RoGRUT: A Hybrid Deep Learning Model for Detecting Power Trapping in Smart Grids

Electricity theft is a widespread non-technical issue that has a negative impact on both power grids and electricity users.It hinders the economic growth of utility companies,poses electrical risks,and impacts the high energy costs borne by consumers.The development of smart grids is crucial for the identification of power theft since these systems create enormous amounts of data,including information on client consumption,which may be used to identify electricity theft using machine learning and deep learning techniques.Moreover,there also exist different solutions such as hardware-based solutions to detect electricity theft that may require human resources and expensive hardware.Computer-based solutions are presented in the literature to identify electricity theft but due to the dimensionality curse,class imbalance issue and improper hyper-parameter tuning of such models lead to poor performance.In this research,a hybrid deep learning model abbreviated as RoGRUT is proposed to detect electricity theft as amalicious and non-malicious activity.The key steps of the RoGRUT are data preprocessing that covers the problem of class imbalance,feature extraction and final theft detection.Different advanced-level models like RoBERTa is used to address the curse of dimensionality issue,the near miss for class imbalance,and transfer learning for classification.The effectiveness of the RoGRUTis evaluated using the dataset fromactual smartmeters.A significant number of simulations demonstrate that,when compared to its competitors,the RoGRUT achieves the best classification results.The performance evaluation of the proposed model revealed exemplary results across variousmetrics.The accuracy achieved was 88%,with precision at an impressive 86%and recall reaching 84%.The F1-Score,a measure of overall performance,stood at 85%.Furthermore,themodel exhibited a noteworthyMatthew correlation coefficient of 78%and excelled with an area under the curve of 91%.

“GRIDS”教学法在工程热力学教学中的创新与实践

针对工程热力学课程传统教学课堂沉闷、教学效率低、专业拓展少、课时吃紧、思政入耳不入心和学生创新能力培养不足等问题,依托省级线上线下混合式一流课程,开展基于“GRIDS”教学法的教学创新与实践。混合式教学模式让线下教学融入更多高阶知识点、针对性案例,让课程内容更具弹性;“GRIDS”每一个字母代表一种教学方法;分组案例汇报拓展学科前沿,培养学生团队合作能力;雨课堂随堂测验;4种思政范式让思政“铭于心而践于行”;讨论式互动培养学生批判性学习思维;学习卡片帮助学生把握重难点。各教学方法的形成性评价是过程化考核依据。教学方法形成合力,将教学痛点逐个击破,形成闭环,并持续改进。

Blast disruption using 3D grids/perforated plates for vehicle protection

In this work, blast disruption and mitigation using 3D grids/perforated plates were tested for underbelly and side protection of vehicles. Two vehicle simulants were used: a small-scale one for side vehicle protection assessment and a true-to-scale simulant for underbelly protection testing. The deformation of target plates was assessed. These were either unprotected or protected by three different types of disruptors. The first disruptor was made of a sandwich structure of two perforated plates filled with a thin aluminum structure allowing the air to pass through. The two other disruptors were made of pieces of cast metallic foam. Two different kinds of foams were used: one with large cells and the second one with small cells. Beforehand, the mitigation efficiency of the disruptors was evaluated using an explosivedriven shock tube(EDST). The experiments showed that blast disruption/mitigation by 3D grid/perforated plate structures was not suitable for vehicle side protection. However, 3D grids/perforated structures proved to be relatively effective for underbelly protection compared to an equivalent mass of steel.

An Ethereum-based solution for energy trading in smart grids

The need for a flexible,dynamic,and decentralized energy market has rapidly grown in recent years.As a matter of fact,Industry 4.0 and Smart Grids are pursuing a path of automation of operations to insure all the steps among consumers and producers are getting closer.This leads towards solutions that exploit the paradigm of public blockchain,which represents the best platform to design flat and liquid markets for which providing trust and accountability to mutual interactions becomes crucial.On the other hand,one of the risks arising in this situation is that personal information is exposed to the network,with intolerable threats to privacy.In this paper,we propose a solution for energy trading,based on the blockchain Ethereum and Smart Contracts.The solution aims to be a concrete proposal to satisfy the needs of energy trading in smart grids,including the important feature that no information about the identity of the peers of the network is disclosed in advance.

