State estimation in distribution power systems is increasingly challenged by the proliferation of distributed energy resources (DERs), bidirectional power flows, and the growing complexity of unbalanced network topologies. Physics-Informed Neural Networks (PINNs) offer a compelling solution by integrating machine learning with the physical laws that govern power system behavior. This paper introduces a PINN-based framework for state estimation in unbalanced distribution systems, leveraging available data and embedded physical knowledge to improve accuracy, computational efficiency, and robustness across diverse operating scenarios. The proposed method is evaluated on four IEEE test feeders—IEEE 13, 34, 37, and 123—using synthetic datasets generated via OpenDSS to emulate realistic operating scenarios, and demonstrates significant improvements over baseline models. Notably, the PINN achieves up to a 97% reduction in current estimation errors while maintaining high voltage prediction accuracy. Extensive simulations further assess model performance under noisy inputs and partial observability, where the PINN consistently outperforms conventional data-driven approaches. These results highlight the method’s ability to generalize under uncertainty, accelerate convergence, and preserve physical consistency in simulated real-world conditions without requiring large volumes of labeled training data.
Renewable energy source-fed heat pumps (HPs) may perform up to very high-efficiency standards, offering a promising tool in the wider residential heat decarbonization effort. In this context, this paper investigates different heating configurations utilizing various renewable thermal sources in conjunction with an HP-based system in order to determine the optimal configuration in terms of efficiency, using an existing, fully functioning residential building in Zaragoza, Spain, as our case study, comprising 40 dwellings. Four different HP configurations are investigated:, (i) an air-source system, (ii) a ground-source system, (iii) a dual-source system with solar thermal collectors, and (iv) a triple-source system based on solar, geothermal, and ambient sources. For the purpose of such investigation, detailed dynamic energy simulations are conducted through the use of the INTEMA.building tool (developed in Modelica), applying a multi-objective optimization process that aims at minimizing both the annual electricity consumption and the net present cost. It is demonstrated that the renewable thermally driven HPs are more efficient than the conventional, air-source ones, with the seasonal coefficient of performance increasing by 9.98% (ground source), 4.57% (dual source), and 17.40% (triple source), compared to the air-source heat pump system. Finally, it is revealed (via integrated techno-economic analyses) that the most effective and economical design is the dual source system, while the most expensive is the ground-source configuration. These findings can guide the ongoing design efforts on green residential heat solutions at both research and commercial implementation level.