Solar Radiation Forecasting — State of Art and Methodological Discussion

1. Introduction

In recent years, the production of clean energy has attracted significant interest. Solar power has been systematically strengthening its position among renewables, and the number and capacity of solar photovoltaic plants have grown rapidly in many countries. Fast progress into carbon neutrality and net zero emission economies with significant use of photovoltaic technology is only possible with effective accumulation and compensation systems to balance solar surpluses and shortfalls with other sources. Strong volatility and intermittency of solar energy generation require the leveraging advance of adequate forecasting methods concerning meteorological and geographical characteristics of plant location [1,2]. Forecasting solar irradiance is essential in planning and operations to deal with energy supply and demand uncertainty, balance and optimise the system, and ensure power continuity [3,4,5,6,7,8]. Accurate forecasting is crucial at all levels of an energy system, including control, operation, management, financial viability of energy companies, and the trajectories of sustainable and responsible innovation. Spatial resolution and time horizon determine the application of forecasts. Controlling power distribution, ensuring network stability and voltage regulation requires a time horizon in seconds [4,9], forecasts from minutes to hours support power reserve management and load optimisation [10], day-ahead forecasts are used for transmission planning and unit commitment [5,7], and a year scale for capacity/network global management [6,11].

The importance of solar energy forecasting is reflected in numerous publications. The bibliometric study has revealed 12,156 works (articles, chapters, etc.) during the period 2013-2023 (database: Scopus; search query: TITLE-ABS-KEY (solar AND forecasting) AND PUBYEAR > 2012 AND PUBYEAR < 2024). A significant increase in the number of articles on solar energy forecasting dates to 2018, with over 1,000 per year. There is also a rapid growth in systematic reviews (SR) and meta-analyses that synthesise the results of previous studies.

Systematic reviews accomplish transparent and rigorous procedures to bring together evidence from multiple studies and summarise the current state of knowledge [12]. The popularity of SR has resulted in the need to synthesise the evidence bases by conducting overviews of reviews and developing methodological tools and guidelines [13,14].

Meta-review (MR) evaluates and synthesises evidence from existing systematic literature reviews (SLR) [15,16] and in this way, facilitates broad comparisons [17]. It is referred to in the literature as an overview of reviews (OR) [18], meta-meta-analysis, tertiary study, umbrella review, and overviews of systematic reviews. Recently, it has gained increased popularity [17,19], but is still underrated in the field of renewables forecasting. The main advantage of MR is to provide a summary synthesis of the analysed reviews to expand research issues beyond those addressed in the individual reviews and to combine them [19]. It is considered particularly useful in areas where many literature reviews have already been published since it allows integration and condenses knowledge [18].

Although the method is not new (e.g., [17,20]), the rapid growth of data and the new advances in search tools and electronic databases have posed new challenges in mapping the state of the art, especially in interdisciplinary topics [21], e.g., engineering management or production management research. The article addresses the problem of determining the meta-review methodology’s scopes, techniques, and conditions in solar forecasting. To the best of our knowledge, this is the first comprehensive overview of reviews on solar forecasting. The article analysed the scope of the review articles. The research focused on a typology of solar forecasting methods.

This article is organised as follows: in the next section, the concept and methodology of meta-review, along with the approach employed in this article, are presented. Then, a bibliometric and text analysis of reviews on solar radiation forecasting is summarised. Concluding the reviews, a typology of solar forecasting models and methods is discussed. The article ends with a summary and future research directions.

2. Meta-Review Concept and Applied Research Methodology

2.1. Meta Reviews in Literature

The literature review serves both as an introduction to research and as a method on its own. It is a key part of every research project or paper since, as referring to current knowledge, it explains a theory behind and meets the paradigm of continuity, accumulation and development of scientific knowledge [18]. It provides evidence for defining the research gap and motivation [22] and opportunities, challenges and guidelines for future research [23]. Although a literature review is a mandatory step in research, it might vary depending on aims and provides different contributions. Among literature review, the following types could be distinguished: scoping review, selective review, tutorial review, theoretical review, algorithmic review, computational review, meta-analysis, qualitative systematic review, and meta-review [18]. Considering quality and confidence, it increases from a narrative review through a scoping review and a rapid review to a systematic review [12].

