Machine learning‐based energy efficient technologies for smart grid

Abstract

The smart grid will allow substantial electricity savings and peak demand savings by potentially supplying utility power for direct load management, the calculation in support of competitive pricing, and even the granular data required for energy usage to be more targeted explicitly at customer needs, the processing of data and predictions for a smart grid in a building with the energy profile and occupants' profile, is challenging. This article has been suggested a Machine Learning-Based Energy-Efficient Framework to analyze the motion of occupants, deliver short-term energy forecasts, and assign renewable energy in the smart grid. Second, an indoor localization device with wireless data analysis collects occupants' profile, and the energy profile is managed by a real-time smart meter network with an electrical charge evaluation. Furthermore, the energy profile and 24-hour profile will be paired with a forecast utilizing an online machine learning framework with an analysis of data in real-time. To decrease peak demand for the primary power grid, the solar energy source is assigned to the further power grids based upon the forecast occupant movement profile and energy consumption profile. On the smart gateway network, the complete power flow with minimal computing resources and a general enabled engine can be controlled. The results of the studies on real-time datasets show that the precision of the suggested energy forecast will increase significantly when compared to the other existing methods.

Performance Analysis of an Optimized ANN Model to Predict the Stability of Smart Grid

“…In the smart grid, work like assigning renewable energy resources, delivering short-term energy forecasting, and sensing the motion of the occupants are to be analyzed to enhance its efficiency. Yao et al use machine learning models for the same and have given Machine Learning Energy-Efficient Framework (MLEEF) [14]. e authors used solar energy for this study.…”

Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting

“…5 Flexible computing methods based on user experience such as the genetic algorithm (GA), fuzzy logic, and neural networks are also used. [6][7][8] To predict short-term electricity demand, Vu et al proposed an autoregressive-based time varying model and determined that this model performed better than traditional seasonal autoregressive and neural network models in short-term electricity forecasting. 9 Muhanad et al performed electricity demand forecasting using Autoregressive Integrated Moving Average, Multivariate Adaptive Regression Spline (MARS), and Support Vector Regression (SVR) methods.…”

“…Mathematical modeling includes methods such as regression analysis, multiple regression, curve fitting, least squares technique, and the Box–Jenkins approach 5 . Flexible computing methods based on user experience such as the genetic algorithm (GA), fuzzy logic, and neural networks are also used 6‐8 . To predict short‐term electricity demand, Vu et al proposed an autoregressive‐based time varying model and determined that this model performed better than traditional seasonal autoregressive and neural network models in short‐term electricity forecasting 9 .…”

Privacy boundary determination of smart meter data using an artificial intelligence adversary

“…Moreover, the high granularity of data boosts artificial intelligence (AI) applications in smart grids. The AI data analysis and data mining tools (such as machine learning/deep learning) have been widely adopted in smart grid applications, such as short‐term load forecasts, renewable energy management, and nonintrusive load monitoring (NILM) 2 . However, smart meter and AI applications are double‐edged swords since they introduce severe privacy issues to consumers.…”

“…The AI data analysis and data mining tools (such as machine learning/ deep learning) have been widely adopted in smart grid applications, such as short-term load forecasts, renewable energy management, and nonintrusive load monitoring (NILM). 2 However, smart meter and AI applications are double-edged swords since they introduce severe privacy issues to consumers. By adopting AI mining algorithms on smart meter data (such as NILM), the adversary can easily infer personal information from smart meter data.…”