arXiv subjects

Giovanni Sansavini

Publications and source records attributed to Giovanni Sansavini.

30 records · Page 2Linked to original sources

arXiv2024

An Improved Anomaly Detection Model for Automated Inspection of Power Line Insulators

Inspection of insulators is important to ensure reliable operation of the power system. Deep learning is being increasingly exploited to automate the inspection process by leveraging object detection models to analyse aerial images captured by drones. A purely object detection-based approach, however, suffers from class imbalance-induced poor performance, which can be accentuated for infrequent and hard-to-detect incipient faults. This article proposes the use of anomaly detection along with object detection in a two-stage approach for incipient fault detection in a data-efficient manner. An explainable convolutional one-class classifier is adopted for anomaly detection. The one-class formulation reduces the reliance on plentifully available images of faulty insulators, while the explainability of the model is expected to promote adoption by the industry. A modified loss function is developed that addresses computational and interpretability issues with the existing model, also allowing for the integration of other losses. The superiority of the novel loss function is demonstrated with MVTec-AD dataset. The models are trained for insulator inspection with two datasets -- representing data-abundant and data-scarce scenarios -- in unsupervised and semi-supervised settings. The results suggest that including as few as five real anomalies in the training dataset significantly improves the model's performance and enables reliable detection of rarely occurring incipient faults in insulators.

cs.CV↗

arXiv2024

Minimum-regret hydrogen supply chain strategies to foster the energy transition of European hard-to-abate industries

Low-carbon hydrogen (H2) is envisioned to play a central role in decarbonizing European hard-to-abate industries, such as refineries, ammonia, methanol, steel, and cement. To enable its widespread use, H2 supply chain (HSC) infrastructure is required. Mature and economically viable low-carbon H2 production pathways include steam methane reforming (SMR) of natural gas coupled with carbon dioxide capture and storage (CCS), water-electrolysis from renewable electricity, biomethane reforming, and biomass gasification. However, uncertainties surrounding demand and feedstock availabilities hamper their proliferation. Here, we investigate the impact of uncertainty in H2 demand and biomass availability on the optimal HSC design. The HSC is modeled as a network of H2 production and consumption sites that are interconnected with H2 and biomass transport technologies. A CCS supply chain is modeled alongside the HSC. The cost-optimal HSC design is determined based on a linear optimization problem that considers a regional resolution and a multi-year time horizon (2022-2050). We adopt a scenario-based uncertainty quantification approach and define discrete H2 demand and biomass availability scenarios. Applying a minimum-regret strategy, we show that sufficiently large low-carbon H2 production capacities (about 9.6 Mt/a by 2030) are essential to flexibly scale up HSCs and accommodate H2 demands of up to 35 Mt/a by 2050. While biomass-based H2 production emerges as the most cost-efficient low-carbon H2 production pathway, investments are not recommended unless the availability of biomass feedstocks is guaranteed. Instead, investments in SMR-CCS and electrolysis often offer greater flexibility. In addition, we highlight the importance of CCS infrastructure, which is required across scenarios.

physics.soc-ph↗

arXiv2024

Funplex: A Modified Simplex Algorithm to Efficiently Explore Near-Optimal Spaces

Modeling to generate alternatives (MGA) is an increasingly popular method in energy system optimization. MGA explores the near-optimal space, namely, system alternatives whose costs are within a certain fraction of the globally optimal cost. Real-world stakeholders may prefer these alternatives due to intangible factors. Nonetheless, widespread MGA adoption is hampered by its additional computational burden. Current MGA methods identify boundary points of the near-optimal space through repeated, independent optimization problems. Hundreds of model runs are usually required, and such individual runs are often inefficient because they repeat calculations or retrace previous trajectories. In this study, we transcend such limitations by introducing a novel algorithm called Funplex, which uses methods from multi-objective Simplex to optimize many MGA objectives with minimal computational redundancy. For a simple linear-programming energy hub case study, we show that Funplex is five times faster than existing methods and yields higher-quality near-optimal spaces. Furthermore, sensitivity analyses suggest that Funplex scales well with the number of investment variables, making it promising for capacity planning models. The current proof-of-concept implementation based on a full multi-objective tableau may face memory and stability limitations for large models. Nonetheless, future developments based on more advanced versions of Simplex may overcome such barriers, thereby making MGA more accessible and standard among modeling teams.