A systematic literature review that uses rigorous and transparent methods to summarise the available knowledge is a well-established and widely used method. Methodological discipline, which lies behind SLR, impacts the synthesis and evaluation of the materials and information and significantly affects the quality of associated further research [24]. The accelerating popularity of SLRs relates to a high degree to the availability of tools for automatic digital-aid quantitative and qualitative analyses, i.e., the frequency of keyword occurrences, methods, cross-citations, and grouping. Rapidly evolving digital tools such as text mining powered with natural language processing enable replicable rapid large-scale analysis and, in some cases, provide a more comprehensive and objective summary [25]. However, automatic research procedures without human judgment on the quality of research and its context risk compromising the quality and credibility of conclusions. Digital tools do not replace expert knowledge for developing selection criteria and interpreting results. They increase the ability of experts to collect information, disseminate it to non-experts, and promote interdisciplinary research [25].

An overview of reviews is a type of systematic review of a large but aggregated number of papers to generalise information contained in previous publications or primary sources with clearly structured procedures. Although some unique methodological challenges, many methods used to conduct SLR are suitable for overviews of reviews [22]. The meta-review procedure is quite similar to formalised systematic reviews, although this method focuses on systematic reviews rather than primary studies [21].

A general framework for SLR and meta-analysis consists of the following steps: (i) defining the objectives and research question(s), (ii) selecting eligibility criteria, (iii) literature search, (iv) data extraction and synthesis, (v) assessing bias risk and quality, (vi) overview and interpretation of results, and (vii) concluding the overview [19,22]. The overview framework might be divided into two stages: first – developing and populating with four steps: (i) specification of the aims and scope, (ii) specification of the eligibility criteria, (iii) selection search methods, (iv) data extraction, and second stage – identification and mapping evaluations that consist of (i) assessing the risk of bias and (ii) certainty of the evidence, (iii) synthesis and summary the findings, (iv) interpretation of findings and concluding [16]. Overviews could follow the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework, which consists of the subsequent phases: identification, screening, and included [23,26]. It obligates to (i) define clear scope, (ii) do strategic searches, (iii) consider the datedness of the SRL, (iv) address overlap among SLR, (v) apply review quality tools, and (vi) report the meta-review findings. The synthesis of reviews may take the form of narrative, semi-quantitative, or quantitative [14]. In examining the overlap of studies in meta-reviews calculating the corrected covered area index might be useful [13,14].

The main principle of overviews is complete and transparent reporting of previous reviews [15]. The roles of meta-review are to identify gaps in the literature, to explore and contrast reviews, and to summarise the evidence from broad comparisons [17]. Identifying the inconsistencies between systematic reviews includes, among others research questions, samples, quality and selection criteria [17]. Summarising and concluding the literature review findings and evidence might benefit new uncovering information [21].

2.2. Research Methodology

This meta-review aims to examine and collate systematic reviews, summarise the evidence and identify the main themes of the analysis on solar forecasting. The reviews were compared based on input data, methods analysed, classification, and findings. The research process adapted in this work has been illustrated in Figure 1. It consists of translating the aim of the work into search strings and inclusion and exclusion criteria. A broad approach was chosen to ensure no important publication was missed. First, a wide range of keywords was selected, and subsequently, irrelevant terms were eliminated to identify those that could characterise actual and relevant reviews. The original set of solar, radiation, irradiance, and photovoltaic terms was limited to solar. The set covered initially: review, state, recent, advance, trend, development, taxonomy, categorisation, and classification turned out to be sufficient for a review in keywords. The result search query combined the terms (Scopus): TITLE ((forecast* OR predict*) AND solar) AND KEY (review). The literature dataset was also supplemented according to the snowballing procedure. Finally, a retrospective procedure was applied to remove non-relevant publications and discard duplicates. The search was conducted in Elsevier’s Scopus, Web of Science Core Collection (WoS) and IEEE Xplore and covered the period until 1.1.2024. Exclusion criteria were papers that were not written in English and conference papers.

Upon initial bibliographical analysis, it was discovered that the earliest review-type publications were released in the 21st century [27], but the most significant increase has been recorded since 2013. It should be noted that the first works were not a typical review but rather a presentation and discussion of methods with examples [28,29] and the literature review aims to provide background to select methods for testing and comparison [30]. Analyses of reviews conducted in recent years are more comprehensive and stick to the methodology, but this is not the rule, especially in the case of conference presentations, e.g. [31,32,33]. The actual analysis covers the last 10 years.