A finite volume method for global electromagnetic induction forward modeling on collocated unstructured grids

Global electromagnetic induction provides an efficient way to probe the electrical conductivity in the Earth’s deep interior.Owing to the increasing geomagnetic data especially from high-accuracy geomagnetic satellites,inverting the Earth’s three-dimensional conductivity distribution on a global scale becomes attainable.A key requirement in the global conductivity inversion is to have a forward solver with high-accuracy and efficiency.In this study,a finite volume method for global electromagnetic induction forward modeling is developed based on unstructured grids.Arbitrary polyhedral grids are supported in our algorithms to obtain high geometric adaptability.We employ a cell-centered collocated variable arrangement which allows convenient discretization for complex geometries and straightforward implementation of multigrid technique.To validate the method,we test our code with two synthetic models and compare our finite volume results with an analytical solution and a finite element numerical solution.Good agreements are observed between our solution and other results,indicating acceptable accuracy of the proposed method.

A Distributed Power Trading Scheme Based on Blockchain and Artificial Intelligence in Smart Grids

As an emerging hot technology,smart grids(SGs)are being employed in many fields,such as smart homes and smart cities.Moreover,the application of artificial intelligence(AI)in SGs has promoted the development of the power industry.However,as users’demands for electricity increase,traditional centralized power trading is unable to well meet the user demands and an increasing number of small distributed generators are being employed in trading activities.This not only leads to numerous security risks for the trading data but also has a negative impact on the cost of power generation,electrical security,and other aspects.Accordingly,this study proposes a distributed power trading scheme based on blockchain and AI.To protect the legitimate rights and interests of consumers and producers,credibility is used as an indicator to restrict untrustworthy behavior.Simultaneously,the reliability and communication capabilities of nodes are considered in block verification to improve the transaction confirmation efficiency,and a weighted communication tree construction algorithm is designed to achieve superior data forwarding.Finally,AI sensors are set up in power equipment to detect electricity generation and transmission,which alert users when security hazards occur,such as thunderstorms or typhoons.The experimental results show that the proposed scheme can not only improve the trading security but also reduce system communication delays.

An evaluation model for smart grids in support of smart cities based on the Hierarchy of Needs Theory

Smart cities depend highly on an intelligent electrical networks to provide a reliable,safe,and clean power supplies.A smart grid achieves such aforementioned power supply by ensuring resilient energy delivery,which presents opportunities to improve the cost-effectiveness of power supply and minimize environmental impacts.A systematic evaluation of the comprehensive benefits brought by smart grid to smart cities can provide necessary theoretical fundamentals for urban planning and construction towards a sustainable energy future.However,most of the present methods of assessing smart cities do not fully take into account the benefits expected from the smart grid.To comprehensively evaluate the development levels of smart cities while revealing the supporting roles of smart grids,this article proposes a model of smart city development needs from the perspective of residents’needs based on Maslow’s Hierarchy of Needs theory,which serves the primary purpose of building a smart city.By classifying and reintegrating the needs,an evaluation index system of smart grids supporting smart cities was further constructed.A case analysis concluded that smart grids,as an essential foundation and objective requirement for smart cities,are important in promoting scientific urban management,intelligent infrastructure,refined public services,efficient energy utilization,and industrial development and modernization.Further optimization suggestions were given to the city analyzed in the case include strengthening urban management and infrastructure constructions,such as electric vehicle charging facilities and wireless coverage.

Anomaly Detection and Classification in Streaming PMU Data in Smart Grids

The invention of Phasor Measurement Units(PMUs)produce synchronized phasor measurements with high resolution real time monitoring and control of power system in smart grids that make possible.PMUs are used in transmitting data to Phasor Data Concentrators(PDC)placed in control centers for monitoring purpose.A primary concern of system operators in control centers is maintaining safe and efficient operation of the power grid.This can be achieved by continuous monitoring of the PMU data that contains both normal and abnormal data.The normal data indicates the normal behavior of the grid whereas the abnormal data indicates fault or abnormal conditions in power grid.As a result,detecting anomalies/abnormal conditions in the fast flowing PMU data that reflects the status of the power system is critical.A novel methodology for detecting and categorizing abnormalities in streaming PMU data is presented in this paper.The proposed method consists of three modules namely,offline Gaussian Mixture Model(GMM),online GMM for identifying anomalies and clustering ensemble model for classifying the anomalies.The significant features of the proposed method are detecting anomalies while taking into account of multivariate nature of the PMU dataset,adapting to concept drift in the flowing PMU data without retraining the existing model unnecessarily and classifying the anomalies.The proposed model is implemented in Python and the testing results prove that the proposed model is well suited for detection and classification of anomalies on the fly.

