Artificial Intelligence and Solar Forecasting: Comparison
View Latest Version
Please note this is a comparison between Version 2 by Rita Xu and Version 1 by Wilfried Van Sark.

Solar energy forecasting is essential for the effective integration of solar power into electricity grids and the optimal management of renewable energy resources.

  • solar energy integration
  • solar forecasting
  • artificial intelligence

1. Introduction

The pressing need for reducing greenhouse gas emissions has led to the worldwide adoption of renewable energy sources (RESs) [1,2,3][1][2][3]. However, RESs tend to be volatile in nature, especially solar and wind energy, making it hard to predict their power output and making them less reliable. This volatile nature can lead to voltage fluctuations, frequency fluctuations, and system outages [1,2,4,5][1][2][4][5].
The large-scale integration of RESs into the energy supply network requires the development of new technologies and methods to balance supply and demand. As the share of RESs in the energy mix increases, the load on the energy grid increases with corresponding consequences. The intermittent nature of solar energy has proven to be an obstacle to the large-scale integration of solar energy. For example, a massive increase in grid-connected PV energy can result in overvoltage or congestion problems [6].
A rethinking of the traditional electricity grid is taking place in order to handle the perceived unpredictable nature of RESs. Traditional grids are continuously evolving and changing, becoming so-called smart grids. A smart grid can be seen as the result of fusing the electricity grid with Information and Communication Technologies (ICT). This allows for a two-way flow of information between the supply side and demand side on the energy grid [1[1][4],4], which in turn allows for the improved control of management over all the different domains that are part of energy production and distribution [4]. Through the creation of decision-support tools that exploit these flows of information, the distribution and management of the grid can be optimized. Decision-support tools often deal with a variety of tasks, such as energy distribution, energy curtailment, and energy storage system activation. These are now being developed and often include forecasting and the recognition of energy demand and production. Artificial Intelligence (AI) is deemed to be very promising for dealing with these complex tasks [1,2,4][1][2][4].
One of the proposed solutions is to forecast solar irradiance and, in turn, to forecast solar energy production to help balance supply and demand through combination with electricity storage [7,8][7][8]. As a result, solar forecasting has seen an increase in interest from researchers, grid operators, and other parties involved in the electricity market [9].

