Over the last two decades, Artificial Intelligence (AI) approaches have been applied to various applications of the smart grid, such as demand response, predictive maintenance, and load forecasting. However, AI is still considered to be a "black-box" due to its lack of explainability and transparency, especially for something like solar photovoltaic (PV) forecasts that involves many parameters. Explainable Artificial Intelligence (XAI) has become an emerging research field in the smart grid domain since it addresses this gap and helps understand why the AI system made a forecast decision. This paper presents several use cases of solar PV energy forecasting using XAI tools, such as LIME, SHAP, and ELI5, which can contribute to adopting XAI tools for smart grid applications. Understanding the inner workings of a prediction model based on AI can give insights into the application field. Such insight can provide improvements to the solar PV forecasting models and point out relevant parameters.INDEX TERMS Explainable Artificial Intelligence (XAI), solar PV power generation forecasting, explainability and transparency.
Purpose The purpose of this paper is to implement new concept of mobile maintenance in manufacturing industry of Northern India. This study tries to introduce the new concept of total productive maintenance program in the case company. Design/methodology/approach The approach is to study the role of mobile maintenance in the context of Indian industry through significant improvement in overall equipment effectiveness (OEE). Findings This industry adopted the mobile maintenance strategy and improved their productivity by decreasing breakdown time. This mobile maintenance strategy can reduce major breakdowns, setup and adjustment losses and improve productivity, product quality and OEE of equipment. Results indicate an average increase in production of 15.63 percent, average reduction in breakdown time of 23.14 percent, average reduction in rejection rate of 17.94 percent and average increase in OEE of 17.08 percent. Moreover, the results of improvements in parameters are validated by using multi-criteria decision-making approaches. Research limitations/implications Maintenance is of great importance in modern era of manufacturing systems for those organizations who consider maintenance as a profit-generating factor. In the dynamic and highly challenging environment, reliable manufacturing equipment is regarded as the major contributor to the performance and profitability of manufacturing systems. Moreover, the selection of manufacturing industry is done on the basis of convenience sampling technique. Originality/value Industry can improve machine availability and OEE by implementing this mobile maintenance concept especially in the Indian context and is very beneficially for the case company under study.
Increasing concern for the environment has led to governments and companies pushing for renewable power generation. The share of wind power for the supply of electricity has been increasing during the last two decades. Increased penetration levels of intermittent power sources like wind power became a challenge for the power companies. Therefore, the need to make accurate forecasts for wind power generation has become a very critical issue for the power system operators. This paper presents a novel approach to forecasting 1 to 24 hours ahead wind power using Long Short-Term Memory based Recurrent Neural Network (LSTM-RNN). The model is based on knowledge from the data, that both weather and wind power have short-term temporal dependencies. The proposed model is implemented using historical generated wind power and Numerical Weather Prediction (NWP) data for Sotavento, a wind farm in Spain. Input parameters from the NWP data are selected by performing a sensitivity analysis for variable selection technique.
During the last decade there has been a major shift towards renewable energy sources to fulfill the increasing demand for energy in a sustainable manner. However, a major challenge with renewable energy sources is their dependence on weather conditions which makes generation highly uncertain and intermittent. Energy storage is deemed instrumental to harness renewable energy overcoming its inherent stochasticity. Nonetheless, the operation of energy storage is not trivial due to its energy limitation and degradation behavior. Many works in literature consider forecast as a cornerstone for effective management of energy storage for various grid applications. However, little work has been devoted to studying the actual value of forecast for energy storage management, which is highly dependent on the use case. This paper presents a review of the state of the art in the use of forecast for energy storage management, identifying the estimated value of forecast with respect to baseline management approaches that do not rely on forecast. The paper also discusses research pathways that would focus on improving forecast only on the energy storage applications that can benefit from it.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.