According to privatization and deregulation of power system, accurate electric load forecasting has come into prominence recently. The new energy market and the smart grid paradigm ask for both better demand side management policies and for more reliable forecasts from single end-users, up to system scale. However, it is complex to predict the electric demand owing to the influencing factors such as climate factors, social activities, and seasonal factors. The methods developed for load forecasting are broadly analyzed in two categories, namely analytical techniques and artificial intelligence techniques. In the literature, commonly used analytical methods are linear regression method, Box-Jenkins method, and nonparametric regression method. The analytical methods work well under normal daily circumstances, but they can't give contenting results while dealing with meteorological, sociological or economical changes, hence they are not updated depending on time. Therefore, artificial intelligence techniques have gained importance in reducing estimation errors. Artificial neural network, support vector machine, and adaptive neuro-fuzzy inference system are among these artificial intelligence techniques. In this paper, a state-of-the-art review of three artificial intelligence techniques for short-term electric load forecasting is comprehensively presented.

Over the past decade, energy forecasting applications not only on the grid side of electric power systems but also on the customer side for load and demand prediction purposes have become ubiquitous after the advancements in the smart grid technologies. Within this context, short-term electrical energy consumption forecasting is a requisite for energy management and planning of all buildings from households and residences in the small-scale to huge building complexes in the large-scale. Today’s popular machine learning algorithms in the literature are commonly used to forecast short-term building electrical energy consumption by generating an abstruse analytical expression between explanatory variables and response variables. In this study, gene expression programming (GEP) and group method of data handling (GMDH) networks are meticulously employed for creating genuine and easily understandable mathematical models among predictor variables and target variables and forecasting short-term electrical energy consumption, belonging to a large hospital complex situated in the Eastern Mediterranean. Consequently, acquired results yielded mean absolute percentage errors of 0.620% for GMDH networks and 0.641% for GEP models, which reveal that the forecasting process can be accomplished and formulated simultaneously via proposed algorithms without the need of applying feature selection methods.

As the global energy landscape evolves towards sustainability, the extensive usage of fossil fuels in electricity generation is progressively diminishing, while the contribution of renewable energy sources is steadily increasing. In this evolving scenario, the importance of load forecasting cannot be overstated in optimizing energy management and ensuring the efficient operation of industrial plants regardless of their scale. By accurately anticipating energy demand, industrial facilities can enhance efficiency, reduce costs, and facilitate the adoption of renewable energy technologies in the power grid. Recent studies have emphasized the pervasive utilization of machine learning-based algorithms in the field of electric load forecasting for industrial plants. Their capacity to analyze intricate patterns and enhance prediction accuracy renders them a favored option for enhancing energy management and operational efficiency. The present analysis revolves around the creation of short-term electric load forecasting models for a large industrial plant operating in Adana, Turkey. The integration of calendar, meteorological, and lagging electrical variables, along with machine learning-based algorithms, is employed to boost forecasting accuracy and optimize energy utilization. The ultimate objective of the present study is to conduct a thoroughgoing and detailed analysis of the statistical performance of the models and associated error metrics. The metrics employed include the R² and MAPE values.

Photovoltaic (PV) power generation may vary with respect to several factors such as solar radiation, temperature, power conditioning units, environmental effects, and shading conditions. The partial shading of PV modules is one of the most crucial factors that causes the performance degradation of PV systems. The main reason for efficiency reduction under partial shading conditions is the creation of multiple local maximums and one global maximum operating point. The classical Maximum Power Point Tracking (MPPT) algorithm fails to determine the global maximum operating point to prevent power losses under partial shading conditions. In this study, a novel hybrid MPPT method based on Perturb & Observe and Particle Swarm Optimization that mainly aims to determine global operating point, is proposed. The proposed hybrid MPPT method is tested under different partial shading conditions and variable irradiance levels. In this manner, the dynamic response of the system is remarkably increased by the proposed MPPT method. To show the superiority of the developed method, a performance comparison is conducted with the P&O- and Kalman-Filter-based MPPT methods. The obtained results illustrate an improvement around 1.5 V in undershoot voltage and 0.2 ms in convergence speed. In addition, the overall system efficiency of the PV system is increased around 2% when compared to the P&O- and Kalman-Filter-based MPPT methods. Consequently, the proposed method seems to be an efficient method in terms of undershoot voltage, convergence time, tracking accuracy, and efficiency under partial shading conditions.

As the global energy landscape evolves towards sustainability, the extensive usage of fossil fuels in electricity generation is progressively diminishing, while the contribution of renewable energy sources is steadily increasing. In this evolving scenario,importance of load forecasting cannot be overstated in optimising energy management and ensuring the efficient operation of industrial plants regardless of their scale. By accurately anticipating energy demand, industral facilities can enhance efficiency, reduce costs, and facilitate the adoption of renewable energy technologies in the power grid. Recent studies have emphasised the pervasive utilisation of machine learning-based algorithms in the field of electric load forecasting for industrial plants. Their capacity to analyse intricate patterns and enhance prediction accuracy renders them a favoured option for enhancing energy management and operational efficiency. The present analysis revolves around the creation of short-term electric load forecasting models for a large industrial plant operating in Adana, Türkiye. The integration of calendar, meteorological, and lagging electrical variables, along with machine learning-based algorithms, is employed to boost forecasting accuracy and optimize energy utilization.The ultimate objective of the present study is to conduct a thoroughgoing and detailed analysis of statistical performance and associated error metrics. The metrics to be employed include the R², MAE, RMSE, and MAPE.