Lorenzo Nespoli

Fabrizio Sossan, Lorenzo Nespoli, Vasco Medici et al.

We consider the problem of estimating the unobserved amount of photovoltaic (PV) generation and demand in a power distribution network starting from measurements of the aggregated power flow at the point of common coupling (PCC) and local global horizontal irradiance (GHI). The estimation principle relies on modeling the PV generation as a function of the measured GHI, enabling the identification of PV production patterns in the aggregated power flow measurements. Four estimation algorithms are proposed: the first assumes that variability in the aggregated PV generation is given by variations of PV generation, the next two use a model of the demand to improve estimation performance, and the fourth assumes that, in a certain frequency range, the aggregated power flow is dominated by PV generation dynamics. These algorithms leverage irradiance transposition models to explore several azimuth/tilt configurations and explain PV generation patterns from multiple plants with non-uniform installation characteristics. Their estimation performance is compared and validated with measurements from a real-life setup including 4 houses with rooftop PV installations and battery systems for PV self-consumption.

Lorenzo Nespoli, Vasco Medici

In this paper, we propose a distributed control strategy for the design of an energy market. The method relies on a hierarchical structure of aggregators for the coordination of prosumers (agents which can produce and consume energy). The hierarchy reflects the voltage level separations of the electrical grid and allows aggregating prosumers in pools, while taking into account the grid operational constraints. To reach optimal coordination, the prosumers communicate their forecasted power profile to the upper level of the hierarchy. Each time the information crosses upwards a level of the hierarchy, it is first aggregated, both to strongly reduce the data flow and to preserve the privacy. In the first part of the paper, the decomposition algorithm, which is based on the alternating direction method of multipliers (ADMM), is presented. In the second part, we explore how the proposed algorithm scales with increasing number of prosumers and hierarchical levels, through extensive simulations based on randomly generated scenarios.

Federico Rosato, Lorenzo Nespoli, Vasco Medici

Smart meters provide relevant information for impedance identification, but they lack global phase alignment and internal network nodes are often unobserved. A few methods for this setting were developed, but they have requirements on data correlation and/or network topology. In this paper, we offer a unifying view of data- and structure-driven identifiability issues, and use this groundwork to propose a method for underdetermined impedance identification. The method can handle intrinsically ambiguous topologies and data; its output is not forcedly a single estimate, but instead a collection of data-compatible impedance assignments. It uses a library of plausible commercial cable types as a prior to refine the solutions, and we show how it can support topology identification workflows built around known georeferenced joints without degree guarantees. The method depends on a small number of non-sensitive parameters and achieves high identification performance on a sizeable benchmark case even with low-size injection/voltage datasets. We identify key steps that can be accelerated via GPU-based parallelization. Finally, we assess the tolerance of the identification to noisy input.

Lorenzo Nespoli, Anubhab Biswas, Vasco Medici

Forecast reconciliation, an ex-post technique applied to forecasts that must satisfy constraints, has been a prominent topic in the forecasting literature over the past two decades. Recently, several efforts have sought to extend reconciliation methods to the probabilistic settings. Nevertheless, formal theorems demonstrating error reduction in nonlinear contexts, analogous to those presented in Panagiotelis et al.(2021), are still lacking. This paper addresses that gap by establishing such theorems for various classes of nonlinear hypersurfaces and vector-valued functions. Specifically, we derive an exact analog of Theorem 3.1 from Panagiotelis et al.(2021) for hypersurfaces with constant-sign curvature. Additionally, we provide probabilistic guarantees for the broader case of hypersurfaces with non-constant-sign curvature and for general vector-valued functions. To support reproducibility and practical adoption, we release a JAX-based Python package, \emph{to be released upon publication}, implementing the presented theorems and reconciliation procedures.

Dario Marvin, Lorenzo Nespoli, Davide Strepparava et al.

The ability to forecast the concentration of air pollutants in an urban region is crucial for decision-makers wishing to reduce the impact of pollution on public health through active measures (e.g. temporary traffic closures). In this study, we present a machine learning approach applied to the forecast of the day-ahead maximum value of the ozone concentration for several geographical locations in southern Switzerland. Due to the low density of measurement stations and to the complex orography of the use case terrain, we adopted feature selection methods instead of explicitly restricting relevant features to a neighbourhood of the prediction sites, as common in spatio-temporal forecasting methods. We then used Shapley values to assess the explainability of the learned models in terms of feature importance and feature interactions in relation to ozone predictions; our analysis suggests that the trained models effectively learned explanatory cross-dependencies among atmospheric variables. Finally, we show how weighting observations helps in increasing the accuracy of the forecasts for specific ranges of ozone's daily peak values.

Lorenzo Nespoli, Vasco Medici

Gradient boosted trees are competition-winning, general-purpose, non-parametric regressors, which exploit sequential model fitting and gradient descent to minimize a specific loss function. The most popular implementations are tailored to univariate regression and classification tasks, precluding the possibility of capturing multivariate target cross-correlations and applying structured penalties to the predictions. In this paper, we present a computationally efficient algorithm for fitting multivariate boosted trees. We show that multivariate trees can outperform their univariate counterpart when the predictions are correlated. Furthermore, the algorithm allows to arbitrarily regularize the predictions, so that properties like smoothness, consistency and functional relations can be enforced. We present applications and numerical results related to forecasting and control.

Lorenzo Nespoli, Vasco Medici, Kristijan Lopatichki et al.

We present a comparative study of different probabilistic forecasting techniques on the task of predicting the electrical load of secondary substations and cabinets located in a low voltage distribution grid, as well as their aggregated power profile. The methods are evaluated using standard KPIs for deterministic and probabilistic forecasts. We also compare the ability of different hierarchical techniques in improving the bottom level forecasters' performances. Both the raw and cleaned datasets, including meteorological data, are made publicly available to provide a standard benchmark for evaluating forecasting algorithms for demand-side management applications.

Lorenzo Nespoli, Vasco Medici

In this paper, we present a method to determine the global horizontal irradiance (GHI) from the power measurements of one or more PV systems, located in the same neighborhood. The method is completely unsupervised and is based on a physical model of a PV plant. The precise assessment of solar irradiance is pivotal for the forecast of the electric power generated by photovoltaic (PV) plants. However, on-ground measurements are expensive and are generally not performed for small and medium-sized PV plants. Satellite-based services represent a valid alternative to on site measurements, but their space-time resolution is limited. Results from two case studies located in Switzerland are presented. The performance of the proposed method at assessing GHI is compared with that of free and commercial satellite services. Our results show that the presented method is generally better than satellite-based services, especially at high temporal resolutions.