Adaptive Reclosing Scheme Based on Traveling Wave Injection For Multi-Terminal dc Grids

The hybrid dc circuit breaker(HCB)has the advantages of fast action speed and low operating loss,which is an idealmethod for fault isolation ofmulti-terminal dc grids.Formulti-terminal dc grids that transmit power through overhead lines,HCBs are required to have reclosing capability due to the high fault probability and the fact that most of the faults are temporary faults.To avoid the secondary fault strike and equipment damage that may be caused by the reclosing of the HCB when the permanent fault occurs,an adaptive reclosing scheme based on traveling wave injection is proposed in this paper.The scheme injects traveling wave signal into the fault dc line through the additionally configured auxiliary discharge branch in the HCB,and then uses the reflection characteristic of the traveling wave signal on the dc line to identify temporary and permanent faults,to be able to realize fast reclosing when the temporary fault occurs and reliably avoid reclosing after the permanent fault occurs.The test results in the simulation model of the four-terminal dc grid show that the proposed adaptive reclosing scheme can quickly and reliably identify temporary and permanent faults,greatly shorten the power outage time of temporary faults.In addition,it has the advantages of easiness to implement,high reliability,robustness to high-resistance fault and no dead zone,etc.

A Program Study of the Union of Semilattices on the Set of Subsets of Grids of Waterloo Language

The aim is to study the set of subsets of grids of the Waterloo language from the point of view of abstract algebra and graph theory. The study was conducted using the library for working with transition graphs of nondeterministic finite automata NFALib implemented by one of the authors in C#, as well as statistical methods for analyzing algorithms. The results are regularities obtained when considering semilattices on a set of subsets of grids of the Waterloo language. It follows from the results obtained that the minimum covering automaton equivalent to the Waterloo automaton can be obtained by adding one additional to the minimum covering set of grids. .

Active injection protection scheme for flexible HVDC grids based on amplitude of input impedance

High-voltage direct current(HVDC)grids require fast and reliable protection of the DC lines.The performance of traditional protection schemes is easily impaired by the limitations of the boundary condition and nonlinearity from the control of converters.One of the key technologies for flexible HVDC grids is the half-bridge modular multilevel converter(HB-MMC).Considering the high controllability of HB-MMC,this study proposes an active injection protection scheme to improve the reliability and sensitivity of the HVDC grid protection.The HB-MMC is used to inject a sinusoidal characteristic signal,at the specified frequency,into the DC lines.Then,the voltage and current at the specified frequency are extracted using the Prony algorithm to calculate the input impedance,which is used for the identification of internal and external faults.The active injection protection scheme was simulated for various cases in the simulation software Power Systems Computer Aided Design.The simulation results indicate that the proposed protection scheme is highly reliable and can overcome transition resistance.

A simple algorithm to improve the performance of the WENO scheme on non-uniform grids

This paper presents a simple approach for improving the performance of the weighted essentially nonoscillatory(WENO) finite volume scheme on non-uniform grids. This technique relies on the reformulation of the fifthorder WENO-JS(WENO scheme presented by Jiang and Shu in J. Comput. Phys. 126:202–228, 1995) scheme designed on uniform grids in terms of one cell-averaged value and its left and/or right interfacial values of the dependent variable.The effect of grid non-uniformity is taken into consideration by a proper interpolation of the interfacial values. On nonuniform grids, the proposed scheme is much more accurate than the original WENO-JS scheme, which was designed for uniform grids. When the grid is uniform, the resulting scheme reduces to the original WENO-JS scheme. In the meantime,the proposed scheme is computationally much more efficient than the fifth-order WENO scheme designed specifically for the non-uniform grids. A number of numerical test cases are simulated to verify the performance of the present scheme.

A fast and reliable overset unstructured grids approach

A cell-centred overset unstructured grids approach is developed.In this approach,the intergrid boundary is initially established based on the wall distance from the cell centre,and is then optimized.To accelerate the intergrid-boundary definition much more,a neighbor-toneighbor donor search algorithm based on advancing-front method is modified with the help of minimum cuboid boxes.To simplify the communications between different grid cell types and to obtain second-order spatial accuracy,a new interpolation method is constructed based on linear reconstruction,which employs only one layer of fringe cells along the intergrid boundary.For unsteady flows with relative motion,the intergrid boundary can be redefined fast and automatically.Several numerical results show that the present dynamic overset unstructured grids approach is accurate and reliable.

An Improved Algorithm of Grounding Grids Corrosion Diagnosis Based on Total Least Square Method

A new model considering corrosion property for grounding grids diagnosis is proposed,which provides reference solutions of ambiguous branches.The constraint total least square method based on singular value decomposition is adopted to improve the effectiveness of grounding grids' diagnosis algorithm.The improvement can weaken the influence of the model's error,which results from the differences between design paper and actual grid.Its influence on touch and step voltages caused by the interior resistance of conductors is taken into account.Simulation results show the validity of this approach.

