2021 North American Power Symposium (NAPS)最新文献_第6页

Deep Reinforcement Learning-based Volt-Var Optimization in Distribution Grids with Inverter-based Resources 基于逆变器资源配电网的深度强化学习优化

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654630

Rakib Hossain, Mohammad Mansour Lakouraj, A. Ghasemkhani, H. Livani, M. Ben–Idris

{"title":"Deep Reinforcement Learning-based Volt-Var Optimization in Distribution Grids with Inverter-based Resources","authors":"Rakib Hossain, Mohammad Mansour Lakouraj, A. Ghasemkhani, H. Livani, M. Ben–Idris","doi":"10.1109/NAPS52732.2021.9654630","DOIUrl":"https://doi.org/10.1109/NAPS52732.2021.9654630","url":null,"abstract":"High penetration of solar photovoltaic (PV) units in distribution grids and the variability of their output power have caused new challenges to grid operators. Voltage fluctuations and their impact on system losses under high PV penetration scenarios are among these emerging challenges. This paper proposes a deep reinforcement learning based Volt-Var optimization method to minimize voltage fluctuations under high penetration of distributed energy resources, such as PV units, in distribution networks. The Deep deterministic policy gradient (DDPG) approach is developed and used for regulating the voltage in the network while minimizing network losses. The DDPG determines the optimal schedule of reactive power output of PV units and battery energy storage devices through controlling their inverters. The reward function includes both the voltage regulation and power loss minimization objectives. The performance of the proposed approach is validated on a modified version of the IEEE-34 bus system with added PVs and BESs and under various PV penetration scenarios. The results show that both voltage fluctuation and power loss reduces when the agent is fully trained that verify the performance of the proposed model.","PeriodicalId":123077,"journal":{"name":"2021 North American Power Symposium (NAPS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121948120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Microgrid Protection Testing Using a Relay-Hardware-in-the-Loop Testbed 利用继电器-硬件在环试验台进行微电网保护测试

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654656

V.I. Farias, Carissa Cavalieri, Mahmoud Kabalan

引用次数: 0

Cyber-Physical Defense in Smart Distribution Networks 智能配电网中的网络物理防御

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654478

Leen Al Homoud, Rinith Reghunath, Safin Bayes, A. Peerzada, K. Davis, R. Balog

{"title":"Cyber-Physical Defense in Smart Distribution Networks","authors":"Leen Al Homoud, Rinith Reghunath, Safin Bayes, A. Peerzada, K. Davis, R. Balog","doi":"10.1109/NAPS52732.2021.9654478","DOIUrl":"https://doi.org/10.1109/NAPS52732.2021.9654478","url":null,"abstract":"The existing electric grid is transitioning to a smart grid with increased penetration of distributed energy resources (DERs), such as photovoltaic (PV) units, battery storage units, electric vehicles (EV), and EV chargers. DERs facilitate the increase in renewable energy generation, which leads to a more sustainable, efficient, and reliable grid paradigm. However, with the rise of communication exchanges and data flow due to DERs, cybersecurity vulnerabilities arise. Much of the literature has focused strictly on mitigating data attacks resulting in nontechnical losses, false state estimation, and inaccurate load forecasting. However, the grid paradigm's cyber-physical security also needs to be considered to ensure that no grid operations take place that impact the physics of the system. Our project achieved that by developing a Machine Learning (ML) algorithm that will detect anomalies in the commands issued to the distribution network's assets. The algorithm was trained using data from a base case obtained from the simulation of the IEEE 34 distribution network. It was tested and improved by adding modifications to the base case. We successfully developed a local anomaly detection algorithm for a photovoltaic system and two voltage regulators, achieving F1-scores of 0.5141, 0.8173, and 0.8982, respectively. All three algorithms achieved low values of false negatives, which is promising as false negatives have a much higher cost since missing one anomaly can result in disastrous effects on the entire grid.","PeriodicalId":123077,"journal":{"name":"2021 North American Power Symposium (NAPS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124831931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Implementation of Battery EVs and BESS into RAPSim Software to Enrich Power Engineering Education in DER-Integrated Distribution Systems 在RAPSim软件中实现电池电动汽车和BESS，丰富der集成配电系统的电力工程教育

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654476

Travis M. Newbolt, P. Mandal, Hongjie Wang

引用次数: 0

Improvement of Customer Class Load Schedules Utilizing AMI Measurements 利用AMI测量改进客户类负载计划

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654673

Forest Atchison, V. Cecchi, S. Kamalasadan

{"title":"Improvement of Customer Class Load Schedules Utilizing AMI Measurements","authors":"Forest Atchison, V. Cecchi, S. Kamalasadan","doi":"10.1109/NAPS52732.2021.9654673","DOIUrl":"https://doi.org/10.1109/NAPS52732.2021.9654673","url":null,"abstract":"The customer class load schedules traditionally used by electric utility distribution management systems (DMS) inform system-level modeling and analysis, including distribution power flow, which in turn dictates decision making at the most foundational levels. These load schedules vary based on the customer's load category (e.g., residential, commercial, and industrial), season, and type of day (e.g., weekend or weekday). In the absence of detailed customer data, load schedules have conventionally been derived from heuristic techniques, assumptions, and examples, and in some cases have remained static as the modern power grid has evolved to contain more modern load types such as LED lighting fixtures, smart appliances, and household electric vehicle charging stations. Given the advent of more readily-available data due to advanced metering infrastructure (AMI), this work provides data-driven improved customer class load schedules that decrease average error across a particular load category. Additionally, the improved schedules will be shown to decrease error in the aggregate when viewed from the level of a distribution feeder.","PeriodicalId":123077,"journal":{"name":"2021 North American Power Symposium (NAPS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129703654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigating Capacity Credit Sensitivity to Reliability Index 容量信用对可靠性指标的敏感性研究

