Search NASA⌕ Search

Engineering topics

Zamzam, Ahmed S.

Publications and source records attributed to Zamzam, Ahmed S..

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Machine Learning-Assisted Distribution System Network Reconfiguration Problem

High penetration from volatile renewable energy resources in the grid and the varying nature of loads raise the need for frequent line switching to ensure the efficient operation of electrical distribution networks. Operators must ensure maximum load delivery, reduced losses, and the operation between voltage limits. However, computations to decide the optimal feeder configuration are often computationally expensive and intractable, making it unfavorable for real-time operations. This is mainly due to the existence of binary variables in the network reconfiguration optimization problem. To tackle this issue, we have devised an approach that leverages machine learning techniques to reshape distribution networks featuring multiple substations. This involves predicting the substation responsible for serving each part of the network. Hence, it leaves simple and more tractable Optimal Power Flow problems to be solved. This method can produce accurate results in a significantly faster time, as demonstrated using the IEEE 37-bus distribution feeder. Compared to the traditional optimization-based approaches, a feasible solution is achieved approximately ten times faster for all the tested scenarios.

deep neural networks↗
DOE OSTI2024

Joint Expansion Planning of Power and Water Distribution Networks

This research considers the joint expansion planning of power and water distribution networks, which are interdependent at various levels. We consider the dependency arising through the power consumption of pumps and develop models for integrating new components into existing networks. Then, we formulate the joint expansion planning as a Mixed Integer Nonlinear Program (MINLP). Applying this MINLP to a small-scale test network, we illustrate the advantages offered by joint expansion planning, such as increased flexibility and reduced costs and redundancy, over independently expanding power and water distribution networks.

expansion planning↗
DOE OSTI2024

Unsupervised Learning for Equitable DER Control: Preprint

In the context of managing distributed energy resources (DERs) within distribution networks (DNs), this work focuses on the task of developing local controllers. We propose an unsupervised learning framework to train functions that can closely approximate optimal power flow (OPF) solutions. The primary aim is to establish specific conditions under which these learned functions can collectively guide the network towards desired configurations asymptotically, leveraging an incremental control approach. The flexibility of the proposed methodology allows to integrate fairness-driven components into the cost function associated with the OPF problem. This addition seeks to mitigate power curtailment disparities among DERs, thereby promoting equitable power injections across the network. To demonstrate the effectiveness of the proposed approach, power flow simulations are conducted using the IEEE 37-bus feeder. The findings not only showcase the guaranteed system stability but also underscore its improved overall performance.

asymptotic stability↗
DOE OSTI2024

Polyhedral Relaxations for Optimal Pump Scheduling of Potable Water Distribution Networks

The classic pump scheduling or optimal water flow (OWF) problem for water distribution networks (WDNs) minimizes the cost of power consumption for a given WDN over a fixed time horizon. In its exact form, the OWF is a computationally challenging mixed-integer nonlinear program (MINLP). It is complicated by nonlinear equality constraints that model network physics, discrete variables that model operational controls, and intertemporal constraints that model changes to storage devices. To address the computational challenges of the OWF, this paper develops tight polyhedral relaxations of the original MINLP, derives novel valid inequalities (or cuts) using duality theory, and implements novel optimization-based bound tightening and cut generation procedures. The efficacy of each new method is rigorously evaluated by measuring empirical improvements in OWF primal and dual bounds over 45 literature instances. The evaluation suggests that our relaxation improvements, model strengthening techniques, and a thoughtfully selected polyhedral relaxation partitioning scheme can substantially improve OWF primal and dual bounds, especially when compared with similar relaxation-based techniques that do not leverage these new methods.

bound tightening↗
DOE OSTI2024

Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning

In multi-timescale multi-agent reinforcement learning (MARL), agents interact across different timescales. In general, policies for time-dependent behaviors, such as those induced by multiple timescales, are non-stationary. Learning non-stationary policies is challenging and typically requires sophisticated or inefficient algorithms. Motivated by the prevalence of this control problem in real-world complex systems, we introduce a simple framework for learning non-stationary policies for multi-timescale MARL. Our approach uses available information about agent timescales to define and learn periodic multi-agent policies. In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy. To learn such policies, we propose a policy gradient algorithm that parameterizes the actor and critic with phase-functioned neural networks, which provide an inductive bias for periodicity. The framework's ability to effectively learn multi-timescale policies is validated on a gridworld and building energy management environment.

control↗
DOE OSTI2023

Hierarchical Data-Driven Protection for Microgrid with 100% Renewable Penetration: Preprint

