Accurate load forecasting is essential for optimizing microgrid and smart grid operations, thereby supporting Energy Management Systems (EMSs). Load forecasting also plays a key role in integrating renewable energy, ensuring grid stability, and facilitating decision-making. In this regard, we present a comprehensive literature review that combines both bibliometric analysis and critical literature synthesis to evaluate state-of-the-art forecasting techniques. Based on a screened corpus of over 200 scientific publications from 2015 to 2024, our analysis reveals a significant shift in the field: AI-based approaches, including Machine Learning (ML) and Deep Learning (DL), represent more than 55% of the analyzed literature, overtaking traditional statistical models. The bibliometric results highlight a 300% increase in publications focusing on ML-based models (e.g., SVM, CNN, LSTM) over the years. Furthermore, approximately 70% of the total reviewed works use at least one exogenous variable, such as weather variables, socioeconomic indicators, and cultural behavior. These findings reflect the transition from traditional statistical models to more flexible and scalable approaches. However, socioeconomic and cultural variables remain underutilized in the literature, particularly for long-term planning. Despite the progress load forecasting processes have made in recent years, thanks to advanced modeling, a few hurdles remain to realizing their full potential in modern microgrids. Thus, we argue that future research should focus on three key areas: (i) scalable real-time adaptive models, including computational complexity characterization, (ii) standardization in data collection for seamless integration of exogenous variables, and (iii) real-world application of forecasting models in decision-making that supports EMSs. Progress in these areas may enhance grid stability, optimize resource allocation, and accelerate the transition to sustainable energy systems.

The estimation of spectral spacing (guard band) among optical channels in gridless WDM systems would be decisive for making swift decisions in reconfigurable optical add-drop multiplexers (ROADMs) to avoid linear interchannel interference (ICI) effects during the channel aggregation process in transit nodes. In this work, we propose a method based on the construction of heat scatter images from constellation diagrams along with convolutional neuronal networks (CNN) to identify when optical channels are spectrally overlapped as well as the value in GHz of the channel separation in a specific optical channel without adjacent channels information. We validate our method in a gridless 16-QAM Nyquist-WDM system with different channel spacing and optical signal-to-noise ratio (OSNR). Experimental results demonstrated that overlap detection can be achieved with 3×16GBd accuracy. Additionally, the estimation of spectral spacing achieved an error (RMSE) of less than 0.6 GHz. The penalty in accuracy and RMSE is only ∼98% and , respectively, when there is no knowledge of the OSNR value. Thus, this method has the potential to be integrated into monitoring tools designed for future dynamic gridless optical transmission systems.

Accurate load forecasting is essential for optimizing the operations of microgrids and smart grids, which supports efficient energy management. Additionally, precise demand forecasting is crucial for integrating renewable energy sources, maintaining grid stability, and improving decision-making processes. In this paper, we present a literature review that employs a methodology combining a bibliometric analysis with a critical literature synthesis to evaluate state-of-the-art load forecasting techniques. The bibliometric analysis reveals a growing research focus on data-driven forecasting techniques, highlighting the increasing integration of Artificial Intelligence (AI) methods in energy demand prediction. Key trends include adopting smart grid technologies, using Machine Learning (ML) and Deep Learning (DL) architectures, and incorporating external factors such as climate variables and socioeconomic indicators. These trends underscore the shift from traditional statistical models to more adaptive and scalable approaches. The robustness of these techniques is further strengthened by the role of hybrid models (approaches that combine different forecasting techniques, such as statistical methods with ML or DL algorithms) to leverage their complementary strengths. These models often achieve higher accuracy and better adaptability across diverse operating conditions. External factors significantly impact forecasting models, capturing demand fluctuations and renewable energy source variability, allowing accurate modeling of real systems. Future research should focus on developing scalable, real-time adaptive models that integrate external data streams and advanced hybrid techniques, enhancing grid stability, optimizing resource allocation, and facilitating sustainable energy systems transition.