Search

Neuromorphic computing leveraging spiking neural network has emerged as a promising solution to tackle the security and reliability challenges with the conventional cyber-physical infrastructure of microgrids. Its event-driven paradigm facilitates promising prospect in resilient and energy-efficient coordination among power electronic converters. However, different from biological neurons that are focused in the literature, microgrids exhibit distinct architectures and features, implying potentially diverse adaptability in its capabilities to dismiss information transfer, which remains largely unrevealed. One of the biggest drawbacks in the information transfer theory is the impact of noise in the signaling accuracy. Hence, this article hereby explores the noise resiliency of neuromorphic inferential communication in microgrids through case studies and underlines potential challenges and solutions as extensions beyond the results, thus offering insights for its implementation in real-world scenarios., Comment: This manuscript has been accepted for publication in 2024 IEEE Energy Conversion Congress and Exposition (ECCE)

In this paper, we infer remote measurements such as remote voltages and currents online with change in AC power flows using spiking neural network (SNN) as grid-edge technology for efficient coordination of power electronic converters. This work unifies power and information as a means of data normalization using a multi-modal regime in the form of spikes using energy-efficient neuromorphic learning and event-driven asynchronous data collection. Firstly, we organize the synchronous real-valued measurements at each edge and translate them into asynchronous spike-based events to collect sparse data for training of SNN at each edge. Instead of relying on error-dependent supervised data-driven learning theory, we exploit the latency-driven unsupervised Hebbian learning rule to obtain modulation pulses for switching of power electronic converters that can now comprehend grid disturbances locally and adapt their operation without requiring explicit infrastructure for global coordination. Not only does this philosophy block exogenous path arrival for cyber attackers by dismissing the cyber layer, it also entails converter adaptation to system reconfiguration and parameter mismatch issues. We conclude this work by validating its energy-efficient and effective online learning performance under various scenarios in different system sizes, including modified IEEE 14-bus system and under experimental conditions., Comment: The manuscript has been accepted for publication in the Proceedings of 2024 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm 2024)

Although digitalization of future power grids offer several coordination incentives, the reliability and security of information and communication technologies (ICT) hinders its overall performance. In this paper, we introduce a novel architecture Spike Talk via a unified representation of power and information as a means of data normalization using spikes for coordinated control of microgrids. This grid-edge technology allows each distributed energy resource (DER) to execute decentralized secondary control philosophy independently by interacting among each other using power flow along the tie-lines. Inspired from the field of computational neuroscience, Spike Talk basically builds on a fine-grained parallelism on the information transfer theory in our brains, particularly when neurons (modeled as DERs) transmit information (inferred from power streams measurable at each DER) through synapses (modeled as tie-lines). Not only does Spike Talk simplify and address the current bottlenecks of the cyber-physical architectural operation by dismissing the ICT layer, it provides intrinsic operational and cost-effective opportunities in terms of infrastructure development, computations and modeling. Hence, this paper provides a pedagogic illustration of the key concepts and design theories. Since we focus on coordinated control of microgrids in this paper, the signaling accuracy and system performance is studied for several neural coding schemes responsible for converting the real-valued local measurements into spikes.

While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple masked discrete diffusion is more performant than previously thought. We apply an effective training recipe that improves the performance of masked diffusion models and derive a simplified, Rao-Blackwellized objective that results in additional improvements. Our objective has a simple form -- it is a mixture of classical masked language modeling losses -- and can be used to train encoder-only language models that admit efficient samplers, including ones that can generate arbitrary lengths of text semi-autoregressively like a traditional language model. On language modeling benchmarks, a range of masked diffusion models trained with modern engineering practices achieves a new state-of-the-art among diffusion models, and approaches AR perplexity. We release our code at: https://github.com/kuleshov-group/mdlm

Quantum key distribution (QKD) has often been hailed as a reliable technology for secure communication in cyber-physical microgrids. Even though unauthorized key measurements are not possible in QKD, attempts to read them can disturb quantum states leading to mutations in the transmitted value. Further, inaccurate quantum keys can lead to erroneous decryption producing garbage values, destabilizing microgrid operation. QKD can also be vulnerable to node-level manipulations incorporating attack values into measurements before they are encrypted at the communication layer. To address these issues, this paper proposes a secure QKD protocol that can identify errors in keys and/or nodal measurements by observing violations in control dynamics. Additionally, the protocol uses a dynamic adjacency matrix-based formulation strategy enabling the affected nodes to reconstruct a trustworthy signal and replace it with the attacked signal in a multi-hop manner. This enables microgrids to perform nominal operations in the presence of adversaries who try to eavesdrop on the system causing an increase in the quantum bit error rate (QBER). We provide several case studies to showcase the robustness of the proposed strategy against eavesdroppers and node manipulations. The results demonstrate that it can resist unwanted observation and attack vectors that manipulate signals before encryption.

This paper introduces a novel approach in designing prediction horizons on a generalized predictive control for a DC/DC boost converter. This method involves constructing a closed-loop system model and assessing the impact of different prediction horizons on system stability. In contrast to conventional design approaches that often rely on empirical prediction horizon selection or incorporate non-linear observers, the proposed method establishes a rigorous boundary for the prediction horizon to ensure system stability. This approach facilitates the selection of an appropriate prediction horizon while avoiding excessively short horizons that can lead to instability and preventing the adoption of unnecessarily long horizons that would burden the controller with high computational demands. Finally, the accuracy of the design method has been confirmed through experimental testing. Moreover, it has been demonstrated that the prediction horizon determined by this method reduces the computational burden by 10\%-20\% compared to the empirically selected prediction horizon.

The modular multilevel converter (MMC) is a topology that consists of a high number of capacitors, and degradation of capacitors can lead to converter malfunction, limiting the overall system lifetime. Condition monitoring methods can be applied to assess the health status of capacitors and realize predictive maintenance to improve reliability. Current research works for condition monitoring of capacitors in an MMC mainly monitor either capacitance or equivalent series resistance (ESR), while these two health indicators can shift at different speeds and lead to different end-of-life times. Hence, monitoring only one of these parameters may lead to unreliable health status evaluation. This paper proposes a data-driven method to estimate capacitance and ESR at the same time, in which particle swarm optimization (PSO) is leveraged to update the obtained estimations. Then, the results of the estimations are used to predict the sub-module voltage, which is based on a capacitor voltage equation. Furthermore, minimizing the mean square error between the predicted and actual measured voltage makes the estimations closer to the actual values. The effectiveness and feasibility of the proposed method are validated through simulations and experiments., Comment: This paper has been accepted at the conference ECCE Asia 2024 (IPEMC 2024)

Harmonic instability occurs frequently in the power electronic converter system. This paper leverages multi-resolution dynamic mode decomposition (MR-DMD) as a data-driven diagnostic tool for the system stability of power electronic converters, not requiring complex modeling and detailed control information. By combining dynamic mode decomposition (DMD) with the multi-resolution analysis used in wavelet theory, dynamic modes and eigenvalues can be identified at different decomposition levels and time scales with the MR-DMD algorithm, thereby allowing for handling datasets with transient time behaviors, which is not achievable using conventional DMD. Further, the selection criteria for important parameters in MR-DMD are clearly defined through derivation, elucidating the reason for enabling it to extract eigenvalues within different frequency ranges. Finally, the analysis results are verified using the dataset collected from the experimental platform of a low-frequency oscillation scenario in electrified railways featuring a single-phase converter.

