Smart Distribution Network Situation Awareness: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Subjects: Engineering, Electrical & Electronic | Computer Science, Artificial Intelligence
Contributor:
Leijiao Ge

Due to the rapid development of emerging information and communication technologies (ICT) and advanced metering infrastructure (AMI), distribution networks are in an evolvement from passive to active distribution networks (ADN), also called smart distribution networks (SDN). Operation and maintenance (O&M) cost is an economic factor that the SDN management must consider. Among multiple O&M technologies, situation awareness (SA) emerges and is gradually integrated into the SDN. Facing a high proportion of RES, adequate monitoring, analysis, and prediction of the SDN operating status are urgent. Therefore, comprehensive SA, which contains detection, comprehension, and projection, becomes a significant guarantee for the optimal operation of SDN.

  • smart distribution network
  • situation awareness
  • high-quality operation and maintenance
  • critical technology
  • comprehensive framework

1. Introduction

Due to the rapid development of emerging information and communication technologies (ICT) and advanced metering infrastructure (AMI), distribution networks are in an evolvement from passive to active distribution networks (ADN), also called smart distribution networks (SDN) [1]. In addition, with the rapidly increasing penetration of distributed generations (DGs) inspired by the smart grid (SG) concept [2], the SDN integrates multiple renewable energy sources (RES) and focuses on reliable operation [3]. To achieve the environmental objective for gas emission reduction and accommodate the high penetration of DGs, supervisory control and data acquisition (SCADA) systems are employed to monitor the SDN, and distribution management systems (DMS) and energy management systems (EMS) act as decision-support information systems for the coordination of remote SDN equipment. Additionally, the widespread application of devices such as distribution transformer terminal unit (TTU), feeder terminal unit (FTU), remote terminal unit (RTU), and distribution automation terminal (DTU) contributes to the maturity of SDN [4][5].
Operation and maintenance (O&M) cost is an economic factor that the SDN management must consider. Mansor et al. [6] presented operational planning of SDN based on utility planning concepts, considering the cost minimization of O&M, switching, losses, and reliability. Based on the volatilities of wind speed and demand load, ref. [7] presented advanced real-time dispatching strategies to minimize long-run expected cost instead of immediate myopic cost. In addition, the quality of O&M technology directly affects the operating status of SDN. To prevent persistent faults in distribution transformers (DTs), Al Mhdawi et al. [8] proposed a remote condition internet of things (IoT) monitoring and fault prediction system using customized software-defined networking technology. In [9], a multi-status simulation based on event-driven for the SDN O&M was investigated, which can simulate the specific events in the SDN with different time constants within the same simulation framework. To improve the reliability of SDN O&M, Kiaei et al. [10] proposed a hybrid fault location for SDN using available multi-source data, which can precisely calculate the fault location in distribution networks with many sub-laterals. The O&M level of multi-terminal SDN directly connected to each user determines the power quality of end-users. Among multiple O&M technologies, situation awareness (SA) emerges and is gradually integrated into the SDN. Facing a high proportion of RES, adequate monitoring, analysis, and prediction of the SDN operating status are urgent. Therefore, comprehensive SA, which contains detection, comprehension, and projection, becomes a significant guarantee for the optimal operation of SDN [11]. Due to the strong adaptability, SA can dynamically evolve with the future SDN technology development to provide higher quality O&M of SDN.
The concept of SA means to percept elements in the environment within a volume of time and space, comprehend their meaning, and project their future status [12]. In general, the process of SA can be divided into three stages: situation detection, situation comprehension, and situation projection [13]. To visualize the concept of SA, SA can be analogous to human psychology. In psychology, the sensory, perception, and behavioral habits can be expressed as follows:
  1. The sensation is the brain’s reflection of various attributes in objective things that directly act on the human sensory organs [14]. Human cognition of objective things starts with sensation. It is the initial detection of complex things and the basis of complex cognitive activities such as perception and behavior. That is similar to the concept of situation detection.
  2. Based on sensory information, perception processes multiple sensory information in a specific way, interprets the sensory information on individual experience, and taps the deep meaning of sensory information. That is similar to the concept of situation comprehension.
  3. Based on sensory and perception, behavior refers to human activities after receiving internal and external stimuli. The theory of planned behavior [15] can explain human decision-making behaviors from the perspective of perceptual information processing and predict the future behavioral tendency based on the expectation value theory [16]. That is similar to the concept of situation projection.
Therefore, the human collects multiple sensory information and relies on perception to process the sensory information. The following behaviors can be explained and predicted by the theory of planned behavior [17]. The human situation refers to the comprehensive integration of mental activity, physiological state, and environmental information. Similarly, the basic principle of the SA corresponds to the above psychological terms, which represents detecting, comprehending, and projecting various elements with specific spatial–temporal properties [18]. In general, three SA stages can be defined as follows:
  1. Situation detection. The task of the stage is to detect essential features in the environment. Multi-dimensional data can be collected and completed in this stage. In addition, situation detection is the data basis of situation comprehension and projection.
  2. Situation comprehension. The essence of the stage is to understand the environment through data analysis. Specifically, the data obtained in the situation detection are integrated, and the connection and potential information between multi-source data are explored.
  3. Situation projection. The core of situation projection is to achieve the practical application of SA knowledge. Based on the information gained from situation detection and comprehension, this stage can predict the future environmental situation in time.

