arXiv subjects

Yize Chen

Publications and source records attributed to Yize Chen.

At least 73 records · Page 4Linked to original sources

arXiv2023

Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF

The explicit neural radiance field (NeRF) has gained considerable interest for its efficient training and fast inference capabilities, making it a promising direction such as virtual reality and gaming. In particular, PlenOctree (POT)[1], an explicit hierarchical multi-scale octree representation, has emerged as a structural and influential framework. However, POT's fixed structure for direct optimization is sub-optimal as the scene complexity evolves continuously with updates to cached color and density, necessitating refining the sampling distribution to capture signal complexity accordingly. To address this issue, we propose the dynamic PlenOctree DOT, which adaptively refines the sample distribution to adjust to changing scene complexity. Specifically, DOT proposes a concise yet novel hierarchical feature fusion strategy during the iterative rendering process. Firstly, it identifies the regions of interest through training signals to ensure adaptive and efficient refinement. Next, rather than directly filtering out valueless nodes, DOT introduces the sampling and pruning operations for octrees to aggregate features, enabling rapid parameter learning. Compared with POT, our DOT outperforms it by enhancing visual quality, reducing over $55.15$/$68.84\%$ parameters, and providing 1.7/1.9 times FPS for NeRF-synthetic and Tanks $\&$ Temples, respectively. Project homepage:https://vlislab22.github.io/DOT. [1] Yu, Alex, et al. "Plenoctrees for real-time rendering of neural radiance fields." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.

cs.CV↗

arXiv2023

Laxity-Aware Scalable Reinforcement Learning for HVAC Control

Demand flexibility plays a vital role in maintaining grid balance, reducing peak demand, and saving customers' energy bills. Given their highly shiftable load and significant contribution to a building's energy consumption, Heating, Ventilation, and Air Conditioning (HVAC) systems can provide valuable demand flexibility to the power systems by adjusting their energy consumption in response to electricity price and power system needs. To exploit this flexibility in both operation time and power, it is imperative to accurately model and aggregate the load flexibility of a large population of HVAC systems as well as designing effective control algorithms. In this paper, we tackle the curse of dimensionality issue in modeling and control by utilizing the concept of laxity to quantify the emergency level of each HVAC operation request. We further propose a two-level approach to address energy optimization for a large population of HVAC systems. The lower level involves an aggregator to aggregate HVAC load laxity information and use least-laxity-first (LLF) rule to allocate real-time power for individual HVAC systems based on the controller's total power. Due to the complex and uncertain nature of HVAC systems, we leverage a reinforcement learning (RL)-based controller to schedule the total power based on the aggregated laxity information and electricity price. We evaluate the temperature control and energy cost saving performance of a large-scale group of HVAC systems in both single-zone and multi-zone scenarios, under varying climate and electricity market conditions. The experiment results indicate that proposed approach outperforms the centralized methods in the majority of test scenarios, and performs comparably to model-based method in some scenarios.

eess.SY↗

arXiv2023

Learning a Multi-Agent Controller for Shared Energy Storage System

Deployment of shared energy storage systems (SESS) allows users to use the stored energy to meet their own energy demands while saving energy costs without installing private energy storage equipment. In this paper, we consider a group of building users in the community with SESS, and each user can schedule power injection from the grid as well as SESS according to their demand and real-time electricity price to minimize energy cost and meet energy demand simultaneously. SESS is encouraged to charge when the price is low, thus providing as much energy as possible for users while achieving energy savings. However, due to the complex dynamics of buildings and real-time external signals, it is a challenging task to find high-performance power dispatch decisions in real-time. By designing a multi-agent reinforcement learning framework with state-aware reward functions, SESS and users can realize power scheduling to meet the users' energy demand and SESS's charging/discharging balance without additional communication, so as to achieve energy optimization. Compared with the baseline approach without the participation of the SESS, the energy cost is saved by around 2.37% to 21.58%.

eess.SY↗

arXiv2022

Enabling Fast Unit Commitment Constraint Screening via Learning Cost Model

Unit commitment (UC) are essential tools to transmission system operators for finding the most economical and feasible generation schedules and dispatch signals. Constraint screening has been receiving attention as it holds the promise for reducing a number of inactive or redundant constraints in the UC problem, so that the solution process of large scale UC problem can be accelerated by considering the reduced optimization problem. Standard constraint screening approach relies on optimizing over load and generations to find binding line flow constraints, yet the screening is conservative with a large percentage of constraints still reserved for the UC problem. In this paper, we propose a novel machine learning (ML) model to predict the most economical costs given load inputs. Such ML model bridges the cost perspectives of UC decisions to the optimization-based constraint screening model, and can screen out higher proportion of operational constraints. We verify the proposed method's performance on both sample-aware and sample-agnostic setting, and illustrate the proposed scheme can further reduce the computation time on a variety of setup for UC problems.

