Research and practice experience have shown that in the Republic of Serbia, vine pruning residues (VPRs) from vineyard production are mostly partially ploughed or uncontrollably burned in fields. Uncontrolled burning of VPRs in fields can destroy flora and fauna and cause uncontrolled fires. On the other hand, on an annual basis, the resulting VPRs can completely replace the fossil fuels used for thermal energy production on these estates and significantly reduce the emission of pollutants from fossil fuels. The novelty of this study lies in the fact that the research was conducted on a very young vineyard, four years old, and the results show that the agricultural property is fully sustainable in terms of thermal energy needs. The research aimed to investigate the energy potential of VPRs at the vineyard located in the Mrčić settlement in Western Serbia. The research results include the following grape varieties: Tamjanika, Morava, Cabernet Sauvignon, and Cabernet Franc. The average yield of VPR biomass for all tested varieties was 0.387 kg/vine or 1741.50 kg/ha. The lower calorific values for the tested biomass samples at 15% moisture content ranged from 14,668 kJ/kg to 14,258 kJ/kg, while the upper values ranged from 16,099 kJ/kg to 15,721 kJ/kg. The total energy potential of biomass obtained from a vineyard, expressed in final energy, was 41.90 MWh/year. In the observed vineyard, for the same equivalent value, biomass from VPRs was 3.57 times cheaper compared to brown coal and 8.26 times cheaper compared to diesel fuel.

This paper presents an adaptive short-term intraday load forecasting strategy designed for the operational requirements of transmission and distribution system operators. Standard forecasting approaches often report strong performance on selected periods, yet real utility operations require accurate predictions for every day and every hour of the year. Deviations during the operating day, caused by unexpected changes in consumer behavior, introduce forecasting errors and financial risk. To address this problem, we propose a multi-tiered forecasting model that selects the base method according to the availability of historically similar days. When many similar days exist, the model uses a pretrained artificial neural network, while linear regression is applied under moderate similarity conditions, and an arithmetic mean is used when only a few similar days are available. A real-time delta correction layer is applied in all cases, using recent intraday measurements to forecast short-term error and adjust the baseline output. This approach enables rapid adaptation to atypical days and intraday anomalies. Testing on five years of utility data demonstrates that the method maintains consistently low MAPE across all days and all hours, providing the level of accuracy needed for intraday market operations and system balancing.