Bearing in mind European Green Deal assumptions regarding a significant reduction of green house emissions, electricity generation from Renewable Energy Sources (RES) is more and more important nowadays. Besides this, accurate and reliable electricity generation forecasts from RES are needed for capacity planning, scheduling, managing inertia and frequency response during contingency events. The recent three years have proved that Machine Learning (ML) models are a promising solution for forecasting electricity generation from RES. In this review, the 8-step methodology was used to find and analyze 262 relevant research articles from the Scopus database. Statistic analysis based on eight criteria (ML method used, renewable energy source involved, affiliation location, hybrid model proposed, short term prediction, author name, number of citations, and journal title) was shown. The results indicate that (1) Extreme Learning Machine and ensemble methods were the most popular methods used for electricity generation forecasting from RES in the last three years (2020–2022), (2) most of the research was carried out for wind systems, (3) the hybrid models accounted for about a third of the analyzed works, (4) most of the articles concerned short-term models, (5) the most researchers came from China, (6) and the journal which published the most papers in the analyzed field was Energies. Moreover, strengths, weaknesses, opportunities, and threats for the analyzed ML forecasting models were identified and presented in this paper.

Problems with inaccurate prediction of electricity generation from photovoltaic (PV) farms cause severe operational, technical, and financial risks, which seriously affect both their owners and grid operators. Proper prediction results are required for optimal planning the spinning reserve as well as managing inertia and frequency response in the case of contingency events. In this work, the impact of a number of meteorological parameters on PV electricity generation in Poland was analyzed using the Pearson coefficient. Furthermore, seven machine learning models using Lasso Regression, K–Nearest Neighbours Regression, Support Vector Regression, AdaBoosted Regression Tree, Gradient Boosted Regression Tree, Random Forest Regression, and Artificial Neural Network were developed to predict electricity generation from a 0.7 MW solar PV power plant in Poland. The models were evaluated using determination coefficient ($R^2$), the mean absolute error ($MAE$), and root mean square error ($RMSE$). It was found out that horizontal global irradiation and water saturation deficit have a strong proportional relationship with the electricity generation from PV systems. All proposed machine learning models turned out to perform well in predicting electricity generation from the analyzed PV farm. Random Forest Regression was the most reliable and accurate model, as it received the highest $R^2$ (0.94) and the lowest $MAE$ (15.12 kWh) and $RMSE$ (34.59 kWh).

Many construction projects fail to meet deadlines or they exceed the assumed budget. This scenario is particularly common in the case of innovative projects, in which too late identification of a high risk of delays and exceeding the assumed costs makes a potentially profitable project untenable. A high risk level, far exceeding the level of risk in standard non-innovative projects, is a characteristic feature of the realization phase of innovative projects. This is associated not only with greater complexity of the design and construction phases, but also with the problems with application of new technologies and prototype solutions, lack of qualified personnel with suitable expertise in specialized areas, and with the ability to properly identify the gaps between available and required knowledge and skills. This paper discusses the process of effective risk management in innovative projects on the example of the realization phase of an innovative, energy-efficient and sustainable building of the Laboratory of Intelligent Building in Cracow - DLJM Lab, from the point of view of DORBUD S.A., its general contractor. In this paper, a new approach to risk management process for innovative construction projects is proposed. Risk management process was divided into five stages: gathering information, identification of the important unwanted events, first risk assessment, development and choice of risk reaction strategies, assessment of the residual risk after introducing risk reactions. 18 unwanted events in an innovative construction project were identified. The first risk assessment was carried out using two-parametric risk matrix, in which the probability of unwanted event occurrence and its consequences were analysed. Three levels of risks were defined: tolerable, controlled and uncontrolled. Risk reactions to each defined unwanted event were developed. The following risk reaction types were considered: risk retention, risk reduction, risk transfer and risk elimination. Three-parametric risk matrix was developed to make it possible to assess risk after implementing risk reactions. The possibility of implementing risk management was inversely proportional to the probability of unwanted event occurrence and its contribution to the project outcome. Introducing this risk management strategy allowed to significantly reduce the risk of the innovative construction project. It proved to be an effective tool to reduce risk to an acceptable level. It had a significant contribution to carrying out the project within the assumed time, budget and quality standards.

Nowadays, horizontal directional drilling (HDD) technology is one of the most popular trenchless construction methods for installing pipelines under obstacles. Both risk analysis and risk management are key tools helping to meet today’s challenging trenchless construction project demands connected with quality, deadlines, costs, and legal issues. In this paper, a new model based on proactive and holistic approaches is presented, which is an extension from traditional risk analysis toward complex risk management in HDD projects. Fuzzy fault tree analysis, fuzzy weighted index, and a risk response matrix supported the risk management process. Overall, 147 risk remediation strategies for all the identified HDD risks were proposed. The following types of risk response strategies were applied: passive and active risk retention, risk transfer, risk elimination, and risk cause or effect reduction. The practical application of the proposed risk management model for HDD projects was shown in an example. The application of the proposed risk management model allows one to effectively reduce the risk of basic events occurrence and provides a remarkable reduction of the risk of the top event’s occurrence.

Nowadays we can observe a growing demand for installations of new gas pipelines in Europe. A large number of them are installed using trenchless Horizontal Directional Drilling (HDD) technology. The aim of this work was to develop and compare new machine learning models dedicated for risk assessment in HDD projects. The data from 133 HDD projects from eight countries of the world were gathered, profiled, and preprocessed. Three machine learning models, logistic regression, random forests, and Artificial Neural Network (ANN), were developed to predict the overall HDD project outcome (failure free installation or installation likely to fail), and the occurrence of identified unwanted events. The best performance in terms of recall and accuracy was achieved for the developed ANN model, which proved to be efficient, fast and robust in predicting risks in HDD projects. Machine learning applications in the proposed models enabled eliminating the involvement of a group of experts in the risk assessment process and therefore significantly lower the costs associated with the risk assessment process. Future research may be oriented towards developing a comprehensive risk management system, which will enable dynamic risk assessment taking into account various combinations of risk mitigation actions.

Nowadays, one of the characteristic features of construction industry is an increased complexity of a growing number of projects. Almost each construction project is unique, has its project-specific purpose, its own project structural complexity, owner's expectations, ground conditions unique to a certain location, and its own dynamics. Failure costs and costs resulting from unforeseen problems in complex construction projects are very high. Project complexity drivers pose many vulnerabilities to a successful completion of a number of projects. This paper discusses the process of effective risk management in complex construction projects in which renewable energy sources were used, on the example of the realization phase of the ENERGIS teaching-laboratory building, from the point of view of DORBUD S.A., its general contractor. This paper suggests a new approach to risk management for complex construction projects in which renewable energy sources were applied. The risk management process was divided into six stages: gathering information, identification of the top, critical project risks resulting from the project complexity, construction of the fault tree for each top, critical risks, logical analysis of the fault tree, quantitative risk assessment applying fuzzy logic and development of risk response strategy. A new methodology for the qualitative and quantitative risk assessment for top, critical risks in complex construction projects was developed. Risk assessment was carried out applying Fuzzy Fault Tree analysis on the example of one top critical risk. Application of the Fuzzy sets theory to the proposed model allowed to decrease uncertainty and eliminate problems with gaining the crisp values of the basic events probability, common during expert risk assessment with the objective to give the exact risk score of each unwanted event probability.