Potential of Explainable Artificial Intelligence in Advancing Renewable Energy: Challenges and Prospects

Energy & Fuels, Journal Year: 2024, Volume and Issue: 38(3), P. 1692 - 1712

Published: Jan. 19, 2024

Modern machine learning (ML) techniques are making inroads in every aspect of renewable energy for optimization and model prediction. The effective utilization ML the development scaling up systems needs a high degree accountability. However, most approaches currently use termed black box since their work is difficult to comprehend. Explainable artificial intelligence (XAI) an attractive option solve issue poor interoperability black-box methods. This review investigates relationship between (RE) XAI. It emphasizes potential advantages XAI improving performance efficacy RE systems. realized that although integration with has enormous alter how produced consumed, possible hazards barriers remain be overcome, particularly concerning transparency, accountability, fairness. Thus, extensive research required address societal ethical implications using create standardized data sets evaluation metrics. In summary, this paper shows potential, perspectives, opportunities, challenges application system management operation aiming target efficient energy-use goals more sustainable trustworthy future.

Language: Английский

---

A Review on Socio-technical Transition Pathway to European Super Smart Grid: Trends, Challenges and Way Forward via Enabling Technologies

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104155 - 104155

Published: Jan. 1, 2025

Language: Английский

---

Multivariate probabilistic forecasting of intraday electricity prices using normalizing flows

Applied Energy, Journal Year: 2023, Volume and Issue: 346, P. 121370 - 121370

Published: June 8, 2023

Language: Английский

---

Improving the prediction of biochar production from various biomass sources through the implementation of eXplainable machine learning approaches

International Journal of Green Energy, Journal Year: 2024, Volume and Issue: 21(12), P. 2771 - 2798

Published: March 14, 2024

Examining the game-changing possibilities of explainable machine learning techniques, this study explores fast-growing area biochar production prediction. The paper demonstrates how recent advances in sensitivity analysis methodology, optimization training hyperparameters, and state-of-the-art ensemble techniques have greatly simplified enhanced forecasting output composition from various biomass sources. argues that white-box models, which are more open comprehensible, crucial for prediction light increasing suspicion black-box models. Accurate forecasts guaranteed by these AI systems, also give detailed explanations mechanisms generating outcomes. For models to gain confidence processes enable informed decision-making, there must be an emphasis on interpretability openness. comprehensively synthesizes most critical features a rigorous assessment current literature relies authors' own experience. Explainable encourage ecologically responsible decision-making improving forecast accuracy transparency. Biochar is positioned as participant solving global concerns connected soil health climate change, ultimately contributes wider aims environmental sustainability renewable energy consumption.

Language: Английский

---

Using Explainable Artificial Intelligence (XAI) to Predict the Influence of Weather on the Thermal Soaring Capabilities of Sailplanes for Smart City Applications

Smart Cities, Journal Year: 2024, Volume and Issue: 7(1), P. 163 - 178

Published: Jan. 15, 2024

Background: Drones, also known as unmanned aerial vehicles, could potentially be a key part of future smart cities by aiding traffic management, infrastructure inspection and maybe even last mile delivery. This paper contributes to the research on managing fleet soaring aircraft gaining an understanding influence weather capabilities. To do so, machine learning algorithms were trained flight data, which was recorded in UK over past ten years at selected gliding clubs (i.e., sailplanes). Methods: A random forest regressor predict duration (RF) classifier used whether least one given day managed soar thermals. SHAP (SHapley Additive exPlanations), form explainable artificial intelligence (AI), understand predictions models. Results: The best RF have mean absolute error 5.7 min (flight duration) accuracy 81.2% (probability thermal day). explanations derived from are line with common knowledge about effect systems potential. However, conclusion this study is importance combining human devise holistic explanation model avoid misinterpretations.