2. Description of Situation Awareness for Smart Distribution Networks

2.1. Objectives of Situation Awareness for Smart Distribution Networks

  1. The primary goal is to achieve real-time or quasi-real-time SA for SDN, which can accurately obtain the critical information of SDN, quickly determine the operating status of the distribution networks, and predict the development trend of SDN at the same time [11]. Based on the historical records of SDN data, SA provides a comprehensive SDN situation to ensure high-quality O&M.
  2. Observability is a significant technical indicator of SA. High-level SA can provide SDN with a highly visual situation and solve the shortcomings of insufficient measurement devices in the SDN [19].
  3. SA has a significant contribution to SDN reliability. Specifically, conduct the SDN self-healing technology, detect potential SDN risks, and predict security situations in advance. Finally, a scientific basis for the SDN active defense can be provided [13].
  4. Through continuous innovation of intelligent algorithms, SA is cultivating SDN self-adaptive capabilities [20]. Based on the information obtained by SA, SDN can independently recognize and improve the situation in an informed way.

2.2. Challenges of Situation Awareness for Smart Distribution Networks

Due to SDN’s diverse scenarios with more equipment and complex operating status, traditional SA cannot adapt to the modern SDN environment. The O&M challenges for modern SA are as follows:
  1. Situational detection challenges. New measurement technologies such as AMI [21] and phasor measurement units (PMUs) [22] are gradually deployed in SDN. Therefore, the data dimensions collected by SDN scale rapidly, which inevitably increases the computational pressure of SA. Due to the insufficient measurement devices, the collected data are challenging to recognize the poor operating status of the SDN. Therefore, the input data of the SA system are asymmetric, and some missing data are necessary to be accurately completed by calculation. How to comprehensively detect SDN status remains a challenging point in high-quality O&M.
  2. Situational comprehension challenges. Large-scale DGs lead the traditional dispatch mode to unsuitable. As a result, the phenomenon of reverse power transmission at the distribution network terminals is prominent, and the risk of voltage fluctuations and power loss increases [23]. In addition, different SDN topologies, operation modes, energy types, and automation levels have higher requirements for the compatibility of situational comprehension in different regions. Traditional situation comprehension technology is challenging to adapt to the current SDN. As the decision center of SDN, situation comprehension should assist the high-quality O&M of multi-form SDN. How to accurately understand the operating situation of the SDN is the focus of research.
  3. Situation projection challenges. Unlike passive distribution networks, SDN has a higher proportion of DGs and electric vehicles (EVs) and more diverse operating modes [24]. The uncertain outputs of DGs and EVs lead to an imbalance between power supply and consumption. Although the SDN flexibility is improved, the RES outputs, three-phase unbalanced load, EV charging, inspection schedule, and stability margin are challenging to determine in the situation projection. Additionally, situation projection for complex scenarios requires sufficient mathematical analysis, computational capability, and robustness capability. How to effectively predict the operational trend of SDN needs to be solved urgently.