Examining the content of the received sets of articles at the preliminary screening at the initial stage of the study, numerous papers have been identified that focus on the evaluation, comparison and discussion of various methods/models/techniques on the same data [34,35,36,37,38,39]. They were excluded from the further analysis. There are also works containing lists of articles on solar forecasting with limited aggregation and summary [29]. Moreover, as mentioned above, articles that aim to improve/develop forecasting methods often include an in-depth literature review [30,40]. The state-of-the-art provides the background for the proposed forecast models [41,42]. A solar techniques review might also precede a discussion on power systems security, scheduling and operations [43].

A particular type of review paper focuses on bibliometric analysis. The main advantage of literature reviews using bibliometric analysis and clustering software is the number of references considered. Some works rely on quantitative bibliometrics performed using software such as VOSviewer, which allows for keyword screening [44] or Google Scholar database and its search engine [45]. Text mining undoubtedly has great potential in the literature review. The challenge of automatic review is the proper dictionary construction, selection and interpretation of terminology and their association to provide in-depth analysis and synthesis with text-mining software [45].

Sometimes, the declared review is not a classical exploration literature review but can be labelled as a reverse/confirmation review. This means that defined a priori methods are evaluated with examples of use [28,36,46,47]. Such works can be referenced as reviews of techniques described in the literature with the presentation of their advantages and disadvantages [5,48]. Some articles consist of general or summarising discussions on selected aspects of solar forecasting in power systems and penetration of solar power generation with supporting in-depth reviews and citations [49,50,51]. The final list of publications includes synthesising and classifying works in solar forecasting. The next section contains review papers on solar energy forecasting that were selected as the basis for this meta-review. Table 1 contains abbreviations used in the text.

3. Reviews on Solar Radiation Forecasting

3.1. Bibliometric Analysis of Reviews

The first stage of analysis revealed 36 noteworthy reviews containing an analysis, synthesis, and classification of works on solar forecasting. According to the Scopus database, 28 papers were classified as reviews and 9 as articles. Figure 2 illustrates the distribution of articles by subject area and by year. Table 2 includes the names of journals that published the reviews.

3.2. Typology of the Scope of Solar Forecasting Reviews

Appendix 1 includes the list of reviews. All the analysed papers emphasise that the research on solar forecasting is rapidly expanding. This is related to the increasing penetration of solar PV due to its environmental and economic benefits. The works indicate that energy is the foundation for economic and social growth. Precise forecasting plays a crucial role in the shift towards a more renewable energy profile and in cutting costs in the power system [62,66].

The reviews mainly covered the analysis of primary data, sometimes with references to the results of previous reviews, e.g. [1,54,65,67]. However, the conclusion from previous research might be used as inspiration. Antonanzas et al. (2016) [62] informed about the need for analysis of the economic consequences of forecasts regarding solar energy, Gandhi et al. (2024) [73] took up the challenge of comprehensively reviewing the value of solar forecasts and the cost of errors.

The works concern solar, a combination of solar and wind, or such factors as loads, market price, etc. Table 3 includes the scope of selected solar forecasting reviews. In the case of solar, forecasting variables are mainly GHI or solar PV output [67].

In principle, all the reviews consider classical error metrics to forecast comparisons. The most used were Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2) and their derivatives, e.g. normalised RMSE (NRMSE), Median Absolute Percentage Error (MdAPE). However, other metrics were also noted [62], e.g. Kolmogorov–Smirnov Integral [1,8], Nash-Sutcliffe efficiency [1], and others.

Among the papers, there are general overviews, but also papers dedicated to methods of one type or even focusing on a homogeneous subclass of models, allowing a deeper look into the structure of the models and collating the results. Particular attention is given to methods that can be categorised as AI [6,29,58,64,66]. These include articles comparing various AI models [63] and comparing the AI model with other empirical models [57]. AI methods were already well represented in the first comprehensive reviews [28,57]. In recent years, the number of articles using various AI techniques to predict solar energy has increased exponentially. This can be related to software development and the ease of using statistical or ML methods [49]. Some works focus on methods dedicated to a selected time horizon, e.g. intra-hour [8]. Table 4 includes the scopes of reviews due to method classification.