Language: Английский

---

Machine Learning Algorithms for Power System Sign Classification and a Multivariate Stacked LSTM Model for Predicting the Electricity Imbalance Volume

International Journal of Computational Intelligence Systems, Journal Year: 2024, Volume and Issue: 17(1)

Published: April 3, 2024

Abstract The energy transition to a cleaner environment has been concern for many researchers and policy makers, as well communities non-governmental organizations. effects of climate change are evident, temperatures everywhere in the world getting higher violent weather phenomena more frequent, requiring clear firm pro-environmental measures. Thus, we will discuss support provided by artificial intelligence (AI) applications achieve healthier environment. focus be on driving transition, significant role AI, collective efforts improve societal interactions living standards. price electricity is included almost all goods services should affordable sustainable development economies. Therefore, it important model, anticipate understand trend markets. includes an imbalance component which difference between notifications real-time operation. Ideally zero, but real operation such differences normal due load variation, lack renewable sources (RES) accurate prediction, unplanted outages, etc. additional produced or some generating units required reduce generation balance power system. Usually, this activity performed balancing market (BM) transmission system operator (TSO) that gathers offers from generators gradually increase output. prediction volume along with prices deficit surplus paramount importance producers’ decision makers create BM. main goal predict minimize costs may cause. In chapter, propose method based classification sign inserted into dataset predicting volume. predicted using several classifiers output added input dataset. rest exogenous variables shifted values previous day d − 1. either (like sign) known Several metrics, mean average percentage error (MAPE), determination coefficient R 2 (MAE) calculated assess proposed combining machine learning (ML) algorithms recurrent neural networks (RNN) memorize variations, namely long short-term memory (LSTM) model.

Language: Английский

---

Using machine learning to expound energy poverty in the global south: Understanding and predicting access to cooking with clean energy

Energy and AI, Journal Year: 2023, Volume and Issue: 14, P. 100290 - 100290

Published: July 22, 2023

Efforts towards achieving high access to cooking with clean energy have not been transformative due a limited understanding of the clean-energy drivers and lack evidence-based policy recommendations. This study addresses this gap by building high-performing machine learning model predict understand mechanisms driving poverty - specifically energy. In first-of-a-kind, estimated cost US$14.5 trillion enable universal encompasses all intermediate inputs required build self-sufficient ecosystems creating value-addition sectors. Unlike previous studies, data-driven clean-cooking transition pathways provide foundations for shaping models that can transform complex landscape. Developing these is necessary increase people's financial resilience tackle poverty. The findings also show absence linear relationship between electricity evidencing need rapid paradigm shift address A new fundamental approach focuses on improving sustaining capacity households through systems so they afford or fuels cooking.

Language: Английский

---

The scheduling role of future pricing information in electricity markets with rising deployments of energy storage: An Australian National Electricity Market case study

Energy Economics, Journal Year: 2025, Volume and Issue: unknown, P. 108191 - 108191

Published: Jan. 1, 2025

Language: Английский

---

Industrial Electricity Pricing and Renewable Energy: A Temporal Analysis of the Effect of Taxes

Energies, Journal Year: 2025, Volume and Issue: 18(8), P. 2026 - 2026

Published: April 15, 2025

This study investigates the industrial electricity pricing (IEP) profiles of 22 OECD countries to understand effect renewable energy and taxes on overall prices. Clustering analysis was performed data from year 2000 2018 observe how prices evolved. Ordinal logit regression determine possible associations between clustered groups percentage share renewables generated (REG), specifically linked wind, solar photovoltaics thermal. Other independent variables indicating economic market structures were also considered. results for both before after tax indicated three clusters, termed low, median, high clusters. IEP in Italy Germany found have highest owing taxes, while such as US, Norway, Canada, Denmark least affected by taxes. Regression show positive REG. The association non-taxed component a unit increase REG is 1.41 times, whereas price (including taxes) 56.26 which 39.9 times higher. Our that penetration has had minimal over time under consideration, but rather taxation coincides with penetration, contributing increases.

Language: Английский

---

On strategic behavior in electricity markets during the 2022 energy crisis: An ex-post analysis for the German power sector

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 5474 - 5485

Published: May 12, 2025

Language: Английский

---