TCP/IP Based Intelligent Load Management System in Micro-Grids Network Using MATLAB/Simulink

Computerized power management system with fast and optimal communication network overcomes all major dicrepencies of undue or inadequate load relief that were present in old conventional systems. This paper presents the basic perception and methodology of modern and true intelligent load management scheme in micro grids topology by employing TCP/IP protocol for fast and intelligent switching. The network understudy performs load management and power distribution intelligently in a unified network. Generated power is efficiently distributed among local loads through fast communication system of server in the form of source and clients in the form of loads through TCP/IP. The efficient use of information between server and clients enables to astutely control the load management in a power system of micro grids system. The processing time of above stated system comes out to be 10ms faster than others which ensure very less delay as compared to conventional methods. The Micro Grids system operating through TCP/IP control has been implemented in MATLAB/Simulink and results have been verified.

Energy Theft Identification Using Adaboost Ensembler in the Smart Grids

One of the major concerns for the utilities in the Smart Grid(SG)is electricity theft.With the implementation of smart meters,the frequency of energy usage and data collection from smart homes has increased,which makes it possible for advanced data analysis that was not previously possible.For this purpose,we have taken historical data of energy thieves and normal users.To avoid imbalance observation,biased estimates,we applied the interpolation method.Furthermore,the data unbalancing issue is resolved in this paper by Nearmiss undersampling technique and makes the data suitable for further processing.By proposing an improved version of Zeiler and Fergus Net(ZFNet)as a feature extraction approach,we had able to reduce the model’s time complexity.To minimize the overfitting issues,increase the training accuracy and reduce the training loss,we have proposed an enhanced method by merging Adaptive Boosting(AdaBoost)classifier with Coronavirus Herd Immunity Optimizer(CHIO)and Forensic based Investigation Optimizer(FBIO).In terms of low computational complexity,minimized over-fitting problems on a large quantity of data,reduced training time and training loss and increased training accuracy,our model outperforms the benchmark scheme.Our proposed algorithms Ada-CHIO andAda-FBIO,have the low MeanAverage Percentage Error(MAPE)value of error,i.e.,6.8%and 9.5%,respectively.Furthermore,due to the stability of our model our proposed algorithms Ada-CHIO and Ada-FBIO have achieved the accuracy of 93%and 90%.Statistical analysis shows that the hypothesis we proved using statistics is authentic for the proposed technique against benchmark algorithms,which also depicts the superiority of our proposed techniques.

Structured Microgrids (SμGs) and Flexible Electronic Large Power Transformers (FeLPTs)

Structured microgrids(SμGs)and Flexible electronic large power transformers(FeLPTs)are emerging as two essential technologies for renewable energy integration,flexible power transmission,and active control.SμGs provide the integration of renewable energy and storage to balance the energy demand and supply as needed for a given system design.FeLPT’s flexibility for processing,control,and re-configurability offers the capability for flexible transmission for effective flow control and enable SμGs connectivity while still keeping multiscale system level control.Early adaptors for combined heat and power have demonstrated significant economic benefits while reducing environmental foot prints.They bring tremendous benefits to utility companies also.With storage and active control capabilities,a 300-percent increase in bulk transmission and distribution lines are possible without having to increase capacity.SμGs and FeLPTs will also enable the utility industry to be better prepared for the emerging large increase in base load demand from electric transportation and data centers.This is a win-win-win situation for the consumer,the utilities(grid operators),and the environment.SμGs and FeLPTs provide value in power substation,energy surety,reliability,resiliency,and security.It is also shown that the initial cost associated with SμG and FeLPTs deployment can be easily offset with reduced operating cost,which in turn reduces the total life-cycle cost by 33%to 67%.

A Perspective on the Future of Distribution: Smart Grids, State of the Art, Benefits and Research Plans

Currently, the design and operation criteria for electrical distribution networks are fastly changing due to some factors;among these, the progressive penetration of Distributed Generation (DG) is destined to cause deep changes in the existing networks, no longer considered as passive terminations of the whole electrical system. Moreover, the increasing application of Information Communication Technologies (ICT) will allow the implementation of the so called “smart grids”, determining new interesting scenarios. In the paper the problems and the potential benefits of DG, the possible new electrical distribution system models and the major research projects on smart grids are faced and reported.

Voltage Control in Smart Grids: An Approach Based on Sensitivity Theory

Due to the development of Distributed Generation (DG), which is installed in Medium-Voltage Distribution Networks (MVDNs) such as generators based on renewable energy (e.g., wind energy or solar energy), voltage control is currently a very important issue. The voltage is now regulated at the MV busbars acting on the On-Load Tap Changer of the HV/MV transformer. This method does not guarantee the correct voltage value in the network nodes when the distributed generators deliver their power. In this paper an approach based on Sensitivity Theory is shown, in order to control the node voltages regulating the reactive power exchanged between the network and the dispersed generators. The automatic distributed voltage regulation is a particular topic of the Smart Grids.