4. Solar energy Forecasting Methods and Their Classification

4.1. Solar Forecasting Process and Data

Considering solar forecasting, there are three main approaches depending on input data: (i) models that utilise endogenous data (historical series from the PV plant [76]), (ii) models based on exogenous data (sky or satellite images, meteorological characteristics, e.g. as solar irradiance, humidity, wind speed, cloud cover, air temperature), and (iii) mix that analyse different sets of inputs [62]. The popular inputs are (i) historical and current irradiance, (ii) meteorological data, (iii) sky images and (iv) others [8]. Type sources of data can be sky cameras, sensor networks, and satellites [7]. In the case of solar energy forecasting applications, solar radiation is considered the most significant parameter, with a correlation over 0.98 with PV power output [59]. It is the most exploited, both in his first works [28] and now. Among other meteorological data used [71], the sunshine hours and air temperature are found to be adequate inputs [38]. The most popular input parameters are temperature, humidity, wind speed, and less frequently: wind direction, precipitation, cloud cover, solar zenith angle, pressure and others [53]. Recently, air pollution has attracted the attention [66].

Among the variety of methods, artificial intelligence has gained significant attention due to its high effectiveness and accuracy in forecasting solar energy generation [66,72]. AI research in solar forecasting is rapidly growing with expanded applications [6,45]. The most common term in articles on solar radiation forecasting is ANN rather than other ML or DL models [6], although this is changing [66].

The AI models on solar irradiance are used in three ways: (i) structural models based on other meteorological and geographical data, (ii) time-series models based only on the historical data on solar irradiance, and (iii) hybrid based on both solar irradiance and other exogenous variables [6].

The advantages of ANN include: (i) less formal statistical training, (ii) 2) detection of complex non-linear relationships between variables, and (iii) multiple training algorithms [48]. AI methods outperform traditional methods in many cases [65] due to the excellent performance in the description of non-linear and complex processes [66]. However, the comparative advantage of ANN was not always noted. The spatio-temporal vector autoregressive (VAR) model for spatially sparse data may result in lower forecast error [35]. In certain conditions, the ANN and ARIMA methods are equal in terms of the quality of forecasting [6]. The significant disadvantages of ANN are: (i) the "black box" nature, which means that the input data and the result are known, without information about the process inside, (ii) the need for more computational power, and (iii) the tendency to overfit [48].

The general data mining process for predictive analysis consists of (i) data selection, (i) preprocessing, (iii) transformation, (iv) data mining, (v) interpretation/evaluation and (iv) knowledge. In the case of ANN prediction tasks in solar energy applications cover: (i) selection of input and output data; (ii) division of the set into training, test, and verification sets; (iii) development of the model; (iv) selection and training parameters, error calculation and verification; (v) selection of the model [38,57]. This can be abbreviated to the process of building a machine learning model through (i) data preparation, including the input parameters, (ii) the selection of features, and (iii) the development of the model with evaluation [66,76]. It is generally consistent with the process of deploying time series techniques [77]. In the case of physical models, one of the most challenging stages is developing a model to map the relations between input variables and output variables [43].

The role of pre-processing or data feature selection has already been emphasised as a stage that improves the quality of data and thus increases the accuracy of the forecast [4,5,55,59,61,66] even in the first review works [28]. Attention is paid to the post-processing phase to model local effects [28,46,61] as a practice to improve the initial forecasts. In the case of ML, post-processing methods might include discriminant analysis and principal component analysis, naive Bayes classification and Bayesian networks, and data mining approaches [6]. Other techniques are wavelet transform, Kalman filter, empirical mode decomposition, self-organisation map, normalisation, trend free [78]. Post-processing task could be divided into: (i) deterministic-to-deterministic, (ii) probabilistic-to-deterministic, (iii) deterministic-to-probabilistic, and (iv) probabilistic-to-probabilistic [61].

4.2. Solar Forecasting Models Classifications

Solar forecasting methods do not have a set of consistent classification criteria [54]. It is not uncommon for reviews to have overlapping proposals for grouping prognostic approaches, e.g. [42]. Details on the classification of solar energy forecast models in analysed reviews are provided in Annex 1.