math.OC↗

arXiv2022

State-of-Charge Aware EV Charging

Recent proliferation in electric vehicles (EVs) are posing profound impacts over the operation of electrical grids. In particular, due to the physical constraints on charging stations' capacity and uncertainty in charging demand, it becomes an emerging challenge to design high performance scheduling algorithms to better serve charging sessions. In this paper, we design a predictive charging controller by actively incorporating each EV's state-of-charge (SOC) information, which has strong effects on the utilization of dispatchable power during peak hours. Simulation results on both synthetic and real-world EV session and charging demand data demonstrate the proposed algorithm's benefits on maximizing charging throughput and achieving higher rate of feasible charging sessions while satisfying battery and station physical constraints at the same time.

eess.SY↗

arXiv2022

Learning Task-Aware Energy Disaggregation: a Federated Approach

We consider the problem of learning the energy disaggregation signals for residential load data. Such task is referred as non-intrusive load monitoring (NILM), and in order to find individual devices' power consumption profiles based on aggregated meter measurements, a machine learning model is usually trained based on large amount of training data coming from a number of residential homes. Yet collecting such residential load datasets require both huge efforts and customers' approval on sharing metering data, while load data coming from different regions or electricity users may exhibit heterogeneous usage patterns. Both practical concerns make training a single, centralized NILM model challenging. In this paper, we propose a decentralized and task-adaptive learning scheme for NILM tasks, where nested meta learning and federated learning steps are designed for learning task-specific models collectively. Simulation results on benchmark dataset validate proposed algorithm's performance on efficiently inferring appliance-level consumption for a variety of homes and appliances.

cs.LG↗

arXiv2022

BEAR: Physics-Principled Building Environment for Control and Reinforcement Learning

Recent advancements in reinforcement learning algorithms have opened doors for researchers to operate and optimize building energy management systems autonomously. However, the lack of an easily configurable building dynamical model and energy management task simulation and evaluation platform has arguably slowed the progress in developing advanced and dedicated reinforcement learning (RL) and control algorithms for building operation tasks. Here we propose "BEAR", a physics-principled Building Environment for Control And Reinforcement Learning. The platform allows researchers to benchmark both model-based and model-free controllers using a broad collection of standard building models in Python without co-simulation using external building simulators. In this paper, we discuss the design of this platform and compare it with other existing building simulation frameworks. We demonstrate the compatibility and performance of BEAR with different controllers, including both model predictive control (MPC) and several state-of-the-art RL methods with two case studies.

eess.SY↗

arXiv2022

Carbon-Aware EV Charging

This paper examines the problem of optimizing the charging pattern of electric vehicles (EV) by taking real-time electricity grid carbon intensity into consideration. The objective of the proposed charging scheme is to minimize the carbon emissions contributed by EV charging events, while simultaneously satisfying constraints posed by EV user's charging schedules, charging station transformer limits, and battery physical constraints. Using real-world EV charging data and California electricity generation records, this paper shows that our carbon-aware real-time charging scheme saves an average of 3.81% of carbon emission while delivering satisfactory amount of energy. Furthermore, by using an adaptive balanced factor, we can reduce 26.00% of carbon emission on average while compromising 12.61% of total energy delivered.

eess.SY↗

arXiv2022

Adam-based Augmented Random Search for Control Policies for Distributed Energy Resource Cyber Attack Mitigation

Volt-VAR and Volt-Watt control functions are mechanisms that are included in distributed energy resource (DER) power electronic inverters to mitigate excessively high or low voltages in distribution systems. In the event that a subset of DER have had their Volt-VAR and Volt-Watt settings compromised as part of a cyber-attack, we propose a mechanism to control the remaining set of non-compromised DER to ameliorate large oscillations in system voltages and large voltage imbalances in real time. To do so, we construct control policies for individual non-compromised DER, directly searching the policy space using an Adam-based augmented random search (ARS). In this paper we show that, compared to previous efforts aimed at training policies for DER cybersecurity using deep reinforcement learning (DRL), the proposed approach is able to learn optimal (and sometimes linear) policies an order of magnitude faster than conventional DRL techniques (e.g., Proximal Policy Optimization).