math.OC↗

arXiv2023

Uncertainty-aware deep learning for digital twin-driven monitoring: Application to fault detection in power lines

Deep neural networks (DNNs) are often coupled with physics-based models or data-driven surrogate models to perform fault detection and health monitoring of systems in the low data regime. These models serve as digital twins to generate large quantities of data to train DNNs which would otherwise be difficult to obtain from the real-life system. However, such models can exhibit parametric uncertainty that propagates to the generated data. In addition, DNNs exhibit uncertainty in the parameters learnt during training. In such a scenario, the performance of the DNN model will be influenced by the uncertainty in the physics-based model as well as the parameters of the DNN. In this article, we quantify the impact of both these sources of uncertainty on the performance of the DNN. We perform explicit propagation of uncertainty in input data through all layers of the DNN, as well as implicit prediction of output uncertainty to capture the former. Furthermore, we adopt Monte Carlo dropout to capture uncertainty in DNN parameters. We demonstrate the approach for fault detection of power lines with a physics-based model, two types of input data and three different neural network architectures. We compare the performance of such uncertainty-aware probabilistic models with their deterministic counterparts. The results show that the probabilistic models provide important information regarding the confidence of predictions, while also delivering an improvement in performance over deterministic models.

cs.LG↗

arXiv2023

Resilient Design in Nuclear Energy: Critical Lessons from a Cross-Disciplinary Review of the Fukushima Dai-ichi Nuclear Accident

Nuclear energy has been gaining momentum recently as one of the solutions to tackle climate change. However, significant environmental and health-risk concerns remain associated with potential accidents. Despite significant preventive efforts, we must acknowledge that accidents may happen and, therefore, develop strategies and technologies for mitigating their consequences. In this paper, we review the Fukushima Dai-ichi Nuclear Power Plant accident, synthesize the time series and accident progressions across relevant disciplines, including in-plant physics and engineering systems, operators' actions, emergency responses, meteorology, radionuclide release and transport, land contamination, and health impacts. In light of the latest observations and simulation studies, we identify three key factors that exacerbated the consequences of the accident: (1) the failure of Unit 2 containment venting, (2) the insufficient integration of radiation measurements and meteorology data in the evacuation strategy, and (3) the limited risk assessment and emergency preparedness. We propose new research and development directions to improve the resilience of nuclear power plants, including (1) meteorology-informed proactive venting, (2) machine learning-enabled adaptive evacuation zones, and (3) comprehensive risk-informed emergency planning while leveraging the experience from responses to other disasters.

physics.soc-ph↗

arXiv2022

Object detection-based inspection of power line insulators: Incipient fault detection in the low data-regime

Deep learning-based object detection is a powerful approach for detecting faulty insulators in power lines. This involves training an object detection model from scratch, or fine tuning a model that is pre-trained on benchmark computer vision datasets. This approach works well with a large number of insulator images, but can result in unreliable models in the low data regime. The current literature mainly focuses on detecting the presence or absence of insulator caps, which is a relatively easy detection task, and does not consider detection of finer faults such as flashed and broken disks. In this article, we formulate three object detection tasks for insulator and asset inspection from aerial images, focusing on incipient faults in disks. We curate a large reference dataset of insulator images that can be used to learn robust features for detecting healthy and faulty insulators. We study the advantage of using this dataset in the low target data regime by pre-training on the reference dataset followed by fine-tuning on the target dataset. The results suggest that object detection models can be used to detect faults in insulators at a much incipient stage, and that transfer learning adds value depending on the type of object detection model. We identify key factors that dictate performance in the low data-regime and outline potential approaches to improve the state-of-the-art.