Traditionally, in the first works, and repeated later, forecasting methods are broadly classified into (i) statistical (based on historical time series, e.g. ANN, MPL, SVM, ARIMA, RNN), (ii) physical models (based on atmospheric methodological data, e.g. NWP), and (iii) ensemble approach [30,33,65] or hybrid [79], sometimes with distinction persistence method [7]. The following breakdown of forecasting techniques is also proposed: (i) persistence method, (ii) physical techniques (NWP and satellite-based), (iii) linear statistical approaches (e.g. ARMA), (iv) artificial neural networks, and (v) fuzzy logic models [5]. Generally, ANN is classified as a statistical method. However, other AI methods, such as ML models, ELM, and SVM, are sometimes clustered in advanced methods [75]. Combining statistical and ML models in the data-driven class was also proposed [80].

Another proposition of classification is: (i) the empirical approach based entirely on data, and (ii) the dynamical approach practical for modelling large-scale solar radiation prediction [48]. Two basic classes of models can be identified based on the forecast horizon criterion: (i) for short-term forecasts up to 6 h (extrapolation and statistical processes), and (ii) for forecasts up to two days ahead or beyond (NWP models). A further standard division is that between (i) probabilistic (providing confidence intervals, in which values are considered within a certain probability) and (ii) deterministic (single value) [33,60].

In the case of ML methods, they can be classified into (i) supervised learning (e.g. linear regression, generalised linear models, nonlinear regression, support vector machines/support vector regression, decision tree learning/Breiman bagging, nearest neighbour, Markov chain), (ii) unsupervised learning (e.g. k-means and k-methods clustering, hierarchical clustering, Gaussian mixture models, cluster evaluation), and (iii) ensemble learning [6]. Another proposition is generalised (GM), ensemble-based (EM), cluster-based (CM), decomposition-based (DM), decomposition-cluster-based (DCM), transition-based (TM), and postprocessing-based (PM) machine-learning models [66].

Many works emphasise the advantages of hybrid and ensemble approaches in improving forecasting accuracy and providing promising solutions for different forecasting horizons [5,45,50,54,75,78]. Ensemble models combine the results of many individual models, while hybrid models combine different techniques or algorithms and take advantage of ensemble techniques, creating sophisticated model structures.

The combining approach could serve as the primary method in a hierarchical multiple-step approach but can also be applied in the pre-processing or post-processing stage [30]. However, they must be tuned appropriately [5]. Generally, they surpass the best alternative single approach, although this is not always the case [30]. Simple techniques might give high accuracy if the input parameters are properly selected, filtered and pre-processed [9].

In the ensemble approach, there are two methods: (i) "competitive" (parallel) when the final forecast is an average of the individual forecasts, and (ii) "cooperative" (sequential) when the prediction process consists of a sequence of sub-tasks solved individually and the final forecast is a sum of the subtask outputs [30,50,65]. Combining, boosting, blending, and slacking methods can be considered in sequential ML. In the case of the parallel, a popular technique is bagging [76].

4.3. Forecasting Techniques’ Adequacy to Forecast Horizon and Resolution

Many works address the problem of fitting the model to the forecast horizon. Early work indicated that models such as ARIMA are suitable for modelling linear time series, and ANN is preferred for modelling nonlinear time series [81]. As the forecasting approaches depend on available data and also on the required forecasting horizon, many works summarise the existing methods versus the time and assess forecasting suitability for forecast horizon and data resolution [1,5,6,7,28,49,53,65,81].

Table 6 presents differences in classification in the analysed reviews — a summary of the graphically presented adequacy of forecasting techniques to temporal and spatial resolution, in many cases adapted from previous studies.

To generalise, the persistence approach is dedicated to very short-term/intra-hour, statistical for very short, short and medium-term/intra-hour and intra-day, and statistical for short, medium and long-term/intra-day and day-ahead. In detail, persistence is dedicated to seconds time horizon and distance up to 10 m, statistical models, e.g. ARMA, ARX, NARX for resolution up to 10 m, methods, e.g. ANN, SVR for longer distance and temporal resolution from minutes to hours, NWP from hours to days, sky image from 1 m to 2 km and satellite from 1 km to 10 km [5].