This paper proposes a gray-box stability analysis mechanism based on data-driven dynamic mode decomposition (DMD) for commercial grid-tied power electronics converters with limited information on its control parameters and topology. By fusing the underlying physical constraints of the state equations into data snapshots, the system dynamic state matrix and input matrix are simultaneously approximated to identify the dominant system dynamic modes and eigenvalues using the DMD with control (DMDc) algorithm. While retaining the advantages of eliminating the need for intrinsic controller information, the proposed gray-box method establishes higher accuracy and interpretable outcomes over the conventional DMD method. Finally, under experimental conditions of a low-frequency oscillation scenario in electrified railways featuring a single-phase converter, the proposed gray-box DMDc is verified to identify the dominant eigenvalues more accurately.

The health status of power semiconductor devices in power converters is important but difficult to monitor. This paper analyzes the relationship between harmonics in inverter control variables and a health precursor (the on-state voltage Von of power semiconductor devices). Based on the analysis, harmonics can estimate Von without adding extra sensing circuits. The method is validated through simulations.

Synergies between advanced communications, computing and artificial intelligence are unraveling new directions of coordinated operation and resiliency in microgrids. On one hand, coordination among sources is facilitated by distributed, privacy-minded processing at multiple locations, whereas on the other hand, it also creates exogenous data arrival paths for adversaries that can lead to cyber-physical attacks amongst other reliability issues in the communication layer. This long-standing problem necessitates new intrinsic ways of exchanging information between converters through power lines to optimize the system's control performance. Going beyond the existing power and data co-transfer technologies that are limited by efficiency and scalability concerns, this paper proposes neuromorphic learning to implant communicative features using spiking neural networks (SNNs) at each node, which is trained collaboratively in an online manner simply using the power exchanges between the nodes. As opposed to the conventional neuromorphic sensors that operate with spiking signals, we employ an event-driven selective process to collect sparse data for training of SNNs. Finally, its multi-fold effectiveness and reliable performance is validated under simulation conditions with different microgrid topologies and components to establish a new direction in the sense-actuate-compute cycle for power electronic dominated grids and microgrids., Comment: The manuscript has been accepted for publication in IEEE Transactions on Smart Grid

Power electronic systems (PES) face significant threats from various data availability and integrity attacks, significantly affecting the performance of communication networks and power system operation. As a result, several attack detection and reconstruction techniques are deployed, which makes it a costly \& complex cybersecurity operational platform with significant room for incremental extensions for mitigation against future threats. Unlike the said traditional arrangements, our paper introduces a foundational approach by establishing a monolithic cybersecurity architecture (MCA) via incorporating semantic principles into the sampling process for distributed energy resources (DERs). This unified approach concurrently compensates for the intrusion challenges posed by cyber attacks by reconstructing signals using the dynamics of the inner control layer. This reconstruction considers essential semantic attributes, like Priority, Freshness, and Relevance to ensure resilient dynamic performance. Hence, the proposed scheme promises a generalized route to concurrently tackle a global set of cyber attacks in elevating the resilience of PES. Finally, rigorous validation on a modified IEEE 69-bus distribution system and a real-world South California Edison (SCE) 47-bus network, using OPAL-RT under diverse operating conditions, underscores its robustness, model-free design capability, scalability, and adaptability to dynamic cyber graphs and system reconfiguration., Comment: This paper has been accepted for publication in IEEE Transactions on Smart Grid

In power electronic systems (PES), attacks on data availability such as latency attacks, data dropouts, and time-synchronization attacks (TSAs) continue to pose significant threats to both the communication network and the control system performance. As per the conventional norms of communication engineering, PES still rely on time synchronized sampling, which translates every received message with equal importance. In this paper, we go beyond event-triggered sampling/estimation to integrate semantic principles into the sampling process for each distributed energy resource (DER), which not only compensates for delayed communicated signals by reconstruction of a new signal from the inner control layer dynamics, but also evaluates the reconstruction stage using key semantic requirements, namely Freshness, Relevance and Priority for good dynamic performance. As a result, the sparsity provided by event-driven sampling of internal control loop dynamics translates as semantics in PES. The proposed scheme has been extensively tested and validated on a modified IEEE 37-bus AC distribution system, under many operating conditions and noisy environment in OPAL-RT environment to establish its robustness, model-free design ability and adaptive behavior to dynamic cyber graph topologies., Comment: This paper has been accepted for publication in IEEE Transactions on Smart Grid

Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images. Central to these algorithms is the diffusion process, a set of equations which maps data to noise in a way that can significantly affect performance. In this paper, we explore whether the diffusion process can be learned from data. Our work is grounded in Bayesian inference and seeks to improve log-likelihood estimation by casting the learned diffusion process as an approximate variational posterior that yields a tighter lower bound (ELBO) on the likelihood. A widely held assumption is that the ELBO is invariant to the noise process: our work dispels this assumption and proposes multivariate learned adaptive noise (MULAN), a learned diffusion process that applies noise at different rates across an image. Specifically, our method relies on a multivariate noise schedule that is a function of the data to ensure that the ELBO is no longer invariant to the choice of the noise schedule as in previous works. Empirically, MULAN sets a new state-of-the-art in density estimation on CIFAR-10 and ImageNet and reduces the number of training steps by 50%. Code is available at https://github.com/s-sahoo/MuLAN

Drones are becoming versatile in a myriad of applications. This has led to the use of drones for spying and intruding into the restricted or private air spaces. Such foul use of drone technology is dangerous for the safety and security of many critical infrastructures. In addition, due to the varied low-cost design and agility of the drones, it is a challenging task to identify and track them using the conventional radar systems. In this paper, we propose a reinforcement learning based approach for identifying and tracking any intruder drone using a chaser drone. Our proposed solution uses computer vision techniques interleaved with the policy learning framework of reinforcement learning to learn a control policy for chasing the intruder drone. The whole system has been implemented using ROS and Gazebo along with the Ardupilot based flight controller. The results show that the reinforcement learning based policy converges to identify and track the intruder drone. Further, the learnt policy is robust with respect to the change in speed or orientation of the intruder drone.

Cyber-physical microgrids are vulnerable to stealth attacks that can degrade their stability and operability by performing low-magnitude manipulations in a coordinated manner. This paper formulates the interactions between CSAs and microgrid defenders as a non-cooperative, zero-sum game. Additionally, it presents a hybrid Moving Target Defense (MTD) strategy for distributed microgrids that can dynamically alter local control gains to achieve resiliency against Coordinated Stealth Attacks (CSAs). The proposed strategy reduces the success probability of attack(s) by making system dynamics less predictable. The framework also identifies and removes malicious injections by modifying secondary control weights assigned to them. The manipulated signals are reconstructed using an Artificial Neural Network (ANN)-based Digital Twin (DT) to preserve stability. To guarantee additional immunity against instability arising from gain alterations, MTD decisions are also validated (via utility and best response computations) using the DT before actual implementation. The DT is also used to find the minimum perturbation that defenders must achieve to invalidate an attacker's knowledge effectively., Comment: IEEE Energy Conversion Congress and Expo (ECCE) 2023

The development of power electronics-based medium voltage direct current (MVDC) networks has revolutionized the marine industry by enabling all-electric ships (AES). This technology facilitates the integration of heterogeneous resources and improves efficiency. The independent shipboard power system (SPS) is controlled by exchanging measurements and control signals over a communication network. However, the reliance on communication channels raises concerns about the potential exploitation of vulnerabilities leading to cyber-attacks that could disrupt the system. In this paper, a notional 12 kV MVDC SPS model with zonal electrical distribution system (ZEDS) architecture is considered as an exemplary model. As the system stability is closely linked to the transient performance, we investigate how to determine the operational status of the system under potential data integrity attacks on the governor and exciter of the power generation modules (PGMs). Further, the impact of these attacks on the stability of rotor speed and the DC link voltage is derived and discussed. The simulation of the system is carried out in MATLAB/Simulink environment., Comment: 2023 IEEE Electric Ship Technologies Symposium (ESTS 2023)