2. Artificial Intelligence and Solar Forecasting

It would be impossible to discuss solar forecasting methods while not mentioning Artificial Intelligence. A lot of research is already focusing on the use of AI for solar forecasting [2,8,13,35][2][8][10][11] and also for decision-support tools in different domains of the electricity grid [3]. The wide range of different applications that have been applied successfully by researchers highlights the versatility of AI techniques. For example, AI has been used to develop energy bidding tools [36][12]; perform day-ahead solar forecasting [37][13], wind speed forecasting [35][11], solar radiation estimation [2[2][8][10][11],8,13,35], the monitoring of fields of PV systems [38][14], fault detection, and the diagnosis of wind energy systems [5]; and demand load predictions [3]. It should be noted that there is no official definition of what AI is [11][15] and what techniques and methods are considered Artificial Intelligence. Instead, AI is often used as an umbrella term to describe a wide variety of techniques, including but not limited to machine learning, supervised learning, optimization algorithms, pattern recognition techniques, and regression methods. One of the main strengths of what are generally considered AI techniques is that they are able to solve complex problems for which it is impossible to find explicit algorithms or mathematical solutions [7]. Often, this includes pattern recognition in large datasets in which the underlying principles or dependencies are very complex or unknown. The recent increase in the usage of AI techniques has been facilitated by a rapid increase in computational power over the last decades [39][16]. One of the most frequently used AI techniques in solar forecasting, as seen in Figure 1, and many other fields of research, is the Artificial Neural Network (ANN) [2,3,11,13,40][2][3][10][15][17]. The strength of ANNs is that they require a very low level of programming to solve a wide variety of complex problems. Specifically, nonlinear, stochastic, or mathematically ill-defined problems (e.g., pattern recognition or classification) are very well suited for ANNs [2,11,40,41][2][15][17][18]. Other popular techniques include the support vector machine [2,8[2][8][10],13], k-Nearest Neighbor algorithms [8[8][15],11], intelligent optimization algorithms [3], and Markov Chains [2,8,13][2][8][10]. Fuzzy Logic Control (FLC) has also been widely applied to control Solar PV systems and smart grids [3]. It makes it easy to use many input variables and to make use of the expert knowledge of human decision makers without the use of complex mathematical expressions [3,42][3][19].
Figure 1. Word web on (a) AI techniques and (b) different data sources for solar energy forecasting.
A recent example of using AI methods for solar forecasting is the work conducted by Eseye et al. [43][20]. A data-driven approach was developed that employs a wavelet transform method, support vector machine, and particle swarm optimization to make predictions on the PV power output. The results were compared to seven other AI-based methods and proved to be competitive. This research also highlights the numerous methods already developed by using AI methods. Mishra and Palanisamy [44][21] developed a solar forecasting method built on Recurrent Neural Networks that was able to predict solar forecasts over a wide range of time horizons ranging from intrahour, hourly, to day-ahead scales using real-time inputs. Another example that showcases the possibilities of AI within solar forecasting is the method developed by Ge et al. [45][22]. They developed a method that only uses empirical data and AI, thus excluding the use of any physical model or empirical relationship while still being able to achieve similar results to more classical methods. Another method that has been gaining interest for nowcasting is the General Adversarial Network (GAN) method, which has already proven to be able to forecast precipitation with high precision [46][23], improve time series Satellite Image prediction [47][24], and perform sky image forecasting [48][25]. For further reading on AI techniques, refs. [8,11][8][15] are recommended.