eess.SY↗

arXiv2021

SAVER: Safe Learning-Based Controller for Real-Time Voltage Regulation

Fast and safe voltage regulation algorithms can serve as fundamental schemes for achieving a high level of renewable penetration in the modern distribution power grids. Faced with uncertain or even unknown distribution grid models and fast-changing power injections, model-free deep reinforcement learning (DRL) algorithms have been proposed to find the reactive power injections for inverters while optimizing the voltage profiles. However, such data-driven controllers can not guarantee satisfaction of the hard operational constraints, such as maintaining voltage profiles within a certain range of the nominal value. To this end, we propose SAVER: SAfe VoltagE Regulator, which is composed of an RL learner and a specifically designed, computational efficient safety projection layer. SAVER provides a plug-and-play interface for a set of DRL algorithms that guarantees the system voltages to be within safe bounds. Numerical simulations on real-world data validate the performance of the proposed algorithm.

eess.SY↗

arXiv2021

Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training

Due to the proliferation of renewable energy and its intrinsic intermittency and stochasticity, current power systems face severe operational challenges. Data-driven decision-making algorithms from reinforcement learning (RL) offer a solution towards efficiently operating a clean energy system. Although RL algorithms achieve promising performance compared to model-based control models, there has been limited investigation of RL robustness in safety-critical physical systems. In this work, we first show that several competition-winning, state-of-the-art RL agents proposed for power system control are vulnerable to adversarial attacks. Specifically, we use an adversary Markov Decision Process to learn an attack policy, and demonstrate the potency of our attack by successfully attacking multiple winning agents from the Learning To Run a Power Network (L2RPN) challenge, under both white-box and black-box attack settings. We then propose to use adversarial training to increase the robustness of RL agent against attacks and avoid infeasible operational decisions. To the best of our knowledge, our work is the first to highlight the fragility of grid control RL algorithms, and contribute an effective defense scheme towards improving their robustness and security.

eess.SY↗

arXiv2021

Understanding the Safety Requirements for Learning-based Power Systems Operations

Recent advancements in machine learning and reinforcement learning have brought increased attention to their applicability in a range of decision-making tasks in the operations of power systems, such as short-term emergency control, Volt/VAr control, long-term residential demand response and battery energy management. Despite the promises of providing strong representation of complex system dynamics and fast, efficient learned operation strategies, the safety requirements of such learning paradigms are less discussed. This paper explores the design requirements on both data and model side of such learning algorithms by exploiting the impacts of adversarial attacks on safety critical system operations. Case studies performed on both voltage regulation and topology control tasks demonstrated the potential vulnerabilities of the standard reinforcement learning algorithms, and possible measures of machine learning robustness and security are discussed for power systems operation tasks.

eess.SY↗

arXiv2020

IntelligentCrowd: Mobile Crowdsensing via Multi-Agent Reinforcement Learning

The prosperity of smart mobile devices has made mobile crowdsensing (MCS) a promising paradigm for completing complex sensing and computation tasks. In the past, great efforts have been made on the design of incentive mechanisms and task allocation strategies from MCS platform's perspective to motivate mobile users' participation. However, in practice, MCS participants face many uncertainties coming from their sensing environment as well as other participants' strategies, and how do they interact with each other and make sensing decisions is not well understood. In this paper, we take MCS participants' perspective to derive an online sensing policy to maximize their payoffs via MCS participation. Specifically, we model the interactions of mobile users and sensing environments as a multi-agent Markov decision process. Each participant cannot observe others' decisions, but needs to decide her effort level in sensing tasks only based on local information, e.g., its own record of sensed signals' quality. To cope with the stochastic sensing environment, we develop an intelligent crowdsensing algorithm IntelligentCrowd by leveraging the power of multi-agent reinforcement learning (MARL). Our algorithm leads to the optimal sensing policy for each user to maximize the expected payoff against stochastic sensing environments, and can be implemented at individual participant's level in a distributed fashion. Numerical simulations demonstrate that IntelligentCrowd significantly improves users' payoffs in sequential MCS tasks under various sensing dynamics.

cs.MA↗

arXiv2020

A Convex Neural Network Solver for DCOPF with Generalization Guarantees

The DC optimal power flow (DCOPF) problem is a fundamental problem in power systems operations and planning. With high penetration of uncertain renewable resources in power systems, DCOPF needs to be solved repeatedly for a large amount of scenarios, which can be computationally challenging. As an alternative to iterative solvers, neural networks are often trained and used to solve DCOPF. These approaches can offer orders of magnitude reduction in computational time, but they cannot guarantee generalization, and small training error does not imply small testing errors. In this work, we propose a novel algorithm for solving DCOPF that guarantees the generalization performance. First, by utilizing the convexity of DCOPF problem, we train an input convex neural network. Second, we construct the training loss based on KKT optimality conditions. By combining these two techniques, the trained model has provable generalization properties, where small training error implies small testing errors. In experiments, our algorithm improves the optimality ratio of the solutions by a factor of five in comparison to end-to-end models.

