Implementing provisions of the EPBD all Member States require to provide EPC (Energy Performance Certificate) when buildings are c onstructed, sold or rented. The purpose of the certificate is to compare buildings’ performance and inform the end-users. However, quite many mismatches and discrepancies could be found when comparing actual energy consumption with the once declared by the EPC. This mismatch of energy demand is known as Energy Performance Gap (EPG). It was analysed by different researchers on national levels. In the study, an overall overview of the high-performance buildings in Lithuania is performed and EPG is analysed using statistical indicators. Analysis has shown that for class A the EPG varies from −101 % to +77 %. More buildings are found to have a positive Energy Performance Gap. For class A+ and A++ variations are within a narrower interval: from +18 to 76 % and from +23 to 77 % accordingly. It confirms the findings in the other countries that very high-energy performance buildings tend to consume more than predicted. Also it is confirmed that despite differences in national certification methodologies, the same problem (just of different scale) exists and EPC schemes need revisions.

No abstract

No abstract

Increasing energy efficiency requirements lead to lower energy consumption in buildings, but at the same time occupants’ influence on the energy balance of the building during the use phase becomes more crucial. The randomness of the building’s occupancy often leads to the mismatch of the predicted and measured energy demand, also called Energy Performance Gap. Therefore, prediction of occupancy is important both in the design and use phases of the building. The goal of the study is to apply Extreme Learning Machine (ELM) models with different optimisation algorithms – Genetic (GA-ELM) and Simulated Annealing (SA–ELM) for occupancy prediction in an office building based on measured CO2 concentrations. Both models show similar and high accuracy of prediction: R2 – 0.73–0.74 and RMSE – 1.8–1.9 for the whole measured period. Influence of population size, number of neurons, and number of iterations on results accuracy was also analysed and recommendations are given. It was concluded that both methods are suitable for occupancy prediction, but because of different simulation times, SA-ELM is recommended for the Building Management Systems (BMS), where higher speed is required.

No abstract