ranking models of prevailing models for analyzing the supremacy and efficiency of the derived approaches.