In the current trend of consumption, electricity consumption will become a very high cost for the end-users. Consumers acquire energy from suppliers who use short, medium, and long-term forecasts to place bids in the power market. This study offers a detailed analysis of relevant literature and proposes a deep learning methodology for forecasting industrial electric usage for the next 24 h. The hourly load curves forecasted are from a large furniture factory. The hourly data for one year is split into training (80%) and testing (20%). The algorithms use the previous two weeks of hourly consumption and exogenous variables as input in the deep neural networks. The best results prove that deep recurrent neural networks can retain long-term dependencies in high volatility time series. Gated recurrent units (GRU) obtained the lowest mean absolute percentage error of $4.82\%$ for the testing period. The GRU improves the forecast by $6.23\%$ compared to the second-best algorithm implemented, a combination of GRU and Long short-term memory (LSTM). From a practical perspective, deep learning methods can automate the forecasting processes and optimize the operation of power systems.

Fuzzy-based control systems have demonstrated a remarkable ability to control nonlinear processes, a characteristic commonly observed in power systems, particularly in the context of power quality enhancement. Despite this, an updated and comprehensive literature review on the applications of fuzzy logic in the domain of power quality control has been lacking. To address this gap, this study critically examines published research on the effective and efficient use of fuzzy logic in resolving quality issues within power systems. Data sources included the Web of Science and academic journal databases, followed by an evaluation of target articles based on predefined criteria. The information was then classified into seven categories, including control system type, features of the fuzzy logic controller, fuzzy logic inference strategy, power quality issue, control device, implementation methodology (efficacy testing), and efficiency improvement. Our study revealed that fuzzy-based control systems have evolved from simple type-1 fuzzy controllers to advanced control systems (type-2 fuzzy and hybrid) capable of effectively addressing complex power quality issues. We believe that the insights gained from this study will be useful to both experienced and inexperienced researchers and industry engineers seeking to leverage fuzzy logic to enhance power quality control.

Short-term load forecasting predetermines how power systems operate because electricity production needs to sustain demand at all times and costs. Most load forecasts for the non-residential consumers are empirically done either by a customer’s employee or supplier personnel based on experience and historical data, which is frequently not consistent. Our objective is to develop viable and market-oriented machine learning models for short-term forecasting for non-residential consumers. Multiple algorithms were implemented and compared to identify the best model for a cluster of industrial and commercial consumers. The article concludes that the sliding window approach for supervised learning with recurrent neural networks can learn short and long-term dependencies in time series. The best method implemented for the 24 h forecast is a Gated Recurrent Unit (GRU) applied for aggregated loads over three months of testing data resulted in 5.28% MAPE and minimized the cost with 5326.17 € compared with the second-best method LSTM. We propose a new model to evaluate the gap between evaluation metrics and the financial impact of forecast errors in the power market environment. The model simulates bidding on the power market based on the 24 h forecast and using the Romanian day-ahead market and balancing prices through the testing dataset.

In contemporary society, electricity has become one of the most prevalent energy sources, with a global distribution network. The significance of energy efficiency has become a prominent subject of interest across various disciplines, leading to a notable surge in research on electricity over the last decade. The present paper explores the significance of examining power losses in power grids and proposes methods to identify and reduce them. The objective of this study is to methodically and systematically review existing databases to identify relevant studies pertinent to electricity losses in power grids. To this end, this study methodically categorizes energy losses into two primary classifications: technical losses and non-technical losses. To this end, two primary analytical approaches have been devised, providing a foundation for the prioritization of the most effective detection methods for each loss category, as well as the most recent findings in the literature on reducing these losses. The issue of power grid instability, stemming from fluctuations and voltage dips, was addressed, with power losses emerging as the primary source of concern. To this end, a comprehensive analysis of major academic databases, including Scopus, Web of Science, IEEE, and Google Scholar, was conducted to identify relevant research articles. This review introduces several important concepts for the energy field by introducing and analyzing the most relevant methods to identify and reduce power losses. The results of our study outlined the comprehensive analysis of 90 relevant studies on the benefits as well as the barriers encountered in the application of methods to identify and reduce electricity losses and the impact they have in the field under review. In conclusion, this paper emphasizes the importance of the in-depth study of the energy domain to achieve performance and contribute to the improvement of power grids. Future research directions are based on the implementation of artificial intelligence (AI) algorithms to achieve this goal.