Search

Technically, residential energy management systems are fundamental sectors in the smart grids for implementing demand response programs in the layer of households for managing energy consumption and reducing energy bills. The paper proposes a novel energy management scheme that takes production and usage into account based on a heuristic searching operation. In addition to modelling the grid, renewable energy sources, batteries, and electric vehicles, various kinds of electrical and thermal devices have been examined, including air conditioners, water heaters, vacuum cleaners etc. A method is developed for solving the objective constraint issue in a smart home in order to reduce energy consumption and determine feasible operation states among the various loads. Moreover, this paper proposes a grey wolf optimization method for solving the issue over a longer simulation period. Various cases were examined to evaluate the effectiveness of this suggested robust optimization algorithm. The outcomes show that the suggested model could not only reduce energy costs significantly but has also shown good performance for energy management purposes. [ABSTRACT FROM AUTHOR]

This paper introduces a hybrid algorithm that combines machine learning and modified teaching learning-based optimization (TLBO) for enhancing smart city communication and energy management. The primary objective is to optimize the modified systems, which face challenges due to their high population density. The proposed algorithm integrates the strengths of machine learning techniques, more specifically, the long short-term memory (LSTM) technique, with teaching learning-based optimization algorithms. To achieve optimization, the algorithm learns from historical data on energy consumption and communication patterns specific to the modeled system. By leveraging these insights, it can predict future energy consumption and communication patterns accurately. Additionally, the algorithm incorporates a modified teaching learning-based optimization approach inspired by the teaching and learning process in classrooms. It adjusts the system parameters based on feedback received from the system, thereby optimizing both energy consumption and communication systems. The effectiveness of the proposed algorithm is evaluated through a case study conducted on the test system, where historical data on energy consumption and communication patterns are analyzed. The results demonstrate that the algorithm efficiently optimizes the communication and energy management systems, leading to substantial energy savings and improved communication efficiency within the test system. In conclusion, this study presents a hybrid machine learning and modified teaching learning-based optimization algorithm that effectively addresses the communication and energy management challenges in the test system. Moreover, this algorithm holds the potential for application in various smart city domains beyond the test system. The findings of this research contribute to the advancement of smart city technologies and offer valuable insights into reducing energy consumption in densely populated urban areas. [ABSTRACT FROM AUTHOR]