cs.CV↗

arXiv2021

Bayesian Origin-Destination Estimation in Networked Transit Systems using Nodal In- and Outflow Counts

We propose a Bayesian inference approach for static Origin-Destination (OD)-estimation in large-scale networked transit systems. The approach finds posterior distribution estimates of the OD-coefficients, which describe the relative proportions of passengers travelling between origin and destination locations, via a Hamiltonian Monte Carlo sampling procedure. We suggest two different inference model formulations: the instantaneous-balance and average-delay model. We discuss both models' sensitivity to various count observation properties, and establish that the average-delay model is generally more robust in determining the coefficient posteriors. The instantaneous-balance model, however, requires lower resolution count observations and produces comparably accurate estimates as the average-delay model, pending that count observations are only moderately interfered by trend fluctuations or the truncation of the observation window, and sufficient number of dispersed data records are available. We demonstrate that the Bayesian posterior distribution estimates provide quantifiable measures of the estimation uncertainty and prediction quality of the model, whereas the point estimates obtained from an alternative constrained quadratic programming optimisation approach only provide the residual errors between the predictions and observations. Moreover, the Bayesian approach proves more robust in scaling to high-dimensional underdetermined problems. The Bayesian instantaneous-balance OD-coefficient posteriors are determined for the New York City (NYC) subway network, based on several years of entry and exit count observations recorded at station turnstiles across the network. The average-delay model proves intractable on the real-world test scenario, given its computational time complexity and the incompleteness as well as coarseness of the turnstile records.

stat.AP↗

arXiv2020

Multi-agent maintenance scheduling based on the coordination between central operator and decentralized producers in an electricity market

Condition-based and predictive maintenance enable early detection of critical system conditions and thereby enable decision makers to forestall faults and mitigate them. However, decision makers also need to take the operational and production needs into consideration for optimal decision-making when scheduling maintenance activities. Particularly in network systems, such as power grids, decisions on the maintenance of single assets can affect the entire network and are, therefore, more complex. This paper proposes a two-level multi-agent decision support systems for the generation maintenance decision (GMS) of power grids in an electricity markets. The aim of the GMS is to minimize the generation cost while maximizing the system reliability. The proposed framework integrates a central coordination system, i.e. the transmission system operator (TSO), and distributed agents representing power generation units that act to maximize their profit and decide about the optimal maintenance time slots while ensuring the fulfilment of the energy demand. The objective function of agents (power generation companies) is based on the reward and the penalty that they obtain from the interplay between power production and loss of production due to failure, respectively. The optimal strategy of agents is then derived using a distributed algorithm, where agents choose their optimal maintenance decision and send their decisions to the central coordinating system. The TSO decides whether to accept the agents' decisions by considering the market reliability aspects and power supply constraints. To solve this coordination problem, we propose a negotiation algorithm using an incentive signal to coordinate the agents' and central system's decisions such that all the agents' decisions can be accepted by the central system. We demonstrate the efficiency of our proposed algorithm using a IEEE 39 bus system.

cs.MA↗

arXiv2020

Integrating reliability and resilience to support microgrid design

Quantifying the potential benefits of microgrids in the design phase can support the transition of passive distribution networks into microgrids. At current, reliability and resilience are the main drivers for this transition. Therefore, this paper presents a mathematical optimization model to support the retrofitting of distribution networks into microgrids integrating techno-economic, resilience and reliability objectives. Storage and distributed generation are optionally installed to complement renewable generation, enabling the microgrid to supply priority demands during stochastic islanding events with uncertain duration. For a comprehensive quantification and optimization of microgrid resilience and reliability, islanding due to external events is combined with a detailed model of internal faults. Minimizing the interruption costs yields optimal capacities and placements of distributed energy resources and new lines for reconfiguration. The proposed method produces microgrid designs with up to 95% reliability and resilience gain and moderate cost increase in two benchmark distribution networks using data from the US Department of Energy. The developed methodology is scalable to large networks owing to the tailored Column-and-Constraint-Generation approach.

