Advanced Metering Infrastructure Research Articles

A Review of anomaly detection techniques in advanced metering infrastructure

Advanced Metering Infrastructure (AMI) is a component of electrical networks that combines the energy and telecommunication infrastructure to collect, measure and analyze consumer energy consumptions. One of the main elements of AMI is a smart meter that used to manage electricity generation and distribution to end-user. The rapid implementation of AMI raises the need to deliver better maintenance performance and monitoring more efficiently while keeping consumers informed on their consumption habits. The convergence from analog to digital has made AMI tend to inherit the current vulnerabilities of digital devices that prone to cyber-attack, where attackers can manipulate the consumer energy consumption for their benefit. A huge amount of data generated in AMI allows attackers to manipulate the consumer energy consumption to their benefit once they manage to hack into the AMI environment. Anomalies detection is a technique can be used to identify any rare event such as data manipulation that happens in AMI based on the data collected from the smart meter. The purpose of this study is to review existing studies on anomalies techniques used to detect data manipulation in AMI and smart grid systems. Furthermore, several measurement methods and approaches used by existing studies will be addressed.

Data falsification attacks in advanced metering infrastructure

Smart grids are the cutting-edge electric power systems that make use of the latest digital communication technologies to supply end-user electricity, but with more effective control and can completely fill end user supply and demand. Advanced Metering Infrastructure (AMI), the backbone of smart grids, can be used to provide a range of power applications and services based on AMI data. The increased deployment of smart meters and AMI have attracted attackers to exploit smart grid vulnerabilities and try to take advantage of the AMI and smart meter’s weakness. One of the possible major attacks in the AMI environment is False Data Injection Attack (FDIA). FDIA will try to manipulate the user’s electric consumption by falsified the data supplied by the smart meter value in a smart grid system using additive and deductive attack methods to cause loss to both customers and utility providers. This paper will explore two possible attacks, the additive and deductive data falsification attack and illustrate the taxonomy of attack behaviors that results in additive and deductive attacks. This paper contributes to real smart meter datasets in order to come up with a financial impact to both energy provider and end-user.

The effect of smart meter penetration on dynamic electricity pricing: Evidence from the United States

A successful grid modernization comprises not only the deployment of new energy infrastructure and technologies, but also the utilization of these technologies to promote modern energy services and active consumer engagement. As an enabling technology in smart grids, advanced metering infrastructure (AMI) has been rapidly deployed in the U.S. By the end of 2016, almost half of all electricity consumers have AMI meters with two-way communication capability. While many have examined the driving forces for smart meter technology diffusion, there has been limited empirical evidence on the actual utilization of smart meters in modern energy services. To fill this research gap, this paper explores how electric utilities in the U.S. are leveraging AMI meter installations to implement dynamic pricing programs. A cross-sectional dataset for 582 electric utilities in the U.S. is constructed based on the EIA 861 form “Annual Electric Power Industry Report” from the year 2016. A fractional response regression model is estimated, and results show that a ten-percentage increase in smart meter penetration is associated with an average of 0.56 percentage increase in customer participation in dynamic pricing programs. The estimated effect of smart meters on dynamic pricing programs is relatively small, given the magnitude of capital investment and the scale of smart meter market penetration in the U.S. Future smart grid policies in the U.S. may gradually move away from public investment in AMI roll out and shift to supportive policies that facilitate the implementation and use of AMI to realize the full benefits of smart grid.

Quality Control Methods for Advanced Metering Infrastructure Data

While urban-scale building energy modeling is becoming increasingly common, it currently lacks standards, guidelines, or empirical validation against measured data. Empirical validation necessary to enable best practices is becoming increasingly tractable. The growing prevalence of advanced metering infrastructure has led to significant data regarding the energy consumption within individual buildings, but is something utilities and countries are still struggling to analyze and use wisely. In partnership with the Electric Power Board of Chattanooga, Tennessee, a crude OpenStudio/EnergyPlus model of over 178,000 buildings has been created and used to compare simulated energy against actual, 15-min, whole-building electrical consumption of each building. In this study, classifying building type is treated as a use case for quantifying performance associated with smart meter data. This article attempts to provide guidance for working with advanced metering infrastructure for buildings related to: quality control, pathological data classifications, statistical metrics on performance, a methodology for classifying building types, and assess accuracy. Advanced metering infrastructure was used to collect whole-building electricity consumption for 178,333 buildings, define equations for common data issues (missing values, zeros, and spiking), propose a new method for assigning building type, and empirically validate gaps between real buildings and existing prototypes using industry-standard accuracy metrics.