3. Comprehensive Framework of Situation Awareness

A five-layer comprehensive framework of SDN SA is shown in Figure 1, which includes distribution network equipment, communication network, situation detection, situation comprehension, and situation projection. In addition, SCADA systems [25], 5G communications [26], distribution automation systems [27], distribution network equipment [28], SA systems, and communication networks [29] are integrated into Figure 1. First, the distribution network equipment at the bottom layer transmits measurement information, equipment status, and network topology to the communication network at the second layer. Then, the communication network summarizes the SDN data and transmits it to situation detection at the third layer. After situation detection collects the data, it completes the pre-processing, completion, and visualization of multi-source data through various critical technologies. Meanwhile, the processed information is transmitted to the management team and situation comprehension at the fourth layer. Situation comprehension combines various critical technologies to explore the detected data, analyze the operating status of SDN, and provide information support for the high-quality O&M. An intelligent O&M mode can be realized based on the operating status of SDN. In addition, SDN historical data is transmitted to the situation projection at the top layer. Next, the situation projection combines meteorological, economic, social, resource, and other factors to predict the developing situation of SDN. After experiencing the forward cycle, the predicted information is fed back to the situation comprehension at the fourth layer. Next, situation comprehension can summarize and analyze all the information and then transmit a more comprehensive SDN situation to the management team. As a result, the management team and the SA system can coordinate to operate an optimal SDN based on the exact situation. A virtuous circle of SA is constructed for the high-quality O&M of SDN.
Figure 1. A 5-layer comprehensive framework of SDN SA.

4. Critical Technologies of Situation Detection

Situation detection includes data acquisition, processing, completion, and visualization, which is the prerequisite of situation comprehension and projection [11]. To improve the SDN visibility, the comprehensive perception of the SDN is realized in both breadth and depth, whose implementation framework is shown in Figure 2. First, multi-source SDN data are collected by smart meters, terminal equipment, PMU, TTU, FTU, DTU, and other equipment. Then, the data are preliminarily processed through pre-processing technologies such as data storage, data fusion, and data cleaning. Next, the critical technologies of situation detection are used in data completion and data presentation to improve the observability of SDN, including big data analytics, 5G communication, virtual acquisition, and optimal configuration of measurement. Finally, the completed data are sent to the situation comprehension and projection.
Figure 2. The implementation framework of situation detection.
When facing the core O&M goals, enough collected data are significant for situation comprehension to analyze the operating status of SDN. To deal with the uncertainties, it is necessary to have enough data for situation projection to predict the future SDN situation. Otherwise, inaccurate or incomplete SDN data might mislead O&M in a worse direction. Thereby, data construction is the foundation of SDN O&M. With the rapid development of the SDN construction, the power data stored in the SDN enterprise database show explosive growth with the O&M [30]. These data are usually stored in the form of unstructured data, such as images and text, which contain vital information about the operating status of SDN equipment. Through SDN situation detection technology, the O&M data can be collected, mined, and completed, where the data abundance can provide the possibility for high-quality SDN O&M.

5. Critical Technologies of Situation Comprehension

Situation comprehension is the data analysis stage, which explores the potential information of the data collected in the situation detection. Many key operational performance indicators need to be correctly evaluated in SDN, such as reliability [31], flexibility [32], stability [33], and power quality [34], which are integrated into the analysis of the SDN situation. As the foundation of high-quality O&M, the implementation framework of situation comprehension is shown in Figure 3. First, SDN data are collected and completed by situation detection. Then, the data are transferred to the situation comprehension system to explore potential information. By conducting critical technologies of situation comprehension, many key operational performance indicators can be acquired and used as the data basis for O&M technologies. Then, the technologies contribute to high-quality O&M based on the situation comprehension results and return the calculation results to the situation guidance. Ultimately, the intelligent O&M combined with situation comprehension and management can be realized. The critical technologies of situation comprehension include uncertain power flow calculation, hybrid state estimation (HSE), reliability analysis, voltage stability analysis, flexibility evaluation, and power quality evaluation technology.
Figure 3. The implementation framework of situation comprehension.
Energy equipment such as wind power, photovoltaic, DC electrolysis of water into hydrogen, hydrogen storage, AC ice storage, and water storage equipment has been increasingly connected to SDN. The introduction of various energy equipment increases the need for real-time scalable and reliable monitoring, control, and protection of SDN. Situation comprehension establishes the mathematical model compatible with multiple types of SDN terminal equipment, adopts the SDN information provided by situation detection to evaluate the SDN key operational indicators, and then realizes the flexible correction of SDN operating status. Based on the critical technologies of the situation comprehension above, the management team can take more specific measures to improve the quality of O&M. For example, the configuration optimization of DGs based on the results of situation comprehension can be applied to improve the economy of SDN O&M. Meanwhile, many uncertainties and power data in SDN can be determined through situational understanding to reduce the blindness of O&M decision making. In addition, self-learning evaluation technology can achieve dynamic evaluation and the weight balance of multiple indicators to effectively evaluate the key operational indicators of SDN [35]. To coordinate different DGs and energy storages, coordinated dispatch technology can be adopted to build an integrated energy system based on the results of situation comprehension and contribute to high-quality O&M [36]. In addition, the popularization of electric IoT gives SDN more powerful computing capabilities, which promotes the miniaturization and intellectualization of IoT terminals. As IoT has found its way to SDN, demand-side management can be more efficient in the presence of IoT [37]. Edge computing technology [38] enables flexible collaboration between smart terminals and improves the response speed of SDN O&M. In sum, situation comprehension can provide O&M with richer information through various technologies and help the management team make the optimal decision.

6. Critical Technologies of Situation Projection

Situation projection is the stage of state prediction to predict the SDN development, evaluate the operational risks, and provide predicted information for SDN management. With the intelligent O&M, the self-adaptation of SDN relies on accurate situation projection. The implementation framework of the situation projection is shown in Figure 4. First, a large amount of processed data from situation detection and situation comprehension is transferred to the situation projection system. Then, multiple factors such as meteorology, economy, society, resources, and load are comprehensively considered. In addition, state-of-the-art intelligent algorithms such as deep learning [39] and Adaboost [40] are applied to situation projection. Finally, critical technologies of situation projection are conducted to simulate and predict the SDN developing trend in different aspects. Meanwhile, the predicted information is sent back to SDN to provide theoretical support for optimal decision making. The critical technologies of situation projection include three-phase unbalanced load prediction technology, renewable energy output prediction technology considering uncertainty, state-of-energy estimation technology, fault prediction and inspection management technology, and security situation projection technology.
Figure 4. The implementation framework of situation projection.
With the rapid development of new SDN equipment, the O&M of SDN is facing many urgent issues. The integration of high-penetration RES [41] and EVs [42] into the distribution systems increases the uncertainty of SDN operations. In addition, various equipment faults [43] and three-phase unbalance problems [44] can frequently occur in SDN. The security situation is also a vital challenge in establishing secure communication networks for SDN [45]. To this end, situation projection is employed to simulate the behaviors and predict the future development of SDN. The critical technologies of situation projection are related to the security, stability, reliability, and other aspects of the SDN. The goal of situation projection is multifaceted, including reducing the occurrence of three-phase unbalance, assessing the operating risks, evaluating the state-of-energy of EVs, addressing the uncertainty of RES output, assuring information security, providing information support, and guiding SDN management to achieve high-quality O&M [11]. To sum up, situation projection plays a role in SDN in the energy transformation and the upgrade toward future smart cities.

This entry is adapted from the peer-reviewed paper 10.3390/en15030828

References

  1. Evangelopoulos, V.A.; Georgilakis, P.S.; Hatziargyriou, N.D. Optimal operation of smart distribution networks: A review of models, methods and future research. Electr. Power Syst. Res. 2016, 140, 95–106.
  2. Gill, S.; Kockar, I.; Ault, G.W. Dynamic Optimal Power Flow for Active Distribution Networks. IEEE Trans. Power Syst. 2014, 29, 121–131.
  3. Antoniadou-Plytaria, K.E.; Kouveliotis-Lysikatos, N.; Georgilakis, P.S.; Hatziargyriou, N.D. Distributed and Decentralized Voltage Control of Smart Distribution Networks: Models, Methods, and Future Research. IEEE Trans. Smart Grid 2017, 8, 2999–3008.
  4. Shicong, M.A.; Bingyin, X.U.; Houlei, G.A.O.; Yongduan, X.U.E.; Jinghua, W. An Earth Fault Locating Method in Feeder Automation System by Examining Correlation of Transient Zero Mode Currents. Autom. Electr. Power Syst. 2008, 32, 48–52.
  5. Ruj, S.; Nayak, A. A Decentralized Security Framework for Data Aggregation and Access Control in Smart Grids. IEEE Trans. Smart Grid 2013, 4, 196–205.
  6. Mansor, N.N.; Levi, V. Operational Planning of Distribution Networks Based on Utility Planning Concepts. IEEE Trans. Power Syst. 2019, 34, 2114–2127.
  7. Meng, F.Y.; Bai, Y.; Jin, J.L. An advanced real-time dispatching strategy for a distributed energy system based on the reinforcement learning algorithm. Renew. Energy 2021, 178, 13–24.
  8. Al Mhdawi, A.K.; Al-Raweshidy, H.S. A Smart Optimization of Fault Diagnosis in Electrical Grid Using Distributed Software-Defined IoT System. IEEE Syst. J. 2020, 14, 2780–2790.
  9. Lv, C.; Sheng, W.X.; Liu, K.Y.; Dong, X.Z.; Deng, P. Multi-status modelling and event simulation in smart distribution network based on finite state machine. IET Gener. Transm. Distrib. 2019, 13, 2846–2855.
  10. Kiaei, I.; Lotfifard, S. Fault Section Identification in Smart Distribution Systems Using Multi-Source Data Based on Fuzzy Petri Nets. IEEE Trans. Smart Grid 2020, 11, 74–83.
  11. Ge, L.; Li, Y.; Chen, Y.; Cui, Q.; Ma, C. Key Technologies of Situation Awareness and Implementation Effectiveness Evaluation in Smart Distribution Network. Gaodianya Jishu/High Volt. Eng. 2021, 47, 2269–2280.
  12. Yin, J.; Lampert, A.; Cameron, M.; Robinson, B.; Power, R. Using Social Media to Enhance Emergency Situation Awareness. IEEE Intell. Syst. 2012, 27, 52–59.
  13. Wang, S.; Liang, D.; Ge, L. Key Technologies of Situation Awareness and Orientation for Smart Distribution Systems. Autom. Electr. Power Syst. 2016, 40, 2–8.
  14. Dundes, A. On the psychology of legend. In American Folk Legend; University of California Press: Oakland, CA, USA, 2020; pp. 21–36.
  15. Lim, H.-R.; An, S. Intention to purchase wellbeing food among Korean consumers: An application of the Theory of Planned Behavior. Food Qual. Prefer. 2021, 88, 104101.
  16. Ajzen, I. The theory of planned behavior. Organ. Behav. Hum. Decis. Processes 1991, 50, 179–211.
  17. Luiza Neto, I.; Matsunaga, L.H.; Machado, C.C.; Gunther, H.; Hillesheim, D.; Pimentel, C.E.; Vargas, J.C.; D’Orsi, E. Psychological determinants of walking in a Brazilian sample: An application of the Theory of Planned Behavior. Transp. Res. Part F-Traffic Psychol. Behav. 2020, 73, 391–398.
  18. Ge, L.J.; Li, Y.L.; Li, S.X.; Zhu, J.B.; Yan, J. Evaluation of the situational awareness effects for smart distribution networks under the novel design of indicator framework and hybrid weighting method. Front. Energy 2021, 15, 143–158.
  19. Diez, D.; Romero, R.; Tena, S. Designing a Human Supervisory Control System for Smart Grid. IEEE Lat. Am. Trans. 2016, 14, 1899–1905.
  20. Ge, L.; Li, Y.; Yan, J.; Wang, Y.; Zhang, N. Short-term Load Prediction of Integrated Energy System with Wavelet Neural Network Model Based on Improved Particle Swarm Optimization and Chaos Optimization Algorithm. J. Mod. Power Syst. Clean Energy 2021, 9, 1490–1499.
  21. Choi, J.S.; Lee, S.; Chun, S.J. A Queueing Network Analysis of a Hierarchical Communication Architecture for Advanced Metering Infrastructure. IEEE Trans. Smart Grid 2021, 12, 4318–4326.
  22. De Oliveira-De Jesus, P.M.; Rodriguez, N.A.; Celeita, D.F.; Ramos, G.A. PMU-Based System State Estimation for Multigrounded Distribution Systems. IEEE Trans. Power Syst. 2021, 36, 1071–1081.
  23. Zhou, X.; Farivar, M.; Liu, Z.; Chen, L.; Low, S.H. Reverse and Forward Engineering of Local Voltage Control in Distribution Networks. IEEE Trans. Autom. Control 2021, 66, 1116–1128.
  24. Mohammadrezaee, R.; Ghaisari, J.; Yousefi, G.; Kamali, M. Dynamic State Estimation of Smart Distribution Grids Using Compressed Measurements. IEEE Trans. Smart Grid 2021, 12, 4535–4542.
  25. Taylor, Z.; Akhavan-Hejazi, H.; Cortez, E.; Alvarez, L.; Ula, S.; Barth, M.; Mohsenian-Rad, H. Customer-Side SCADA-Assisted Large Battery Operation Optimization for Distribution Feeder Peak Load Shaving. IEEE Trans. Smart Grid 2019, 10, 992–1004.
  26. Ye, J.; Ge, X.; Mao, G.; Zhong, Y. 5G Ultradense Networks With Nonuniform Distributed Users. IEEE Trans. Veh. Technol. 2018, 67, 2660–2670.
  27. Siirto, O.K.; Safdarian, A.; Lehtonen, M.; Fotuhi-Firuzabad, M. Optimal Distribution Network Automation Considering Earth Fault Events. IEEE Trans. Smart Grid 2015, 6, 1010–1018.
  28. Wang, N.; Zhao, F. An Assessment of the Condition of Distribution Network Equipment Based on Large Data Fuzzy Decision-Making. Energies 2020, 13, 197.
  29. Ding, D.; Han, Q.-L.; Ge, X.; Wang, J. Secure State Estimation and Control of Cyber-Physical Systems: A Survey. IEEE Trans. Syst. Man Cybern.-Syst. 2021, 51, 176–190.
  30. Ledva, G.S.; Mathieu, J.L. Separating Feeder Demand Into Components Using Substation, Feeder, and Smart Meter Measurements. IEEE Trans. Smart Grid 2020, 11, 3280–3290.
  31. Yang, X.; Gu, C.; Yan, X.; Li, F. Reliability-Based Probabilistic Network Pricing With Demand Uncertainty. IEEE Trans. Power Syst. 2020, 35, 3342–3352.
  32. Chen, S.; Li, P.; Ji, H.; Yu, H.; Yan, J.; Wu, J.; Wang, C. Operational flexibility of active distribution networks with the potential from data centers. Appl. Energy 2021, 293, 116935.
  33. Huang, W.; Zheng, W.; Hill, D.J. Distribution Network Reconfiguration for Short-Term Voltage Stability Enhancement: An Efficient Deep Learning Approach. IEEE Trans. Smart Grid 2021, 12, 5385–5395.
  34. DE Vasconcelos, F.M.; Santos Rocha, C.H.; Meschini Almeida, C.F.; Pereira, D.d.S.; Leite Rosa, L.H.; Kagan, N. Methodology for Inspection Scheduling in Power Distribution Networks Based on Power Quality Indexes. IEEE Trans. Power Deliv. 2021, 36, 1211–1221.
  35. Ge, L.; Li, Y.; Zhu, X.; Zhou, Y.; Wang, T.; Yan, J. An Evaluation System for HVDC Protection Systems by a Novel Indicator Framework and a Self-Learning Combination Method. IEEE Access 2020, 8, 152053–152070.
  36. Torbaghan, S.S.; Suryanarayana, G.; Hoschle, H.; D’Hulst, R.; Geth, F.; Caerts, C.; Van Hertem, D. Optimal Flexibility Dispatch Problem Using Second-Order Cone Relaxation of AC Power Flows. IEEE Trans. Power Syst. 2020, 35, 98–108.
  37. Mohseni, M.; Joorabian, M.; Ara, A.L. Distribution system reconfiguration in presence of Internet of things. IET Gener. Transm. Distrib. 2021, 15, 1290–1303.
  38. Gong, C.; Lin, F.; Gong, X.; Lu, Y. Intelligent Cooperative Edge Computing in Internet of Things. IEEE Internet Things J. 2020, 7, 9372–9382.
  39. Du, S.; Li, T.; Yang, Y.; Horng, S.-J. Deep Air Quality Forecasting Using Hybrid Deep Learning Framework. IEEE Trans. Knowl. Data Eng. 2021, 33, 2412–2424.
  40. Chen, L.; Li, M.; Su, W.; Wu, M.; Hirota, K.; Pedrycz, W. Adaptive Feature Selection-Based AdaBoost-KNN With Direct Optimization for Dynamic Emotion Recognition in HumanRobot Interaction. IEEE Trans. Emerg. Top. Comput. Intell. 2021, 5, 205–213.
  41. Azizivahed, A.; Arefi, A.; Ghavidel, S.; Shafie-khah, M.; Li, L.; Zhang, J.; Catalao, J.P.S. Energy Management Strategy in Dynamic Distribution Network Reconfiguration Considering Renewable Energy Resources and Storage. IEEE Trans. Sustain. Energy 2020, 11, 662–673.
  42. Viet Thang, T.; Islam, M.R.; Muttaqi, K.M.; Sutanto, D. An Efficient Energy Management Approach for a Solar-Powered EV Battery Charging Facility to Support Distribution Grids. IEEE Trans. Ind. Appl. 2019, 55, 6517–6526.
  43. Liang, J.; Jing, T.; Niu, H.; Wang, J. Two-Terminal Fault Location Method of Distribution Network Based on Adaptive Convolution Neural Network. IEEE Access 2020, 8, 54035–54043.
  44. Kong, W.; Ma, K.; Wu, Q. Three-Phase Power Imbalance Decomposition Into Systematic Imbalance and Random Imbalance. IEEE Trans. Power Syst. 2018, 33, 3001–3012.
  45. Xiao, J.; Zhang, B.; Luo, F. Distribution Network Security Situation Awareness Method Based on Security Distance. IEEE Access 2019, 7, 37855–37864.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
Video Production Service
Feedback