The paper presents experiments with application of Radial Basis Function (RBF) network to Short Term Load Forecasting (STLF) problems. The proposed regression model is used to forecast forty-eight hours ahead electric load. The model has been implemented on real data: inputs to the RBF are past loads, weekday and special-day coding and the output is the load forecast for the given hour. Ordinary RBF was applied in the experiments. The centers of the Gaussian basis functions were selected on the base of the quasi-Newton algorithm. Mean absolute percentage error of about 4% is derived from the data from the Power System in Crete. The performance of the proposed model has been compared with simulations performed by the MLP network, and former models developed for the distribution company in Poland. © 2001 IEEE

This paper presents a comprehensive analysis of public procurement documents in the domain of university buildings taken from the e-procurement platform, particularly focusing on their transformation towards more efficient energy consumption. Using a corpus of the titles of the public procurement documents from 2020 to 2022, we used Latent Dirichlet Allocation (LDA) for topic modeling to understand the key thematic areas of focus. The methodology presented in this study incorporated a bifurcated approach. This two-stage procedure began with preprocessing and dictionary creation from the corpus of titles of procurement documents. Following this, the Latent Dirichlet Allocation (LDA) model was employed for topic extraction and trend analysis, thereby providing a comprehensive understanding of the thematic progression in procurement practices over time. Our analysis revealed a shift in emphasis from modernization towards the adoption of energy-saving technologies as well as a growing focus on broader sustainability initiatives. However, a less prevalent topic was adherence to cooling & heating systems, suggesting potential areas for improvement in procurement practices. These findings contribute to the growing body of knowledge on sustainable procurement in university buildings and offer valuable insight for universities to enhance their energy efficiency strategies.

This paper investigates the problem of the short-term electrical load forecasting (STLF) in medium size utility. The model consisted of ensemble of the neural predictors with special heuristic input selection procedure is presented. We also discuss the problem of uncertainties involved in load forecasts, and confidence intervals calculation methods for neural STLF predictors.

The assessment and monitoring of Polish cities in terms of providing electronic services were explored. It is noticed that a comprehensive analysis of the electronic maturity of the municipality's management system includes evaluations of electronic services by external and internal stakeholders. The indicators of Polish cities in the “Smart City Ranking” were accepted as an assessment of external stakeholders. The conducted informational and contextual analysis testified that Warsaw and Krakow have exemplary practices in “Governance” and “Activities”. E-services in the areas of “Health & Safety”, “Mobility” and “Opportunities (Work & School)” need improvement. The second measurement analysis used the maturity assessment model of the electronic project and program management systems. The e-maturity of municipal e-projects as well as electronic program management systems is based on ICT characteristics. The expert assessment matrices and optimal values of initial indicators of e-maturity formed for each project management knowledge area. The calculation results of the digital implementation of management of municipal e-projects and e-programs by individual components are presented in profile form. This makes it possible to select the optimal set of actions required to achieve a higher level of e-maturity.