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654458

Saad Muaddi, Arun Kumar Karngala, Ahmad Abuelrub, C. Singh

引用次数: 1

Residential Customer Clustering Based On Household Electricity Load Disaggregation 基于家庭用电负荷分解的居民用户聚类

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654485

Kewei Xu, Hao Zhu

引用次数: 0

Stochastic Pricing Game for Aggregated Demand Response Considering Comfort Level 考虑舒适度的总需求响应随机定价对策

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654659

Yang Chen, Kadir Amasyali, Byungkwon Park, M. Olama, B. Telsang, S. Djouadi

{"title":"Stochastic Pricing Game for Aggregated Demand Response Considering Comfort Level","authors":"Yang Chen, Kadir Amasyali, Byungkwon Park, M. Olama, B. Telsang, S. Djouadi","doi":"10.1109/NAPS52732.2021.9654659","DOIUrl":"https://doi.org/10.1109/NAPS52732.2021.9654659","url":null,"abstract":"In recent years, demand response (DR) has been explored as a fundamental strategy for demand-side management due to its advantages in mediating intermittency of renewable energy generation, load shifting, etc. To engage customers in DR programs, several deterministic price-based DR strategies have been developed and implemented. However, the stochastic weather conditions and occupants' consumption behaviors often make the deterministic solution less robust to uncertainties. In this paper, with the consideration of the uncertainties, a stochastic Stackelberg game is proposed to model the price-demand negotiation between a distributed system operator and load aggregators, where the virtual battery constraints are extracted from the building thermostatically controlled loads (TCLs)‘ characteristics to guarantee comfortable TCLs' levels. Following the negotiation, a priority-based control method is used to allocate the optimal aggregated power DR profile at the building level and track the power signal. Several groups of experiments have demonstrated the effectiveness and robustness of the stochastic solutions.","PeriodicalId":123077,"journal":{"name":"2021 North American Power Symposium (NAPS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122680823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Facilitating Energy-Efficient Operation of Smart Building using Data-driven Approaches 利用数据驱动的方法促进智能楼宇的节能运作

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654641

G. Revati, M. Palak, Syed Shadab, A. Sheikh

{"title":"Facilitating Energy-Efficient Operation of Smart Building using Data-driven Approaches","authors":"G. Revati, M. Palak, Syed Shadab, A. Sheikh","doi":"10.1109/NAPS52732.2021.9654641","DOIUrl":"https://doi.org/10.1109/NAPS52732.2021.9654641","url":null,"abstract":"The building operations and control have become automated with the help of information and communication technologies (ICT) leading to a new paradigm shift i.e. Smart Buildings, which can improve the comfort and efficiency of the user while consuming less energy than a traditional building. Smart buildings may also interact with the power grid, which is becoming increasingly crucial for utility demand response programs, which necessitates precise prediction of the smart buildings electricity usage. Hence, the paper focuses on the data-driven approaches for predicting electricity usage in a smart building in absence of the system model. The technique such as dynamic mode decomposition (DMD) and deep learning models such as recurrent neural network (RNN), long short term memory (LSTM), and gated recurrent unit (GRU) are considered in this paper. The paper proposes the development of a hybrid model which is a blend of the best features of RNN and GRU for predicting electricity consumption. Another highlight of the paper is the proposition of hyperparameters which ensures to improve the prediction accuracy of the deep learning methods. For testing the effectiveness of all the methods in predicting electricity usage, a comparative study is carried out on two different types of smart buildings. Finally, based on the result it can be claimed that the proposed hybrid model along with the introduction of hyperparameter outperforms other methods of deep learning and DMD as validated by error metrics.","PeriodicalId":123077,"journal":{"name":"2021 North American Power Symposium (NAPS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115684158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Measured Admittance Model for Dynamic Simulation of Inverter-Based Resources Using Numerical Laplace Transform 基于数值拉普拉斯变换的逆变器资源动态仿真测量导纳模型

2021 North American Power Symposium (NAPS) Pub Date : 2021-11-14 DOI: 10.1109/NAPS52732.2021.9654782

Miao Zhang, L. Bao, Zhixin Miao, Lingling Fan, P. Gómez

{"title":"Measured Admittance Model for Dynamic Simulation of Inverter-Based Resources Using Numerical Laplace Transform","authors":"Miao Zhang, L. Bao, Zhixin Miao, Lingling Fan, P. Gómez","doi":"10.1109/NAPS52732.2021.9654782","DOIUrl":"https://doi.org/10.1109/NAPS52732.2021.9654782","url":null,"abstract":"With confidentiality constraints of detailed control information of inverter-based resources (IBR), black-box models, e.g., admittance/impedance models, obtained from measurements are often used for stability analysis. This paper makes a further inquiry: If stability analysis is possible with admittance models, is it possible to produce time-domain simulation results with admittance models only? One method adopted in the literature is to create a linear state-space model for the entire system by interconnecting components. The requirement for such an approach is that each component's model should be proper. To relax this requirement, the current paper seeks an alternate approach: direct conversion of frequency-domain data to time-domain data via numerical Laplace transform (NLT). To begin with, this paper presents NLT's advantage over inverse fast Fourier transfer (IFFT) using tutorial examples. This is followed by an example of a type-4 wind farm weak grid operation stability analysis and fast simulation using admittance models obtained from measurements. It can be seen that frequency-domain measurements, along with data fitting and NLT, lead to not only stability analysis but also fast time-domain simulation for stability demonstration.","PeriodicalId":123077,"journal":{"name":"2021 North American Power Symposium (NAPS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132191994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1