Annual Reliability and Maintainability Symposium (RAMS)

Quantum Inference for Reliability Assessment

Gabrieln San Martí Silva, Enrique López Droguett

Published Jan 23, 2023• 1 citation

Abstract

The increased availability of specialized quantum hardware has made possible the exploration of the field by the general scientific community. Enterprises such as IBM, Google, and Microsoft have launched or will launch shortly cloud quantum computing services, which will accelerate forward the development of the field even further. It is, therefore, necessary to prepare the RAMS community to harness the advantages that quantum computing may offer to our discipline. In this paper, we present a proposed application for efficient probabilistic inference in Bayesian networks using gate-based quantum computing and a quantum algorithm called Amplitude Amplification. The proposed methodology is exemplified on a non-trivial Bayesian network, composed of nodes representing discrete probability distributions. To the best of our knowledge, this is the first attempt to use Bayesian networks in combination with Amplitude Amplification for the risk and reliability assessment context. The results indicate that the usage of quantum computing can effectively increase the efficiency of the sampling process, decreasing the number of samples required to obtain estimates of similar quality when compared to a traditional Monte Carlo sampling approach.

DOI: 10.1109/rams51473.2023.10088259

Related papers

Incorporating Continuous Distributions in Quantum Bayesian Networks for Reliability Assessment

Lavìnia Maria Mendes Araújo, Rui Silva, Enrique López Droguett +2 more

Operational demands in industries, such as the energy sector, underscore the critical need for reliable equipment capable of withstanding long-term planning and unpredictable factors.Reliability assessment is important for maintaining productivity and optimizing maintenance strategies, especially in scenarios where data limitations challenge traditional assessment methods.In this context, Bayesian inference has emerged as a dynamic tool to update reliability estimates using data from various hierarchical levels.However, conventional simulation techniques may lack computational efficiency when dealing with the reliability estimation of complex systems, creating opportunities to explore alternative approaches such as quantum computation techniques.Quantum Computing leverages principles of quantum mechanics, such as superposition and entanglement, to try to address these computational challenges more effectively.Previous works have applied quantum Bayesian networks using amplitude amplification methods to the context of risk and reliability, focusing on nodes representing discrete probability distributions.This research aims to enhance this approach by incorporating continuous marginal and conditional probabilities into the analysis, which is particularly relevant for systems that rely on these distributions to model events.We explore the encoding of continuous probability distributions within the amplitude amplification framework, aiming to improve the efficiency and precision of probabilistic inference.Additionally, we apply this methodology to Bayesian networks, benchmarking the performance of quantum methods against classical simulation techniques like Monte Carlo to identify scenarios where quantum techniques demonstrate clear advantages.

European Safety and Reliability Conference (ESREL)Jan 1, 20250 citations

Quantum-Enhanced Reliability Assessment of Power Networks in Response to Wildfire Events

Gabriel San Martín Silva, Tarannom Parhizkar, Hieu Trung Nguyen +1 more

As the risk associated with wildfires in the western United States increases every year, it becomes fundamental to research alternatives to both improve the resilience and reliability of engineering systems against those types of events, as well as mitigate the effects that wildfire emergencies may have on human population and critical infrastructure. An often- overlooked cause of wildfire emergencies are failures in power line systems and electricity distribution networks. Given the immense number of factors that can affect the probability of a power line ignition occurring, the analysis quickly becomes intractable for traditional probabilistic inference methodologies. In this paper, a quantum-enhanced probabilistic sampling and inference application is proposed for improving the acceptance ratio of queries of the form P(Q|E = e) when compared to traditional Monte-Carlo approaches. For this purpose, the system of interest is first modeled as a Bayesian network. Then, quantum computing is used to translate that Bayesian network into an equivalent quantum circuit using a set of basic quantum gates. Finally, the sampling process is enhanced by applying a quantum protocol called Amplitude Amplification to the resulting quantum circuit. Empirical results are presented using as a case study a non-trivial six-node Bayesian network.

