arXiv subjects

Ilgiz Murzakhanov

Publications and source records attributed to Ilgiz Murzakhanov.

10 recordsLinked to original sources

arXiv2023

GPU-Accelerated Verification of Machine Learning Models for Power Systems

Computational tools for rigorously verifying the performance of large-scale machine learning (ML) models have progressed significantly in recent years. The most successful solvers employ highly specialized, GPU-accelerated branch and bound routines. Such tools are crucial for the successful deployment of machine learning applications in safety-critical systems, such as power systems. Despite their successes, however, barriers prevent out-of-the-box application of these routines to power system problems. This paper addresses this issue in two key ways. First, for the first time to our knowledge, we enable the simultaneous verification of multiple verification problems (e.g., checking for the violation of all line flow constraints simultaneously and not by solving individual verification problems). For that, we introduce an exact transformation that converts the "worst-case" violation across a set of potential violations to a series of ReLU-based layers that augment the original neural network. This allows verifiers to interpret them directly. Second, power system ML models often must be verified to satisfy power flow constraints. We propose a dualization procedure which encodes linear equality and inequality constraints directly into the verification problem; and in a manner which is mathematically consistent with the specialized verification tools. To demonstrate these innovations, we verify problems associated with data-driven security constrained DC-OPF solvers. We build and test our first set of innovations using the $α,β$-CROWN solver, and we benchmark against Gurobi 10.0. Our contributions achieve a speedup that can exceed 100x and allow higher degrees of verification flexibility.

cs.LG↗

arXiv2023

Optimal Design of Volt/VAR Control Rules for Inverter-Interfaced Distributed Energy Resources

The IEEE 1547 Standard for the interconnection of distributed energy resources (DERs) to distribution grids provisions that smart inverters could be implementing Volt/VAR control rules among other options. Such rules enable DERs to respond autonomously in response to time-varying grid loading conditions. The rules comprise affine droop control augmented with a deadband and saturation regions. Nonetheless, selecting the shape of these rules is not an obvious task, and the default options may not be optimal or dynamically stable. To this end, this work develops a novel methodology for customizing Volt/VAR rules on a per-bus basis for a single-phase feeder. The rules are adjusted by the utility every few hours depending on anticipated demand and solar scenarios. Using a projected gradient descent-based algorithm, rules are designed to improve the feeder's voltage profile, comply with IEEE 1547 constraints, and guarantee stability of the underlying nonlinear grid dynamics. The stability region is inner approximated by a polytope and the rules are judiciously parameterized so their feasible set is convex. Numerical tests using real-world data on the IEEE 141-bus feeder corroborate the scalability of the methodology and its explore the trade-offs of Volt/VAR control with alternatives.

eess.SY↗

arXiv2023

Physics Informed Neural Networks for Phase Locked Loop Transient Stability Assessment

A significant increase in renewable energy production is necessary to achieve the UN's net-zero emission targets for 2050. Using power-electronic controllers, such as Phase Locked Loops (PLLs), to keep grid-tied renewable resources in synchronism with the grid can cause fast transient behavior during grid faults leading to instability. However, assessing all the probable scenarios is impractical, so determining the stability boundary or region of attraction (ROA) is necessary. However, using EMT simulations or Reduced-order models (ROMs) to accurately determine the ROA is computationally expensive. Alternatively, Machine Learning (ML) models have been proposed as an efficient method to predict stability. However, traditional ML algorithms require large amounts of labeled data for training, which is computationally expensive. This paper proposes a Physics-Informed Neural Network (PINN) architecture that accurately predicts the nonlinear transient dynamics of a PLL controller under fault with less labeled training data. The proposed PINN algorithm can be incorporated into conventional simulations, accelerating EMT simulations or ROMs by over 100 times. The PINN algorithm's performance is compared against a ROM and an EMT simulation in PSCAD for the CIGRE benchmark model C4.49, demonstrating its ability to accurately approximate trajectories and ROAs of a PLL controller under varying grid impedance.

eess.SY↗

arXiv2023

A Novel Decentralized Inverter Control Algorithm for Loss Minimization and LVRT Improvement

Algorithms that adjust the reactive power injection of converter-connected RES to minimize losses may compromise the converters' fault-ride-through capability. This can become crucial for the reliable operation of the distribution grids, as they could lose valuable resources to support grid voltage at the time they need them the most. This paper explores how two novel loss-minimizing algorithms can both achieve high reduction of the system losses during normal operation and remain connected to support the voltage during faults. The algorithms we propose are decentralized and model-free: they require no communication and no knowledge of the grid topology or the grid location of the converters. Using local information, they control the reactive power injection to minimize the system losses. In this paper, we extend these algorithms to ensure the low voltage ride through (LVRT) capability of the converters, and we integrate them with state-of-the-art Wavelet-CNN-LSTM RES forecasting methods that enhance their performance. We perform extensive simulations on the real-time digital simulation (RTDS) platform, where we demonstrate that the algorithms we propose can achieve a substantial decrease in power losses while remaining compliant with the grid codes for LVRT makes them suitable for the implementation across the distribution system.

eess.SY↗

arXiv2022

Interpretable Machine Learning for Power Systems: Establishing Confidence in SHapley Additive exPlanations