In this article, we determine a fundamental anatomical modeling parallelism between low-inertia power systems and Bohr's atomic model. The proposed atomic architecture will serve as a microscopic building block, where we validate the structural analogy of low-inertia power systems using semi-classical quantum approximations in IEEE 9-bus & 39-bus systems. As a future scope of work, detailed modeling & system stability will be investigated by using pre-quantization and geometric quantization methods., Comment: Version 2

In this paper, a hyperparameter tuning based Bayesian optimization of digital twins is carried out to diagnose various faults in grid connected inverters. As fault detection and diagnosis require very high precision, we channelize our efforts towards an online optimization of the digital twins, which, in turn, allows a flexible implementation with limited amount of data. As a result, the proposed framework not only becomes a practical solution for model versioning and deployment of digital twins design with limited data, but also allows integration of deep learning tools to improve the hyperparameter tuning capabilities. For classification performance assessment, we consider different fault cases in virtual synchronous generator (VSG) controlled grid-forming converters and demonstrate the efficacy of our approach. Our research outcomes reveal the increased accuracy and fidelity levels achieved by our digital twin design, overcoming the shortcomings of traditional hyperparameter tuning methods.

Timely and accurate detection of anomalies in power electronics is becoming increasingly critical for maintaining complex production systems. Robust and explainable strategies help decrease system downtime and preempt or mitigate infrastructure cyberattacks. This work begins by explaining the types of uncertainty present in current datasets and machine learning algorithm outputs. Three techniques for combating these uncertainties are then introduced and analyzed. We further present two anomaly detection and classification approaches, namely the Matrix Profile algorithm and anomaly transformer, which are applied in the context of a power electronic converter dataset. Specifically, the Matrix Profile algorithm is shown to be well suited as a generalizable approach for detecting real-time anomalies in streaming time-series data. The STUMPY python library implementation of the iterative Matrix Profile is used for the creation of the detector. A series of custom filters is created and added to the detector to tune its sensitivity, recall, and detection accuracy. Our numerical results show that, with simple parameter tuning, the detector provides high accuracy and performance in a variety of fault scenarios.

Blockchain has recently been depicted as a secure protocol for information exchange in cyber-physical microgrids. However, it is still found vulnerable to consensus manipulation attacks. These stealth attacks are often difficult to detect as they use kernel-level access to mask their actions. In this paper, we firstly build a trusted and secured peer-to-peer network mechanism for physical DC microgrids' validation of transactions over Distributed Ledger. Secondly, we leverage from a physics-informed approach for detecting malware-infected nodes and then recovering from stealth attacks using a self-healing recovery scheme augmented into the microgrid Blockchain network. This scheme allows compromised nodes to adapt to a reconstructed trustworthy signal in a multi-hop manner using corresponding measurements from the reliable nodes in the network. Additionally, recognizing the possible threat of denial-of-service attacks and random time delays (where information sharing via communication channels is blocked), we also integrate a model-free predictive controller with the proposed system that can locally reconstruct an expected version of the attacked/delayed signals. This supplements the capabilities of Blockchain, enabling it to detect and mitigate consensus manipulation attempts, and network latencies., Comment: Accepted for publication in IEEE Transactions on Smart Grid

Training normalizing flow generative models can be challenging due to the need to calculate computationally expensive determinants of Jacobians. This paper studies the likelihood-free training of flows and proposes the energy objective, an alternative sample-based loss based on proper scoring rules. The energy objective is determinant-free and supports flexible model architectures that are not easily compatible with maximum likelihood training, including semi-autoregressive energy flows, a novel model family that interpolates between fully autoregressive and non-autoregressive models. Energy flows feature competitive sample quality, posterior inference, and generation speed relative to likelihood-based flows; this performance is decorrelated from the quality of log-likelihood estimates, which are generally very poor. Our findings question the use of maximum likelihood as an objective or a metric, and contribute to a scientific study of its role in generative modeling., Comment: 9 pages, 3 figures, 8 tables, 11 pages appendix