Considering only the time horizon, preferred methods for the following ranges: from 1 min to 10 mins − persistence of ground measurements, from 10 mins to 1 h − ground-based cloud motion vectors (CMVs) data-driven methods, from 1 h to 5 h − satellite-based CMVs and od 5 h to 10 days − NWP models [46]. Total sky images are adequate up to 1 km, satellite images up to 100 km and temporal resolution to a few hours (intra-hour, intra-day), statistical for maximum intra-day forecasts and 1 km, and physical from 1 h and distance from 1 km [81]. The forecast horizon longer than a week ahead with granularity time over 1 h is available only by NWP models [6]. However, hybrid models break the stratification. The components might originate from different groups and utilise various data sources in the sequence or parallel approach. The classical taxonomy of solar energy forecasting techniques based on the relationship between space-time resolution needs to be updated. Statistical methods are frequently considered as pre- and post-processing tools, not a standalone category, and NWPs also with very high resolution can provide the required results [49]. The adequacy of the model to the data needs to be revised also in the case of artificial intelligence taking into account it dynamic development.

5. Development of Solar Energy Forecasting Models Classification

The study of review works revealed inconsistencies in the classification, fragmentation, and duplication of proposals. What draws attention are the fuzzy criteria for the models’ clustering.

Physical models, also known as "white box" models, are based on a theoretical foundation, fundamental laws, and principles, covered in mathematical equations that describe the relationship between the characteristics of a photovoltaic system, solar irradiance, and other environmental and geographical factors that determine the photovoltaic output. These models don’t require a large amount of historical data, but still. Their accuracy depends on the availability of weather forecast data [3,76], which must be developed a priori. The most common physical models are numerical weather forecast models (NWP) [81].

It is emphasised that statistical approaches do not require a full understanding and knowledge of the process and rely on mapping the relation between operation data series along with NWP data. They assume that the future values are determined by its past values [3,76]. However, forecasting based on a model, e.g. ARIMA, begins with initial data exploration, determining the factors influencing its form, and speculations on components and trends. The model should pass substantive verification and explain the phenomenon under study.

Many times, AI models are categorised as a statistical approach. The AI/ML/DL techniques heavily rely on statistical methods. They have common roots, although considering the dynamic development of AI capabilities, distinctions should be made between auto-regressive models and AI-based models in which unsupervised learning algorithms decide on the structure and parameters of the models and adapt them to training data. This problem is sometimes avoided by calling both classical statistical models and AI data-driven models [76].

The challenge is to review hybrid models, although the attempts have been made (e.g., [50,63,74]). In the general case of having n methods, the number of possible approaches is a sum of combinations with/without repetitions for every possible number of elements from 1 to n. Creativity in creating hybrid and ensemble models is limited by the problem of overfitting, which may occur in redundant analyses.

A summary of the adequacy of forecasting models to the time horizon and data source has been proposed by, among other [54,67]. Table 7 includes a modified version of the proposition based on selected review papers that consider AI models’ growing capabilities. It is worth noting that the same lagged or unlagged data can be used in different approaches for model training or direct forecasting.

6. Conclusions

Creating new knowledge is a complex process that involves recognising the state of the art. The literature review plays a crucial role in various scientific disciplines, both as a research genre and as a methodological one, and it cannot be overstated. This work has compared various review studies on solar forecasting that adopt different perspectives and analyse divergent data to identify recent advancements in the field. Renewable energy, particularly solar, has gained much attention over the past two decades, and the trend continues.

The study has shown that there is no single accurate and efficient solar forecasting method for every application. The analysed reviews vary significantly in their approach to the topic, scope, texts included, and the conclusions drawn from them. Some are comprehensive, while others are quite limited and selective. However, there are also common elements among them. In solar energy forecasting technologies, there is potential to enhance accuracy, efficiency, effectiveness, and flexibility through novel, combined interpretable AI models, making adaptations through pre-processing and post-processing improvements.

The authors have attempted to synthesize the typology of forecasting methods presented in the reviewed reviews and to identify each technique’s scope of applicability. Nevertheless, the taxonomy of models, their adequacy to the data, and expected results need to be further revised. The advancement of AI unveils fresh opportunities in the real-time prediction of images and data.

This meta-review serves as a comprehensive analysis. Considering the dynamic development of review research, there is undoubtedly a need for further research and updating of current conclusions. In-depth studies may involve comparisons of selected works from a more homogeneous collection to assess the motivation behind each project and the characteristics and quality of the data used to present state-of-the-art. Future studies might pay attention to hybrid models, analysis of their structure validity, and their classification.

This work allows readers to better understand the solar forecasting methods currently in use and the possibilities of their application in real-world applications. Identifying development trends also creates a substantive basis for further conceptual work on elaborating and implementing new robust solar forecasting methods.