The accurate detection and isolation of faults is critical for the reliable operation of microgrids (MGs). Traditional protection approaches are even more challenged for 100% renewable MGs because inverter-based resources (IBRs) are the only sources for fault current which are usually low and unpredictable/non-uniform. This calls for new protection scheme that can identify IBR fault responses and detect faults in MGs. Data-driven based protection can learn the pattern of IBR fault responses and make the correct decision to identify faults. Therefore, this paper presents a data-driven approach for fault localization in island MGs. The approach builds a training dataset of comprehensive fault scenarios that can be used to learn fault characteristics from processed measurements. The localization task is modeled as a binary classification problem at each relay, which simplifies the learning process. Then, a hierarchical decision mechanism is used to identify the fault location. The proposed approach is assessed using an exemplary MG with several grid-forming (GFM) and grid-following (GFL) inverters, where accurate estimation of fault location is achieved. The data-driven based protection approach developed in this paper provides a generic framework and useful guidance for power system protection engineers to achieve reliable protection for MGs with 100% renewables.

artificial intelligence↗
DOE OSTI2023

Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning: Preprint

We study multiagent reinforcement learning (MARL) with constraints. This setting is gaining importance as MARL algorithms find new applications in real-world systems ranging from power grids to drone swarms. Most constrained MARL (C-MARL) algorithms use a primal-dual approach to enforce constraints through a penalty function added to the reward. In this paper, we study the structural effects of the primal-dual approach on the constraints and value function. First, we show that using the constraint evaluation as the penalty leads to a weak notion of safety, but by making simple modifications to the penalty function, we can enforce meaningful probabilistic safety constraints. Second, we show that the penalty term changes the value function in a way that is easy to model, and demonstrate the consequences of not doing so. We conclude with simulations in a simple constrained multiagent environment to back up the theoretical results.

data-driven control↗
DOE OSTI2023

Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning

Constrained multiagent reinforcement learning (C-MARL) is gaining importance as MARL algorithms find new applications in real-world systems ranging from energy systems to drone swarms. Most C-MARL algorithms use a primal-dual approach to enforce constraints through a penalty function added to the reward. In this paper, we study the structural effects of this penalty term on the MARL problem. First, we show that the standard practice of using the constraint function as the penalty leads to a weak notion of safety. However, by making simple modifications to the penalty term, we can enforce meaningful probabilistic (chance and conditional value at risk) constraints. Second, we quantify the effect of the penalty term on the value function, uncovering an improved value estimation procedure. We use these insights to propose a constrained multiagent advantage actor critic (C-MAA2C) algorithm. Simulations in a simple constrained multiagent environment affirm that our reinterpretation of the primal-dual method in terms of probabilistic constraints is effective, and that our proposed value estimate accelerates convergence to a safe joint policy.

chance constraints↗
DOE OSTI2023

Physics-Driven Convolutional Autoencoder Approach for CFD Data Compressions: Preprint

With the growing size and complexity of turbulent flow models, data compression approaches are of the utmost importance to analyze, visualize, or restart the simulations. Recently, in-situ autoencoder-based compression approaches have been proposed and shown to be effective at producing reduced representations of turbulent flow data. However, these approaches focus solely on training the model using point-wise sample reconstruction losses that do not take advantage of the physical properties of turbulent flows. In this paper, we show that training autoencoders with additional physics-informed regularizations, e.g., enforcing incompressibility and preserving enstrophy, improves the compression model in three ways: (i) the compressed data better conform to known physics for homogeneous isotropic turbulence without negatively impacting point-wise reconstruction quality, (ii) inspection of the gradients of the trained model uncovers changes to the learned compression mapping that can facilitate the use of explainability techniques, and (iii) as a performance byproduct, training losses are shown to converge up to 12x faster than the baseline model.

auto-encoders↗
DOE OSTI2022

Managing Power Systems-Induced Wildfire Risks Using Optimal Scheduled Shutoffs

The increasing demands for electricity and the increase in extreme weather conditions are putting unprecedented pressure on our electric grids. Often, this pressure leads to electrical component failures, which might ignite wildfires. This work develops a novel model to balance the reliability of power network operations and the risk of wildfire ignition by opti- mizing the operational schedule of power transmission networks considering time-varying risk measures that include exogenous and operational factors. Energy storage systems are considered to deliver power during peak wildfire hours and enable temporal load shifting. The problem is formulated as a mixed-integer linear program that maximizes a weighted sum of the served power demand and the reduction in grid-induced wildfire risk. The results demonstrate the ability of the model to significantly reduce wildfire risk without considerable load shedding.

power systems operations↗
DOE OSTI2022

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems: Preprint

We present the PowerGridworld software package to provide users with a light-weight, modular, and customizable framework for creating power systems-focused, multi-agent gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). While many frameworks exist for training multi-agent (MA) RL policies, none exist to rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning multi-agent RL policies using both OpenAI's MADDPG and RLLib's PPO algorithms where, in both cases, at least some subset of agents incorporate elements of the power flow solution at each time step as part of their reward (negative cost) structures.

MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Secure Control Regions for Distributed Stochastic Systems with Application to Distributed Energy Resource Dispatch

With the increasing connectedness and interdependence of systems that are stochastic in nature, the issue of how to manage and coordinate them for safe operation has evidently become more important. In many networked system architectures, the system-wide output must be delicately managed, often within a prescribed set of bounds. In this paper, a novel control framework is proposed where the bounds on the outputs are translated into independent bounds on the controllable inputs of each subsystem. The main benefit of this framework is that respecting the individual control bounds suffices to guarantee that the system-wide outputs will remain within safe boundaries. Because the systems are assumed to be stochastic, the bounds on the output are introduced as probabilistic chance constraints. The benefits of this framework are demonstrated by applying it to the control of distributed energy resources in a distribution network where the main goal is to keep the voltage magnitudes within their prescribed bounds. The control bounds are evaluated using real data on an IEEE test system.

chance constrained optimization↗
DOE OSTI2022

Managing Power Systems-Induced Wildfire Risks Using Optimal Scheduled Shutoffs: Preprint

The growing demands for electricity and the increase in extreme weather conditions are putting unprecedented pressure on our electrical grids. Oftentimes, this pressure leads to electrical components failures which might ignite wildfires. This work develops a novel model to balance the reliability of power networks operations and risks of wildfires ignition by optimizing the operational schedule of power transmission networks considering time-varying risk measures that consider exogenous and operational factors. Energy storage systems are considered to deliver power during peak wildfire hours and enable temporal load shifting. The problem is formulated as a mixed-integer linear program that maximizes a weighted sum of the served power demand and the reduction in grid-induced wildfires risk. The results demonstrate the ability of the model to reduce wildfires risks significantly without considerable load shedding.

energy scheduling↗
DOE OSTI2022

Secure Control Regions for Distributed Stochastic Systems with Application to Distributed Energy Resource Dispatch: Preprint

With the increasing connectedness and interdependence of systems that are stochastic in nature, the issue of how to manage and coordinate them for safe operation has evidently become more important. In many networked system architectures, the system-wide output has to be delicately managed; often within a prescribed set of bounds. In this paper, a novel control framework is proposed where the bounds on the outputs are translated into independent bounds on the controllable inputs of each subsystem. The main benefit of this framework is that respecting the individual control bounds suffices to guarantee that the system-wide outputs will remain within safe boundaries. Since the systems are assumed to be stochastic, the bounds on the output are introduced as probabilistic chance constraints. The benefits of this framework are demonstrated by applying it to the control of distributed energy resources in a distribution networks where main goal is to keep the voltage magnitudes with their prescribed bounds. The control bounds are evaluated using real data on an IEEE test system.

chance constrained optimization↗
DOE OSTI2022

Multiarea Distribution System State Estimation via Distributed Tensor Completion

Here, this paper proposes a model-free distribution system state estimation method based on tensor completion using canonical polyadic decomposition. In particular, we consider a setting where the network is divided into multiple areas. The measured physical quantities at buses located in the same area are processed by an area controller. A three-way tensor is constructed to collect these measured quantities. The measurements are analyzed locally to recover the full state information of the network. A distributed closed-form iterative algorithm based on the alternating direction method of multipliers is developed to obtain the low-rank factors of the whole network state tensor where information exchange happens only between neighboring areas. The convergence properties of the distributed algorithm and the sufficient conditions on the number of samples for each smaller network that guarantee the identifiability of the factors of the state tensor are presented. To demonstrate the efficacy of the proposed algorithm and to check the identifiability conditions, numerical simulations are carried out using the IEEE 123-bus system and a large-scale real utility feeder.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets: Preprint

Increasing levels of renewable generation motivate a growing interest in data-driven approaches for AC optimal power flow (AC OPF) to manage uncertainty. However, a lack of disciplined dataset creation and benchmarking prohibits useful comparison between approaches in the literature. To instigate confidence, models must be able to reliably predict solutions across a wide range of operating conditions. This paper develops the OPF-Learn package for Julia and Python which uses a computationally efficient approach to create representative datasets that span a wide spectrum of the AC OPF feasible region. Load profiles are uniformly sampled from a convex set that contains the AC OPF feasible set. For each infeasible point found, the convex set is reduced using infeasibility certificates, found by utilizing properties of a relaxed formulation. The framework is shown to generate datasets which are more representative of the entire feasible space versus traditional techniques seen in the literature, improving machine learning model performance.

dataset↗
DOE OSTI2022

Data-Driven Chance-Constrained Design of Voltage Droop Control for Distribution Networks: Preprint

This paper addresses the design of local control methods for voltage control in distribution networks with high level of distributed energy resources (DERs). The designed control methods adapt the active and reactive power output of distributed energy resources proportional to the deviation of the local measured voltage magnitudes from a reference voltage, which is referred to as droop control. Thus, the design focuses on determining the droop characteristics which satisfy network-wide voltage magnitude constraints. The uncertainty and variability of DERs renders the design of optimal droop controls very challenging. Hence, this paper proposes chance constraints to limit the risk from intermittent DERs, by designing droop control coefficients that guarantee the satisfaction of network operational constraints with a specific probability. In addition, the proposed approach relies entirely on historical data rather than assuming knowledge of the probability distributions that characterize the uncertainty of DERs. The efficacy of the proposed method is demonstrated on a 37-bus distribution feeder.

chance-constrained optimization↗