We propose an algorithm to explore the global optimization method, using SAT solvers, for training a neural net. Deep Neural Networks have achieved great feats in tasks like-image recognition, speech recognition, etc. Much of their success can be attributed to the gradient-based optimisation methods, which scale well to huge datasets while still giving solutions, better than any other existing methods. However, there exist learning problems like the parity function and the Fast Fourier Transform, where a neural network using gradient-based optimisation algorithm can not capture the underlying structure of the learning task properly. Thus, exploring global optimisation methods is of utmost interest as the gradient-based methods get stuck in local optima. In the experiments, we demonstrate the effectiveness of our algorithm against the ADAM optimiser in certain tasks like parity learning. However, in the case of image classification on the MNIST Dataset, the performance of our algorithm was less than satisfactory. We further discuss the role of the size of the training dataset and the hyper-parameter settings in keeping things scalable for a SAT solver.

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful replacement is crucial for effective gradient-based learning. Prior works rely on smoothing the solver with input perturbations, relaxing the solver to continuous problems, or interpolating the loss landscape with techniques that typically require additional solver calls, introduce extra hyper-parameters, or compromise performance. We propose a principled approach to exploit the geometry of the discrete solution space to treat the solver as a negative identity on the backward pass and further provide a theoretical justification. Our experiments demonstrate that such a straightforward hyper-parameter-free approach is able to compete with previous more complex methods on numerous experiments such as backpropagation through discrete samplers, deep graph matching, and image retrieval. Furthermore, we substitute the previously proposed problem-specific and label-dependent margin with a generic regularization procedure that prevents cost collapse and increases robustness., Comment: ICLR 2023 conference paper. The first two authors contributed equally

Internet of Things (IoT) and advanced communication technologies have demonstrated great potential to manage residential energy resources by enabling demand-side management (DSM). Home energy management systems (HEMSs) can automatically control electricity production and usage inside homes using DSM techniques. These HEMSs will wirelessly collect information from hardware installed in the power system and in homes with the objective to intelligently and efficiently optimize electricity usage and minimize costs. However, HEMSs can be vulnerable to cyberattacks that target the electricity pricing model. The cyberattacker manipulates the pricing information collected by a customer's HEMS to misguide its algorithms toward non-optimal solutions. The customer's electricity bill increases, and additional peaks are created without being detected by the system operator. This article introduces demand-response (DR)-based DSM in HEMSs and discusses DR optimization using heuristic algorithms. Moreover, it discusses the possibilities and impacts of cyberattacks, their effectiveness, and the degree of resilience of heuristic algorithms against cyberattacks. This article also opens research questions and shows prospective directions.

Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly limited owing to their poor scalability with larger networks. In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model explanation. In particular, we apply this technique to identify minimal regions in an input that are most relevant for a neural network's prediction. Our approach uses gradient information (based on Integrated Gradients) to focus on a subset of neurons in the first layer, which allows our technique to scale to large networks. The corresponding SMT constraints encode the minimal input mask discovery problem such that after masking the input, the activations of the selected neurons are still above a threshold. After solving for the minimal masks, our approach scores the mask regions to generate a relative ordering of the features within the mask. This produces a saliency map which explains "where a model is looking" when making a prediction. We evaluate our technique on three datasets - MNIST, ImageNet, and Beer Reviews, and demonstrate both quantitatively and qualitatively that the regions generated by our approach are sparser and achieve higher saliency scores compared to the gradient-based methods alone. Code and examples are at - https://github.com/google-research/google-research/tree/master/smug_saliency

We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task., Comment: 9 pages, 9 figures, ICML 2018