math.OC↗

arXiv2019

Can models for long-term decarbonization policies guarantee security of power supply? A perspective from gas and power sector coupling

The assessment of adequacy and security of the energy system requires the detailed knowledge of physical and operational characteristics. In contrast, studies concerning energy transitions employ stylized models that oftentimes ignore the technical properties but have a lasting influence on long-term energy policies. This paper investigates the gap between energy system planning and operational models by linking these two perspectives: (1) a long-term investment model with low spatial resolution and high level of aggregation, and (2) a spatially resolved system security model that captures the interdependences between the backbone of the electric power sector, i.e., the electricity and the gas infrastructures. We assess EU decarbonization pathways of the electricity sector towards 2050 by integrating the investment decisions of the long-term planning model and the safety performance of the resulting system operations via the security assessment model. In a large RES deployment scenario, we investigate two flexibility options: gas power plants and cross-country transmission expansion. Using the integrated model, we analyze how the adequacy and security of supply under extreme short-term operational conditions impact the long-term planning of the energy system and the investment decision-making. We provide country specific recommendations for UK. Results indicate weaknesses in the gas-electricity system and suggest improvements on capacity allocation.

eess.SY↗

arXiv2019

Resilience Evaluation Framework for Integrated Critical Infrastructure-Community Systems under Seismic Hazard

In this paper, an agent-based modeling framework to evaluate the seismic resilience of an integrated system comprising the community and its civil infrastructure systems is proposed. Specifically, an agent-based model of the recovery process of civil infrastructure systems is incorporated into a previously developed compositional supply/demand seismic resilience quantification framework. The proposed model represents the behavior of the operators of civil infrastructure systems as they strive to recover their functionality in the aftermath of an earthquake as well as their mutual interactions and the interactions with the community they provide services to. A case study of the seismic resilience of a virtual system comprising the electric power supply system, the transportation system and the community (EPSS-TS-Community system) is conducted using the proposed framework. A parametric investigation is carried out to examine the effect of different earthquake magnitude scenarios as well as different behaviors of the involved agents and their interaction on the seismic resilience of the virtual system. It was demonstrated that the proposed agent-based modeling approach is effective in representing the interactions among different participants in the recovery process. It was also revealed that timely and well-planned intervention in the recovery process can be effective in alleviating the post-earthquake lack of resilience resulting from the insufficient supply of civil infrastructure service to meet the community demands. Therefore, the proposed framework could be employed to formulate the recovery trajectory of the intertwined socio-technical system subjected to different earthquake scenarios. The interplay among different agents, as well as the interdependence between civil infrastructure systems is found to profoundly shape the recovery path for this integrated EPSS-TS-Community system.

physics.soc-ph↗

arXiv2019

Agent-Based Recovery Model for Seismic Resilience Evaluation of Electrified Communities

In this paper, an agent-based framework to quantify the seismic resilience of an Electric Power Supply System (EPSS) and the community it serves is presented. Within the framework, the loss and restoration of the EPSS power generation and delivery capacity and of the power demand from the served community are used to assess the electric power deficit during the damage absorption and recovery processes. Damage to the components of the EPSS and of the community built environment is evaluated using the seismic fragility functions. The restoration of the community electric power demand is evaluated using the seismic recovery functions. However, the post-earthquake EPSS recovery process is modeled using an agent-based model with two agents, the EPSS Operator and the Community Administrator. The resilience of the EPSS-Community system is quantified using direct, EPSS-related, and societal, community-related, indicators. Parametric studies are carried out to quantify the influence of different seismic hazard scenarios, agent characteristics, and power dispatch strategies on the EPSS-Community seismic resilience. The use of the agent-based modeling framework enabled a rational formulation of the post-earthquake recovery phase and highlighted the interaction between the EPSS and the community in the recovery process not quantified in resilience models developed to date. Furthermore, it shows that the resilience of different community sectors can be enhanced by different power dispatch strategies. The proposed agent-based EPSS-Community system resilience quantification framework can be used to develop better community and infrastructure system risk governance policies.

physics.soc-ph↗