Open research questions in Energy Load and Power Forecasting
134 unresolved questions extracted from the limitations and future-work sections of 631 Energy Load and Power Forecasting papers in our library. Each links back to the study that raised it.
What the literature leaves open
The intermittent and highly volatile characteristics of PV power generation introduce substantial uncertainty to grid scheduling and energy management. Prior methods have limitations in handling non-stationary photovoltaic (PV) time-series. There is a need for accurate ultra-short-term forecasting to accommodate and integrate the increasing solar production.
The random production characteristics of wind energy lead to grid flexibility and reliability issues. The lack of systematic feature selection methods in wind energy production prediction. The need to handle missing observations in the meteorological dataset.
Improving wind power prediction performance using the SKB-FA-XGB method based on hybrid feature selection · 2026 · DOIPrior studies have mostly used single-stage feature selection approaches. The lack of systematic feature selection methods in wind energy production prediction. The need for a hybrid approach that combines statistical filter and meta-heuristic algorithm.
Improving wind power prediction performance using the SKB-FA-XGB method based on hybrid feature selection · 2026 · DOIConventional forecasting models struggle to distinguish heterogeneous patterns in the observed series. Redundant meteorological input data may hinder the learning process. The difficulty of capturing periodic patterns, abrupt local changes, and short-term fluctuations in net-load time series.
Further research on hybrid models that combine interpretability with high predictive accuracy is needed - Investigation of the link between data typology and modeling approach is necessary
The accuracy of the Weibull distribution for wind-speed measurements, particularly for shorter time periods, is still an open question. There is a need for a systematic investigation of the accuracy of the Weibull distribution and its comparison with other possible distributions.
The increasing integration of renewable energy sources into power systems has introduced greater volatility into electricity generation. The need for accurate forecasting of future supply and demand is crucial for efficient power distribution and utilization. The lack of large datasets for training and testing medium-term electricity generation forecasting models.
The lack of studies on medium-term electricity generation forecasting. The limited use of transfer learning methods based on zero-shot learning in energy forecasting. The need for a novel approach to address the gap in medium-term electricity generation forecasting.
The inherent nonlinearity and uncertainty in energy consumption data. The complexity of interactions between energy usage and meteorological data. The need for integrated energy management strategies to address significant interdependencies among energy usage metrics.
Advanced Machine Learning Techniques for Energy Consumption Analysis and Optimization at UBC Campus: Correlations with Meteorological Variables · 2024 · DOILimited knowledge on process parameters, - The accuracy decreases as the forecast horizon lengthens, - The multi-step approach encounters challenges in representing different operational phases of the furnace
Tackling Uncertainty: Forecasting the Energy Consumption and Demand of an Electric Arc Furnace with Limited Knowledge on Process Parameters · 2024 · DOIAvailable models exhibit limitations in predicting energy consumption. There is a need for a statistic-stochastic energy consumption forecast model based on non-perfect knowledge.
Tackling Uncertainty: Forecasting the Energy Consumption and Demand of an Electric Arc Furnace with Limited Knowledge on Process Parameters · 2024 · DOIIn conclusion, the authors highlight the lack of a universal forecasting approach and the need for further research on hybrid models that combine interpretability with high predictive accuracy.
Future research should focus on improving hybrid ML models, integrating explainable AI techniques, and enhancing real-time adaptability to evolving energy demands.
While it is well known that the Weibull distribution is a good model for wind-speed measurements and can be explained through simple statistical arguments, how such a model holds for shorter time periods is still an open question.
The primary objective is to uncover the complex relationships between energy usage and meteorological data, addressing gaps in understanding how these variables impact consumption patterns in different campus buildings by considering factors such as seasons, hours of the day, and weather conditions.
Advanced Machine Learning Techniques for Energy Consumption Analysis and Optimization at UBC Campus: Correlations with Meteorological Variables · 2024 · DOIFuture research should focus on developing universal AI models, increasing model accuracy with explainable AI techniques, and integrating region-specific forecasts to aid decision-making in various sectors.
The paper focuses on the deterministic forecasting problem and does not address probabilistic forecasting. The values of 𝜆 1 and 𝜆 2 are heuristic and require calibration. The paper does not provide a calibration procedure for the hyperparameters.
ST-GNN-IOT: Spatio-Temporal Graph Neural Networks with Sensor-Proxy-Driven Dynamic Edge-Weight Modulation for Large-Scale Renewable Energy Forecasting · 2026 · DOITo calibrate the hyperparameters 𝜆 1 and 𝜆 2 using POSOCO operational cost data. To extend the proposed technique to probabilistic forecasting. To apply the proposed technique to other non-stationary renewable corridors.
