The Solar Energy Forecasting Using LSTM Deep Learning Technique

Al-Jaafreh, Tamer Musha'l; Al-Odienat, Abdullah; Altaharwah, Yousef A.

doi:10.1109/etcea57049.2022.10009717

Cited by 7 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the prediction accuracy was lower than in previous works that used similar sources of data (weather data and solar radiation). Jebli et al [ 12 ] achieved R

scores of 93 to 95% for scenarios that did not overfit, while Al-Jaafreh et al [ 13 ] achieved an RMSE of 0.035 using 16 features to predict the hourly produced energy. Those slightly better results might be explained by the bigger size of datasets and algorithms used (neural network-based architectures).…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, it can also be accurately predicted from solar radiation combined with other weather data (temperature, wind direction and speed, humidity, pressure, etc. ), with both ML and DL [ 12 , 13 ]. Hybrid forecasting (i.e., combining different algorithms for different steps of the prediction pipeline) and recurrent neural networks (RNNs) are now mostly employed [ 14 ].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Recommender System for Increasing Energy Efficiency of Solar-Powered Smart Homes

Meteier,

El Kamali,

Angelini

et al. 2023

Sensors

View full text Add to dashboard Cite

Photovoltaic installations can be environmentally beneficial to a greater or lesser extent, depending on the conditions. If the energy produced is not used, it is redirected to the grid, otherwise a battery with a high ecological footprint is needed to store it. To alleviate this problem, an innovative recommender system is proposed for residents of smart homes equipped with battery-free solar panels to optimise the energy produced. Using artificial intelligence, the system is designed to predict the energy produced and consumed for the day ahead using three data sources: sensor logs from the home automation solution, data collected by the solar inverter, and weather data. Based on these predictions, recommendations are then generated and ranked by relevance. Data collected over 76 days were used to train two variants of the system, considering or without considering energy consumption. Recommendations selected by the system over 14 days were randomly picked to be evaluated for relevance, ranking, and diversity by 11 people. The results show that it is difficult to predict residents’ consumption based solely on sensor logs. On average, respondents reported that 74% of the recommendations were relevant, while the values contained in them (i.e., accuracy of times of day and kW energy) were accurate in 66% (variant 1) and 77% of cases (variant 2). Also, the ranking of the recommendations was considered logical in 91% and 88% of cases. Overall, residents of such solar-powered smart homes might be willing to use such a system to optimise the energy produced. However, further research should be conducted to improve the accuracy of the values contained in the recommendations.

show abstract

“…However, the prediction accuracy was lower than in previous works that used similar sources of data (weather data and solar radiation). Jebli et al [ 12 ] achieved R

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Recommender System for Increasing Energy Efficiency of Solar-Powered Smart Homes

Meteier,

El Kamali,

Angelini

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Furthermore, other variables are often implemented. Temperature variables are among the most popular, featured in recent publications like [88] , [89] , [90] , [91] , [75] , due to their easy accessibility and high Pearson correlation coefficients, which can reach 0.9. Similarly, wind speed variables, as implemented in [92] , [81] , [77] , and humidity [81] , [93] , which have moderate Pearson correlation coefficients, are also utilized.…”

Section: State Of the Artmentioning

confidence: 99%

“…Solar irradiance stands out as the most correlated variable to PV power production. Articles such as [89] , [85] , [86] , [87] illustrate PV power forecasting methods by setting the model's label to solar irradiance. Similar approaches have been used with different variables such as temperature [93] and weather [84] .…”

Section: State Of the Artmentioning

confidence: 99%

“…As anticipated, the majority (15 articles) predicted a one-time step ahead since achieving high accuracy is less complicated in this scenario. This approach has been demonstrated in articles such as [79] , [89] , [90] , [86] , [106] . Forecasting 24 steps ahead can provide more valuable insights for power applications while considering moderate use of computer resources.…”

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation