Smart Distribution Grid Research Articles

Machine Learning-Based Node Characterization for Smart Grid Demand Response Flexibility Assessment

As energy distribution systems evolve from a traditional hierarchical load structure towards distributed smart grids, flexibility is increasingly investigated as both a key measure and core challenge of grid balancing. This paper contributes to the theoretical framework for quantifying network flexibility potential by introducing a machine learning based node characterization. In particular, artificial neural networks are considered for classification of historic demand data from several network substations. Performance of the resulting classifiers is evaluated with respect to clustering analysis and parameter space of the models considered, while the bootstrapping based statistical evaluation is reported in terms of mean confusion matrices. The resulting meta-models of individual nodes can be further utilized on a network level to mitigate the difficulties associated with identifying, implementing and actuating many small sources of energy flexibility, compared to the few large ones traditionally acknowledged.

Impact of short-time fourier transform parameters on the accuracy of EMI spectra estimates in the 2-150 kHz supraharmonic interval

Methods based on time-domain sampling and successive tapering and Fourier analysis, used in the “harmonics” frequency interval up to 2.4kHz, cannot be automatically extended to the 2-150 kHz interval, in particular considering the emissions of Switched-Mode Power Supplies (SMPSs) in a modern smart grid or low-voltage distribution scenario. Emissions are substantially impulsive and oscillatory superposed to the mains signal, possibly featuring multiple switching fundamentals and their harmonics with unstable or purposely changing fundamental frequency. Fourier analysis (namely Discrete Fourier Transform) is commonly used to characterize the spectrum of emissions from time-domain data, but the influence of its settings should be verified for accuracy and systematic errors, so to establish the uncertainty of spectral estimates. After an initial theoretical and practical discussion of characteristics, objectives and weak points, a verification is carried out with the help of several measurements performed in different operating conditions on a set of six different SMPSs, evaluating systematic error and uncertainty, and defining a set of recommendations.

Constrained Multiagent Markov Decision Processes: a Taxonomy of Problems and Algorithms

In domains such as electric vehicle charging, smart distribution grids and autonomous warehouses, multiple agents share the same resources. When planning the use of these resources, agents need to deal with the uncertainty in these domains. Although several models and algorithms for such constrained multiagent planning problems under uncertainty have been proposed in the literature, it remains unclear when which algorithm can be applied. In this survey we conceptualize these domains and establish a generic problem class based on Markov decision processes. We identify and compare the conditions under which algorithms from the planning literature for problems in this class can be applied: whether constraints are soft or hard, whether agents are continuously connected, whether the domain is fully observable, whether a constraint is momentarily (instantaneous) or on a budget, and whether the constraint is on a single resource or on multiple. Further we discuss the advantages and disadvantages of these algorithms. We conclude by identifying open problems that are directly related to the conceptualized domains, as well as in adjacent research areas.

Retraction: Stability analysis of distributed smart grid based on machine learning (IOP Conf. Ser.: Earth Environ. Sci. 692 022125)

This article has been retracted by IOP Publishing following a request by the authors concerning the availability of the data in their article. IOP Publishing has investigated in line with COPE guidelines, and during the investigation it was discovered that the article contains verbatim overlap with another work by different authors without citation [1]. As such, IOP Publishing is retracting this work. The authors agree to this retraction. [1] Chao Zhang et al 2021 IOP Conf. Ser.: Earth Environ. Sci. 651 022049 Retraction published: 10 January 2023

Stability analysis of distributed smart grid based on machine learning

Decentralized Smart Grid (DSG) is a new technology proposed to power networks with elastic nodes. It can realize dynamic electricity price demand response without large-scale transformation of the infrastructure.In order to analyze the system stability of DSG, six representative machine learning classification models were applied to analyze the stability data of 10,000 samples of the 4-node system. Combined with the requirements of power system security, stability and economic performance, the effect of each classification model on the stability prediction of DSG system was tested.The test results showed that the model with a Gaussian kernel basis function kernel support Vector machine (RBF SVM) was suitable for data analysis, with the accuracy up to 97.10% and the F metric up to 0.977.CART decision tree model is suitable for real-time forecasting of power system. Under the requirement of ensuring real-time forecasting, its accuracy can reach 84.90% and F metric can reach 0.882. Its modeling and prediction calculation requirements are only 0.98% and 1.59% of that of RBF SVM model respectively.

Multiterminal HVDC System with Power Quality Enhancement

High-Voltage Direct Current (HVDC) systems are a feasible solution that allows the transmission of energy between several power networks. As a consequence of the use of HVDC systems, renewable energy sources can be integrated more easily into distribution grids and smart grids. Furthermore, HVDC systems can contribute to improving the power quality (PQ) of the grids to which they are connected. This paper presents a multiterminal HVDC system that not only controls the flows of active power between four different networks, but also compensates imbalances and harmonics in the grid currents to maintain balanced and sinusoidal voltages at the point of common coupling of the various grids. The compensation is carried out by the voltage-source converters (VSCs) connected to their respective AC grids. A control scheme based on the use of resonant regulators and proportional–integral (PI) controllers is responsible for of achieving the necessary power flow control with the amelioration of the PQ. A case study of a multiterminal HVDC system that comprises four terminals sharing a DC bus of 80 kV is simulated by means of PSCADTM/EMTDCTM (Power System Computer-Aided Design; Electromagnetic Transients including Direct Current), where the AC grids associated with the terminals suffer from voltage imbalances and voltage harmonics owing to the connection of unbalanced loads and nonlinear loads. The obtained simulation results show the performance of the complete system in terms of active power flow, voltage regulation, and harmonic distortions of the grid current and the grid voltage.

Cyber Physical Defense Framework for Distributed Smart Grid Applications

Cyber-Physical Systems (CPS) is the amalgamation of highly sophisticated sensors with physical spaces. These close conjunctions of sensors with communication infrastructure intrinsically linking to society’s Critical Infrastructures (C.I.) are being witnessed more often in the context of Smart Grid (SG). As a backbone of C.I., Smart Grid demonstrates ability to precisely monitor large scale energy systems and designed in order to achieve complex local and global objectives. Being capable of performing such sophisticated operation it also bears the vulnerability of being exposed for cyber-physical co-ordinated attack that may lead to catastrophic effect. Many researchers have analyze the different stages of cyber-physical co-ordinated attacks like attack detection, prevention, impact analysis and recovery plans but there exist a research gap to address all the issues under single framework. Through this paper, we propose a novel Cyber Physical Defense Framework (CPDF) based on National Institute of Standards and Technology (NIST) guidelines to address the cyber attack on SG. Our work addresses the pre and post attack scenario, attack vector formulation through hierarchical PetriNet modeling and recovery mechanism. We have performed experiment for Distributed Denial of Service (DDoS) and False Data Injection attack (FDI) to validate our framework effectiveness and established the efficacy of proposed model. In the end, we have presented a case study of FDI attack detection using machine learning technique on IEEE 9-bus and 14-bus system.

Designing Constraint-Based False Data-Injection Attacks Against the Unbalanced Distribution Smart Grids

The advent of smart power grid, which plays a vital role in the upcoming smart city era, is accompanied with the implementation of a monitoring tool, called state estimation (SE). For the case of the unbalanced residential distribution grid, the state-estimating operation, which is conducted at a regional scale, is considered as an application of the edge computing-based Internet of Things (IoT). While the outcome of the SE is important to the subsequent control activities, its accuracy heavily depends on the data integrity of the information collected from the scattered measurement devices. This fact exposes the vulnerability of the SE module under the effect of data-driven attacks. Among these, the false data-injection (FDI) attack is attracting much attention due to its capability to interfere with the normal operation of the network without being detected. This article presents an attack design scheme based on a nonlinear physical-constraint model that is able to produce an FDI attack with theoretically stealthy characteristic. To demonstrate the effectiveness of the proposed design scheme, simulations with the IEEE 13-node test feeder and the WSCC 9-bus system are conducted. The experimental results indicate that not only the false-positive rate of the bad data detection mechanism is 100% but the physical consequence of the attack is severe. These results pose a serious challenge for the operators in maintaining the integrity of measurement data.

Analysis of Smart Grid Stability and Security Management Based on Data Mining

In the process of the operation and construction of the smart grid, the development of science and technology and the improvement of social productive forces have put forward higher requirements for the development of the power system. In this process, the scale and form of the power system have also changed to a certain extent, and power security has also become the most concerned issue. In the information society, through the application of the Internet of things and big data technology in power security management and control. It can simplify the operation process of the staff and reduce the occurrence of accidents. Distributed smart grid is a new technology proposed for power networks with elastic nodes, which can realize dynamic electricity price demand response without large-scale transformation of infrastructure. In order to analyze the system stability of DSG, six representative machine learning classification models are applied to analyze the stability data of 10000 samples of 4-node system. Combined with the requirements of power system security, stability and economy, the effect of each classification model on the prediction of DSG system stability is tested.

End-User Privacy Protection Scheme from cyber intrusion in smart grid advanced metering infrastructure

Smart monitoring work as a backbone of a smart grid distribution network. To support the existing grid toward a smart grid scenario, smart metering plays a vital role at the customer end side. The massive deployment of smart meters in the distribution side raises a concern about data loss, privacy loss and False Data Intrusion Attack (FDIA). In order to protect the commercial and non-commercial users “End-User Privacy Protection Scheme (EPPS)” is proposed, which allows smart meters to report correct reading during FDIA/intrusion. In this proposed technique statistical machine learning method based on Gaussian Mixture Model Clustering (GMMC) and Mean Square Error (MSE) using two performance indices, the Data Protection Capability (DPC) and the confidential interval for true measurement against false data injection is evaluated. For performance evaluation of the proposed methodology, a passive distributed network is studied. Using EPPS, customer pattern is reconstructed by eliminating cyber intrusion due to FDIA on a smart metering system. This research validates the proposed method through MATLAB software using the smart meter data taken from the National Renewable Energy Laboratory (NREL).

Integrated Multistage Self-Healing in Smart Distribution Grids Using Decentralized Multiagent

Smart self-healing is perceived as a new alternative to ensure reliability and quality of power supply with the development of intelligent communication and control technology. On the basis of multistage characteristics of self-healing control, this article proposes an integrated multistage self-healing strategy for smart distribution systems using multiagent system (MAS), in which the complex self-healing problem is decomposed into phased sub-problems and is addressed by a unified control framework composed of different algorithms of stages. In the proposed control framework, decision-making agents vary with fault points and transition between self-healing stages making the technique fully decentralized. Stressing on the coordination between stage algorithms composed of communication self-adaption, fault tolerance, fault location and isolation, service restoration and state regression, the proposed strategy features well real-time control performance and relatively complete self-healing functions. Comprehensive simulation studies are carried out on the 84-bus and 22-bus distribution systems using MATLAB and JADE and the self-healing test platform respectively, and the test results have shown the effectiveness of the proposed strategy.

Research on Real-time Automatic Acquisition Technology of Topology Data in Distribution Network

The current distribution network equipment renovation plan arrangement is mainly based on the equipment health level, operating years and other indicators. Coordination and optimization between renovation projects are still lacking. Scattered and disorderly transformation will cause potential safety hazards in the distribution network operation. The paper proposes to establish a unified real-time data collection platform for distribution network based on real-time/historical database, and gives the construction idea and implementation plan of the platform. The designed platform has data interfaces with mainstream production control systems, user meters and electrical related systems, and integrates a wealth of common software tools, which can manage and analyze the real-time/quasi-real-time data of the distribution network in a unified manner and can facilitate Coordinated with the implementation of advanced applications of smart distribution networks, it has laid the foundation for the analysis and control of the optimized operation of the entire grid/local area grid and the construction of an integrated model of smart grid operation and distribution. At the same time, the paper proposes a method for checking the topology of low-voltage distribution networks based on outlier detection, calculates the correlation coefficient between the voltage sequence data to measure the similarity of the voltage curves of different users, and finally verifies the users and stations in the grid GIS system The correctness of the zone transformer topology connection relationship.

Quantitative approach of battery management system with optimised integrated distributed energy storage system for smart distribution grid

As electricity shortage has been increasing day by day and conventional power system does not fulfil this exponentially increasing demand because every consumer depend on the main central generatio...

Quantitative approach of battery management system with optimised integrated distributed energy storage system for smart distribution grid

Quantitative approach of battery management system with optimised integrated distributed energy storage system for smart distribution grid

A Spatiotemporal Data Summarization Approach for Real-Time Operation of Smart Grid

In a smart grid distribution management system, operation, planning, forecasting and decision making relies on demand-side management functions, which require real-time smart grid data. This data has significant dollar value because it is extremely useful for efficient control and intelligent prediction of the energy consumption, and expert management of residential and commercial load. However, the huge amount of (smart grid) data generated at a very high velocity poses a number of challenges. Utility companies have a huge demand for efficient summarization techniques to mine interesting patterns and extracting useful and actionable intelligence. Research from various domains has shown that data summarization can significantly improve the scalability and efficiency of various data analytic tasks (e.g., transactional database mining, data streams mining, network monitoring). This paper proposes a summarization approach (i.e., a set of algorithms, data structures, and query mechanisms) that enables the utility company to accurately infer various energy consumption patterns in real-time by automatic monitoring of smart grid data using significantly less computational resources. The proposed summarization approach is suitable for processing spatiotemporal streams, and it can also provide answers in real-time to various smart grid applications (e.g., demand-side management, direct load control, smart pricing and Volt-VAr control). Both theoretical bound and experimental evaluation are presented in this paper, which shows that the memory required for the proposed data structure grows linearly for the first 52 weeks; but interestingly, after the first year, the memory growth is negligible. The experimental results show that the proposed approach can process around 4 million smart meter readings every second or 120 million readings every minute. The proposed approach outperforms widely commercially used Database Management Systems (DBMSs) in terms of update and query costs: it is about 200 times faster than DBMSs in terms of update time, and about 340 times faster than DBMSs in terms of query time.

A Review of Health Assessment Techniques for Distribution Transformers in Smart Distribution Grids

Due to the large number of distribution transformers in the distribution grid, the status of distribution transformers plays an important role in ensuring the safe and reliable operation of the these grids. To evaluate the distribution transformer health, many assessment techniques have been studied and developed. These tools will support the transformer operators in predicting the status of the distribution transformer and responding effectively. This paper will review the literature in the area, analyze the latest techniques as well as highlight the advantages and disadvantages of current methodologies.

A review: Smart Distribution Grid Management using Agents

This paper focuses on the main features of the smart distribution grid (grid management using agents). The fault management is consisting of three stages including faulted section identification, faulted section isolation, and restoration. The probable control strategies utilized in the smart grid are either centralized, decentralized, or autonomous control. Multi-Agent System (MAS) based model uses both centralized and decentralized strategies. The fault management process is usually carried out based on MAS. A literature survey on fault management control schemes is investigated. Furthermore, the reliability is estimated for both centralized, decentralized, autonomous, and modified centralized control strategies. This paper presents reliability modeling and analysis of all considered control strategies. In this paper, comprehensive detailed reliability models of considered control strategies are developed. Using this equivalent reliability model, various reliability indices are calculated.

DC Overload Behavior of Low-Voltage Varistor-Based Surge Protective Devices

This letter provides evidence of a peculiar behavior of metal-oxide varistors under DC overvoltages. It stresses the need for extending the V–I characteristic of varistors in the time domain so as to accurately predict the dynamic performance of varistor-based surge protective devices under temporary overvoltages. Observations and mathematical formulation of DC overload behavior of metal-oxide varistors may have significant implications in energy absorption requirements for low-voltage surge protective devices and unlocks possible monitoring strategies in emerging DC distribution smart grids.

Fault diagnosis, service restoration, and data loss mitigation through multi-agent system in a smart power distribution grid

ABSTRACT Smart power distribution grid is equipped with different sensors and smart meters for getting measurements at different nodes. Additionally, for monitoring and control purpose Intelligent Electronic Devices (IEDs) are also installed. On the occurrence of fault in the grid, power utility implement a Fault Detection, Isolation and Restoration (FDIR) scheme to restore the power in healthy section of the network, this process is known as Service Restoration (SR). In the existing scenario, a centralized control scheme is used for monitoring and control of distribution grid. This control scheme is slow in terms of deployment of FDIR plan. So, the authors propose a multi-agent-based de-centralized control scheme for FDIR. For this multi-agent system, different agents are defined to perform tasks of fault detection, fault isolation, and restoration. Also, the aspect of communication among agents is presented and to tackle data loss problem, a Compressive Sensing (CS) based technique is applied. A novel Support Vector Machine (SVM) approach is proposed for fault classification. For SR, a Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) based method is used and is validated through its application for different fault scenarios in an IEEE 69 bus test system. Also, for testing of data loss mitigation agent, a real-time Phasor Measurement Unit (PMU) data is taken. The whole framework is designed in a python-based Smart Python Agent Development Environment (SPADE) and the related computation is done using MATLAB.

The network of telecommunications cross‐layer cooperation control of wireless sensor communication network applied in smart distribution grid

SummaryWith the rapid development of artificial intelligence, the intelligent distribution network can effectively improve the overall power supply quality of the distribution system. The designed distributed power has been able to achieve an optimal operation of grid connection, while the high‐speed operation of distribution equipment can achieve effective interaction with users. At present, intelligent distribution network is widely studied and applied in power industry because of its advantages of high efficiency energy and environmental protection. Because of its unique characteristics, such as low cost and fast speed, wireless sensor network is cleverly applied in intelligent distribution network. However, wireless sensor network has some defects in energy utilization due to its large range and too many nodes. This paper presents a cross‐layer cooperative control model, which can control the real time and reliability of network power data communication through stack protocol layer. This method can learn the weight value adaptively by training the influence relationship between the parameters of each protocol layer and achieve real‐time and reliable data communication by adjusting the policy and parameters of each layer in real time. This method takes the parameters of each wireless sensor node as the unit to establish the influence relationship between each other so as to realize the connection between each node of wireless sensor network and then to control the wireless sensor network as a whole to ensure the real‐time reliability of data communication in intelligent distribution network. In this paper, a lot of simulation experiments have been done, and the results show that the proposed cross‐layer cooperative control model can control the whole wireless sensor network to achieve efficient data transmission capacity of intelligent distribution wireless sensor network.