Interpretable Machine Learning (IML) is expected to remove significant barriers for the application of Machine Learning (ML) algorithms in power systems. This letter first seeks to showcase the benefits of SHapley Additive exPlanations (SHAP) for understanding the outcomes of ML models, which are increasingly being used. Second, we seek to demonstrate that SHAP explanations are able to capture the underlying physics of the power system. To do so, we demonstrate that the Power Transfer Distribution Factors (PTDF) -- a physics-based linear sensitivity index -- can be derived from the SHAP values. To do so, we take the derivatives of SHAP values from a ML model trained to learn line flows from generator power injections, using a simple DC power flow case in the 9-bus 3-generator test network. In demonstrating that SHAP values can be related back to the physics that underpin the power system, we build confidence in the explanations SHAP can offer.

eess.SY↗

arXiv2022

Decentralized Model-free Loss Minimization in Distribution Grids with the Use of Inverters

Distribution grids are experiencing a massive penetration of fluctuating distributed energy resources (DERs). As a result, the real-time efficient and secure operation of distribution grids becomes a paramount problem. While installing smart sensors and enhancing communication infrastructure improves grid observability, it is computationally impossible for the distribution system operator (DSO) to optimize setpoints of millions of DER units. This paper proposes communication-free and model-free algorithms that can actively control converter-connected devices, and can operate either as stand-alone or in combination with centralized optimization algorithms. We address the problem of loss minimization in distribution grids, and we analytically prove that our proposed algorithms reduce the total grid losses without any prior information about the network, requiring no communication, and based only on local measurements. Going a step further, we combine our proposed local algorithms with a central optimization of a very limited number of converters. The hybrid approaches we propose have much lower communication and computation requirement than traditional methods, while they also provide performance guarantees in case of communication failure. We demonstrate our algorithms in four networks of varying sizes: a 5-bus network, an IEEE 141-bus system, a real Danish distribution system, and a meshed IEEE 30-bus system.

eess.SY↗

arXiv2022

Extended Mathematical Derivations: Decentralized Model-free Loss Minimization in Distribution Grids with the Use of Inverters

This document contains extended mathematical derivations for the communication-free and model-free algorithms that can actively control converter-connected devices, and can operate either as stand-alone or in combination with centralized optimization algorithms. We address the problem of loss minimization in distribution grids, and we analytically prove that our proposed algorithms reduce the total grid losses without any prior information about the network, requiring no communication, and based only on local measurements.

eess.SY↗

arXiv2022

Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow

This paper introduces a framework to capture previously intractable optimization constraints and transform them to a mixed-integer linear program, through the use of neural networks. We encode the feasible space of optimization problems characterized by both tractable and intractable constraints, e.g. differential equations, to a neural network. Leveraging an exact mixed-integer reformulation of neural networks, we solve mixed-integer linear programs that accurately approximate solutions to the originally intractable non-linear optimization problem. We apply our methods to the AC optimal power flow problem (AC-OPF), where directly including dynamic security constraints renders the AC-OPF intractable. Our proposed approach has the potential to be significantly more scalable than traditional approaches. We demonstrate our approach for power system operation considering N-1 security and small-signal stability, showing how it can efficiently obtain cost-optimal solutions which at the same time satisfy both static and dynamic security constraints.

eess.SY↗

arXiv2021

Neural network interpretability for forecasting of aggregated renewable generation

With the rapid growth of renewable energy, lots of small photovoltaic (PV) prosumers emerge. Due to the uncertainty of solar power generation, there is a need for aggregated prosumers to predict solar power generation and whether solar power generation will be larger than load. This paper presents two interpretable neural networks to solve the problem: one binary classification neural network and one regression neural network. The neural networks are built using TensorFlow. The global feature importance and local feature contributions are examined by three gradient-based methods: Integrated Gradients, Expected Gradients, and DeepLIFT. Moreover, we detect abnormal cases when predictions might fail by estimating the prediction uncertainty using Bayesian neural networks. Neural networks, which are interpreted by gradient-based methods and complemented with uncertainty estimation, provide robust and explainable forecasting for decision-makers.

cs.LG↗

arXiv2021

Priority Lists for Power System Investments: Locating Phasor Measurement Units

Power systems incrementally and continuously upgrade their components, such as transmission lines, reactive capacitors, or generating units. Decision-making tools often support the selection of the best set of components to upgrade. Optimization models are often used to support decision making at a given point in time. After certain time intervals, re-optimization is performed to find new components to add. In this paper, we propose a decision-making framework for incrementally updating power system components. This is an alternative approach to the classical sequential re-optimization decision making for an investment problem with modeled budget constraints. Our approach provides a priority list as a solution with a list of new components to upgrade. We show that i) our framework is consistent with the evolution of power system upgrades, and ii) in particular circumstances, both frameworks provide the same solution if the problem satisfies submodularity property. We have selected the problem of phasor measurement unit localization and compared the solution with the classical sequential re-optimization framework. For this particular problem, we show that the two approaches provide close results, while only our proposed algorithm is applicable in practice. The cases of 14 and 118 IEEE buses are used to illustrate the proposed methodology.

eess.SY↗