References

  1. Al-Othman, A.; Tawalbeh, M.; Martis, R.; Dhou, S.; Orhan, M.; Qasim, M.; Olabi, A.G. Artificial intelligence and numerical models in hybrid renewable energy systems with fuel cells: Advances and prospects. Energy Convers. Manag. 2022, 253, 115154.
  2. Sobri, S.; Koohi-Kamali, S.; Rahim, N.A. Solar photovoltaic generation forecasting methods: A review. Energy Convers. Manag. 2018, 156, 459–497.
  3. Liu, Z.; Sun, Y.; Xing, C.; Liu, J.; He, Y.; Zhou, Y.; Zhang, G. Artificial intelligence powered large-scale renewable integrations in multi-energy systems for carbon neutrality transition: Challenges and future perspectives. Energy AI 2022, 10, 100195.
  4. Sayed-Mouchaweh, M. (Ed.) Artificial Intelligence Techniques for a Scalable Energy Transition; Springer Nature: Cham, Switzerland, 2020.
  5. Marugán, A.P.; Márquez, F.P.G.; Perez, J.M.P.; Ruiz-Hernández, D. A survey of artificial neural network in wind energy systems. Appl. Energy 2018, 228, 1822–1836.
  6. Shabbir, N.; Kutt, L.; Astapov, V.; Husev, O.; Ahmadiahangar, R.; Wen, F.; Kull, K. Congestion control strategies for increased renewable penetration of photovoltaic in LV distribution networks. Energy Rep. 2022, 8, 217–223.
  7. Vallance, L.; Charbonnier, B.; Paul, N.; Dubost, S.; Blanc, P. Towards a standardized procedure to assess solar forecast accuracy: A new ramp and time alignment metric. Sol. Energy 2017, 150, 408–422.
  8. Voyant, C.; Notton, G.; Kalogirou, S.; Nivet, M.L.; Paoli, C.; Motte, F.; Fouilloy, A. Machine learning methods for solar radiation forecasting: A review. Renew. Energy 2017, 105, 569–582.
  9. Visser, L.; Lorenz, E.; Heinemann, D.; van Sark, W.G. 1.11—Solar Power Forecasts. Compr. Renew. Energy 2023, 1, 213–233.
  10. Tuohy, A.; Zack, J.; Haupt, S.E.; Sharp, J.; Ahlstrom, M.; Dise, S.; Grimit, E.; Möhrlen, C.; Lange, M.; Casado, M.G.; et al. Solar Forecasting. IEEE Power Energy Mag. 2015, 15, 1540–7977.
  11. Hatti, M. (Ed.) Artificial Intelligence and Renewables Towards an Energy Transition; Springer Nature: Cham, Switzerland, 2021.
  12. Visser, L.; Kootte, M.; Ferreira, A.; Sicurani, O.; Pauwels, E.; Vuik, C.; Sark, W.V.; AlSkaif, T. An operational bidding framework for aggregated electric vehicles on the electricity spot market. Appl. Energy 2022, 308, 118280.
  13. Visser, L.; AlSkaif, T.; van Sark, W. Operational day-ahead solar power forecasting for aggregated PV systems with a varying spatial distribution. Renew. Energy 2022, 183, 267–282.
  14. Daliento, S.; Chouder, A.; Guerriero, P.; Pavan, A.M.; Mellit, A.; Moeini, R.; Tricoli, P. Monitoring, Diagnosis, and Power Forecasting for Photovoltaic Fields: A Review. Int. J. Photo Energy 2017, 2017, 356851.
  15. Inman, R.H.; Pedro, H.T.; Coimbra, C.F. Solar forecasting methods for renewable energy integration. Prog. Energy Combust. Sci. 2013, 39, 535–576.
  16. Ahmad, T.; Zhang, D.; Huang, C.; Zhang, H.; Dai, N.; Song, Y.; Chen, H. Artificial intelligence in sustainable energy industry: Status Quo, challenges and opportunities. J. Clean. Prod. 2021, 289, 125834.
  17. Krogh, A. What are artificial neural networks? Nat. Biotechnol. 2008, 26, 195–197.
  18. Yegnanarayana, B. Artificial Neural Networks; PHI Learning Pvt. Ltd.: New Delhi, India, 2009.
  19. Lee, C.C. Fuzzy logic in control systems: Fuzzy logic controller. I. IEEE Trans. Syst. Man Cybern. 1990, 20, 404–418.
  20. Eseye, A.T.; Zhang, J.; Zheng, D. Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information. Renew. Energy 2018, 118, 357–367.
  21. Mishra, S.; Palanisamy, P. Multi-time-horizon solar forecasting using recurrent neural network. In Proceedings of the 2018 IEEE Energy Conversion Congress and Exposition (ECCE), Portland, OR, USA, 23–27 September 2018; pp. 18–24.
  22. Tan, C. Generating the Cloud Motion Winds Field from Satellite Cloud Imagery Using Deep Learning Approach. 2020. Available online: https://arxiv.org/abs/2010.01283v2 (accessed on 20 December 2022).
  23. Ravuri, S.; Lenc, K.; Willson, M.; Kangin, D.; Lam, R.; Mirowski, P.; Fitzsimons, M.; Athanassiadou, M.; Kashem, S.; Madge, S.; et al. Skilful precipitation nowcasting using deep generative models of radar. Nature 2021, 597, 672–677.
  24. Wang, R.; Teng, D.; Yu, W.; Zhang, X.; Zhu, J. Improvement and Application of a GAN Model for Time Series Image Prediction—A Case Study of Time Series Satellite Cloud Images. Remote Sens. 2022, 14, 5518.
  25. Andrianakos, G.; Tsourounis, D.; Oikonomou, S.; Kastaniotis, D.; Economou, G.; Kazantzidis, A. Sky Image forecasting with Generative Adversarial Networks for cloud coverage prediction. In Proceedings of the 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Patras, Greece, 15–17 July 2019; pp. 1–7.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)
ScholarVision Creations
Feedback