Annual Reliability and Maintainability Symposium (RAMS)Jan 23, 20238 citations

Title: Quantum-Enhanced Bayesian Inference for Bayesian Networks

Jincheng Zhang

Quantum-enhanced Bayesian inference offers the potential to significantly accelerate probabilistic predictions compared to classical Bayesian methods, particularly in complex Bayesian networks. This paper explores the implementation of a novel quantum-enhanced Bayesian inference algorithm, utilizing quantum computation to optimize Bayesian updates and inference. We present a framework for leveraging quantum hardware to enhance the accuracy and efficiency of probabilistic predictions within Bayesian network modeling. The core mechanism focuses on quantum-assisted Bayesian updates, designed to overcome computational bottlenecks inherent in traditional Bayesian inference. The proposed algorithm demonstrates improved accuracy and scalability through a rigorous analysis of its performance on a representative set of Bayesian network scenarios. The investigation delves into the potential advantages and challenges of integrating quantum computing into the Bayesian inference process.

Sep 6, 20260 citations

Implementação e Avaliação de Inferência Bayesiana Clássica e Quântica

Lopes, Gabriel Barros

This thesis explores the intersection of Bayesian inference and quantum computing, with a particular focus on developing and analyzing quantum approaches to probabilistic modeling. The motivation arises from the limitations of classical inference methods, which often become intractable when applied to high-dimensional distributions and complex Bayesian networks. By leveraging quantum algorithms, the work investigates how probabilistic reasoning can benefit from computational speedups, scalability, and more efficient handling of uncertainty.The implementation targets canonical benchmark problems—the Sprinkler Network and the Asia Network—where both classical and quantum Bayesian inference techniques are applied and compared. Using Qiskit, the thesis demonstrates how quantum circuits can encode probabilistic models through parameterized rotations and controlled operations, and how posterior distributions can be computed by sampling and amplitude amplification. Comparative experiments systematically evaluate the accuracy, variance, and scalability of quantum Bayesian inference against classical baselines, highlighting trade-offs between precision and shot counts while exploring the potential for quadratic speedups.The results show that although present-day hardware constraints, such as limited qubit counts and noise, restrict large-scale deployment, quantum implementations already display strong promise for complex probabilistic reasoning tasks. Importantly, the conclusions underscore the role of quantum Bayesian networks as a pathway toward practical quantum-enhanced machine learning.

Sep 23, 20250 citations

Modern Power System Risk Assessment Using Quantum Computing

Seyed Amir Hosseini, Antonello Monti, Saeed Peyghami

The incorporation of renewable energy and the expanding size of power systems have elevated operational uncertainty, thereby raising the risk of load loss. Additionally, the analysis duration has been extended as a consequence. Swift and imperative risk assessments are vital for guaranteeing the safety and reliability of modern power systems operations. In this paper, the utilization of Quantum computing methodologies to enhance the efficiency of the risk assessment in modern power systems is explored. Two prevalent methods, namely Monte Carlo simulation and Bayesian networks, are the focus of this study. The first part introduces a Quantum Monte Carlo circuit designed to analyze risk with greater efficiency compared to the conventional Monte Carlo simulations commonly employed on classical computers. Moreover, the exploration of Quantum computing in Bayesian networks offers a novel approach for modeling and analyzing dependencies within power systems. The potential of Quantum computing to redefine risk assessment methodologies in the domain of power system reliability is illuminated by this research.

International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)Jun 24, 20242 citations

Quantum-Enhanced Bayesian Network Propagation for Risk Assessment

Jincheng Zhang

This paper investigates the potential of quantum computing to enhance Bayesian Network (BN) propagation for risk assessment. Traditional BN models struggle with scalability and computational complexity, particularly when dealing with long-time horizons and complex scenarios. We propose a novel framework that leverages quantum algorithms to accelerate probabilistic model updates, thereby improving accuracy and enabling more sophisticated risk assessment. This work explores the feasibility of quantum-enhanced BN propagation through the application of variational quantum eigensolver (VQE) and quantum annealing techniques. The core claim is that quantum computing offers a significant advantage in risk assessment by improving model accuracy and providing a more robust representation of uncertainty.

Aug 31, 20260 citations