eess.SY↗

arXiv2020

Using Mobility for Electrical Load Forecasting During the COVID-19 Pandemic

The novel coronavirus (COVID-19) pandemic has posed unprecedented challenges for the utilities and grid operators around the world. In this work, we focus on the problem of load forecasting. With strict social distancing restrictions, power consumption profiles around the world have shifted both in magnitude and daily patterns. These changes have caused significant difficulties in short-term load forecasting. Typically algorithms use weather, timing information and previous consumption levels as input variables, yet they cannot capture large and sudden changes in socioeconomic behavior during the pandemic. In this paper, we introduce mobility as a measure of economic activities to complement existing building blocks of forecasting algorithms. Mobility data acts as good proxies for the population-level behaviors during the implementation and subsequent easing of social distancing measures. The major challenge with such dataset is that only limited mobility records are associated with the recent pandemic. To overcome this small data problem, we design a transfer learning scheme that enables knowledge transfer between several different geographical regions. This architecture leverages the diversity across these regions and the resulting aggregated model can boost the algorithm performance in each region's day-ahead forecast. Through simulations for regions in the US and Europe, we show our proposed algorithm can outperform conventional forecasting methods by more than three-folds. In addition, we demonstrate how the proposed model can be used to project how electricity consumption would recover based on different mobility scenarios.

eess.SP↗

arXiv2020

Learning to Solve Network Flow Problems via Neural Decoding

Many decision-making problems in engineering applications such as transportation, power system and operations research require repeatedly solving large-scale linear programming problems with a large number of different inputs. For example, in energy systems with high levels of uncertain renewable resources, tens of thousands of scenarios may need to be solved every few minutes. Standard iterative algorithms for linear network flow problems, even though highly efficient, becomes a bottleneck in these applications. In this work, we propose a novel learning approach to accelerate the solving process. By leveraging the rich theory and economic interpretations of LP duality, we interpret the output of the neural network as a noisy codeword, where the codebook is given by the optimization problem's KKT conditions. We propose a feedforward decoding strategy that finds the optimal set of active constraints. This design is error correcting and can offer orders of magnitude speedup compared to current state-of-the-art iterative solvers, while providing much better solutions in terms of feasibility and optimality compared to end-to-end learning approaches.

math.OC↗

arXiv2020

Input Convex Neural Networks for Optimal Voltage Regulation

The increasing penetration of renewables in distribution networks calls for faster and more advanced voltage regulation strategies. A promising approach is to formulate the problem as an optimization problem, where the optimal reactive power injection from inverters are calculated to maintain the voltages while satisfying power network constraints. However, existing optimization algorithms require the exact topology and line parameters of underlying distribution system, which are not known for most cases and are difficult to infer. In this paper, we propose to use specifically designed neural network to tackle the learning and optimization problem together. In the training stage, the proposed input convex neural network learns the mapping between the power injections and the voltages. In the voltage regulation stage, such trained network can find the optimal reactive power injections by design. We also provide a practical distributed algorithm by using the trained neural network. Theoretical bounds on the representation performance and learning efficiency of proposed model are also discussed. Numerical simulations on multiple test systems are conducted to illustrate the operation of the algorithm.

math.OC↗

arXiv2019

Vulnerabilities of Power System Operations to Load Forecasting Data Injection Attacks

We study the security threats of power system operation brought by a class of data injection attacks upon load forecasting algorithms. In particular, with minimal assumptions on the knowledge and ability of the attacker, we design attack data on input features for load forecasting algorithms in a black-box approach. System operators can be oblivious of such wrong load forecasts, which lead to uneconomical or even insecure decisions in commitment and dispatch. This paper is the first attempt to bring up the security issues of load forecasting algorithms to our knowledge, and show that accurate load forecasting algorithm is not necessarily robust to malicious attacks. More severely, attackers are able to design targeted attacks on system operations strategically with additional topology information. We demonstrate the impact of load forecasting attacks on two IEEE test cases. We show our attack strategy is able to cause load shedding with high probability under various settings in the 14-bus test case, and also demonstrate system-wide threats in the 118-bus test case with limited local attacks.

math.OC↗