ST-GNN-IOT: Spatio-Temporal Graph Neural Networks with Sensor-Proxy-Driven Dynamic Edge-Weight Modulation for Large-Scale Renewable Energy Forecasting · 2026 · DOIMeeting the need for electricity is essential for the continuity of life. Sustainability issues are considered among the most critical agenda items for countries.
Prediction of the Gross Electricity Generation Amount with Energy Sources Using the M5P Decision Tree Algorithm · 2026 · DOIThe study aims to address the need for predicting electricity generation values. The study aims to contribute to the development of sustainable energy systems.
Prediction of the Gross Electricity Generation Amount with Energy Sources Using the M5P Decision Tree Algorithm · 2026 · DOIPrior studies have used machine learning methods for energy consumption forecasting, but interpretability is a challenge. There is a need for a directly interpretable framework for energy consumption analysis.
Interpreting Primary Energy Consumption in Europe and Türkiye Using Explainable Artificial Intelligence · 2026 · DOIThe paper uses SHAP and LIME explainable AI methods to interpret energy consumption but does not compare their explanations for consistency or identify cases where XAI method choice affects policy recommendations, particularly for the conflicting GDP-energy relationships observed in developing versus developed European countries.
Interpreting Primary Energy Consumption in Europe and Türkiye Using Explainable Artificial Intelligence · 2026 · DOIExisting prediction methods rely on CFD numerical simulations, which have limitations - Lack of efficient and accurate wind field prediction methods
Across this set, rolling or receding-horizon optimization is applied to power systems and microgrids, but none explicitly measures or optimizes the trade-off between forecast calibration (e.g., prediction interval coverage or Winkler score) and rolling scheduling cost over a multi-step horizon. Calibration is treated as a forecast quality metric, not as a decision-relevant objective.
Balancing Cost and Risk in High-Load Power Systems: An Integrated Prediction–Optimization Strategy · 2026 · DOIInvestigating the application of the proposed framework to other power systems, - Exploring the use of other uncertainty quantification methods, - Developing more advanced robust optimization approaches
Balancing Cost and Risk in High-Load Power Systems: An Integrated Prediction–Optimization Strategy · 2026 · DOI
Most-cited papers in Energy Load and Power Forecasting
- Electricity price forecasting: A review of the state-of-the-art with a look into the future · International Journal of Forecasting · 2014 · 1,438 citations
- Probabilistic electric load forecasting: A tutorial review · International Journal of Forecasting · 2016 · 1,239 citations
- Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond · International Journal of Forecasting · 2016 · 909 citations
- A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting · International Journal of Forecasting · 2019 · 676 citations
- Data-driven probabilistic machine learning in sustainable smart energy/smart energy systems: Key developments, challenges, and future research opportunities in the context of smart grid paradigm · Renewable and Sustainable Energy Reviews · 2022 · 664 citations
- Global Energy Forecasting Competition 2012 · International Journal of Forecasting · 2013 · 482 citations
- Optimizing renewable energy systems through artificial intelligence: Review and future prospects · Energy & Environment · 2024 · 426 citations
- Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism · Applied Energy · 2022 · 410 citations
- Forecasting electricity prices for a day-ahead pool-based electric energy market · International Journal of Forecasting · 2005 · 403 citations
- Carbon price forecasting based on CEEMDAN and LSTM · Applied Energy · 2022 · 402 citations
Most recent work
- PowerMistral: A data-efficient wind power forecasting framework leveraging pre-trained large language models · Applied Energy · 2026
- An integrated TCN-ECA-BiLSTM and TD3 framework for high-accuracy forecasting and optimal load allocation in combined heat and power systems · Energy · 2026
- Development of a physics-guided bidirectional long short-term memory for wind power forecasting · Engineering Applications of Artificial Intelligence · 2026
- An enhanced interpretable ML approach for forecasting long-term CO2 and N2O emissions via optimized random forest modeling · Fuel · 2026
- Machine learning approaches to predicting energy price correlation: From a responsible AI perspective · Technological Forecasting and Social Change · 2026
- The HEFTCom2024 winning model: A stacked CatBoost approach for probabilistic wind and solar power forecasting · International Journal of Forecasting · 2026
- A Comprehensive Review of AI-based Wind Power Forecasting Over Multiple Time Horizons · Process Integration and Optimization for Sustainability · 2026
- Towards smart hotels: energy forecasting with machine learning models · Logic Journal of the IGPL · 2026
- Predictive intelligence of machine learning models for global energy perspectives and transformations towards sustainability · Energy Reports · 2026
- Toward a unified data-driven turbulence model through multi-objective learning · National Science Review · 2026
Find a gap in your own Energy Load and Power Forecasting sub-topic
This page shows what the Energy Load and Power Forecasting literature already flags as unresolved. To narrow it to your specific question, run the guided finder — it searches the gap library on demand and checks candidates against 250M+ OpenAlex works.
Open the Research Gap Finder →