A retrospective analysis of the impact of the COVID-19 restrictions on energy consumption at a disaggregated level

Since the emergence of the virus that causes COVID-19 (the SARS-CoV-2) in Wuhan in December 2019, societies all around the world have had to change their normal life patterns due to the restrictions and lockdowns imposed by governments. These changes in life patterns have a direct reflection on energy consumption. Thanks to Smart Grid technologies, specifically to the Advance Metering Infrastructure at secondary distribution network, this impact can be evaluated even at the customer level. Thus, this paper analyzes the consumption behavior and the impact that this crisis has had using Smart Meter data. The proposed approach includes the selection and normalization of features, automatic clustering, the obtaining of the estimated consumption without considering the crisis (at short and mid-terms) and the impact evaluation. The proposed approach has been tested on a case with a real Smart Meter infrastructure from Manzanilla (Huelva, Spain). The results of this use case showed that residential customers have increased their consumption around 15% during full lockdown and 7.5% during the reopening period. In contrast, globally, non-residential customers have decreased their consumption 38% during full lockdown and 14.5% during the reopening period. However, referring to non-residential customers, five different consumption profiles were found with different short-term and mid-term behaviors during the COVID crisis. The different behavior found shows customers who have maintained their normal consumption during the lockdown, others who have reduced it (to a greater or lesser extent) and have not recovered it after the removal of the restrictions, and others who have reduced the consumption but then they recovered it when the restrictions were removed. The metadata of the customers in each behavior cluster found are highly correlated to the restrictions imposed to control the spread of the virus. This study shows evidence about the proposed approach usefulness to analyze the behavior and the impact at customer level during the COVID-19 crisis.

Deep reinforcement learning based home energy management system with devices operational dependencies

Advanced metering infrastructure and bilateral communication technologies facilitate the development of the home energy management system in the smart home. In this paper, we propose an energy management strategy for controllable loads based on reinforcement learning (RL). First, based on the mathematical model, the Markov decision process of different types of home energy resources (HERs) is formulated. Then, two RL algorithms, i.e. deep Q-learning and deep deterministic policy gradient are utilized. Based on the living habits of the residents, the dependency modes for HERs are proposed and are integrated into the reinforcement learning algorithms. Through the case studies, it is verified that the proposed method can schedule HERs properly to satisfy the established dependency modes. The difference between the achieved result and the optimal solution is relatively small.

Cyber Threat Intelligence Framework for Incident Response in an Energy Cloud Platform

Advanced information technologies have transformed into high-level services for more efficient use of energy resources through the fusion with the energy infrastructure. As a part of these technologies, the energy cloud is a technology that maximizes the efficiency of energy resources through the organic connection between the entities that produce and consume the energy. However, the disruption or destruction of energy cloud systems through cyberattacks can lead to incidents such as massive blackouts, which can lead to national disasters. Furthermore, since the technique and severity of modern cyberattacks continue to improve, the energy cloud environment must be designed to resist cyberattacks. However, since the energy cloud environment has different characteristics from general infrastructures such as the smart grid and the Advanced Metering Infrastructure (AMI), it requires security technology specialized to its environment. This paper proposes a cyber threat intelligence framework to improve the energy cloud environment’s security. Cyber Threat Intelligence (CTI) is a technology to actively respond to advanced cyber threats by collecting and analyzing various threat indicators and generating contextual knowledge about the cyber threats. The framework proposed in this paper analyzes threat indicators that can be collected in the advanced metering infrastructure and proposes a cyber threat intelligence generation technique targeting the energy cloud. This paper also proposes a method that can quickly apply a security model to a large-scale energy cloud infrastructure through a mechanism for sharing and spreading cyber threat intelligence between the AMI layer and the cloud layer. Our framework provides a way to effectively apply the proposed technologies through the CTI architecture, including the local AMI layer, the station layer, and the cloud layer. Furthermore, we show that the proposed framework can effectively respond to cyber threats by showing a 0.822 macro-F1 score and a 0.843 micro-F1 score for cyberattack detection in an environment that simulates a model of an attacker and an energy cloud environment.

Attack Context Embedded Data Driven Trust Diagnostics in Smart Metering Infrastructure

Spurious power consumption data reported from compromised meters controlled by organized adversaries in the Advanced Metering Infrastructure (AMI) may have drastic consequences on a smart grid’s operations. While existing research on data falsification in smart grids mostly defends against isolated electricity theft, we introduce a taxonomy of various data falsification attack types, when smart meters are compromised by organized or strategic rivals. To counter these attacks, we first propose a coarse-grained and a fine-grained anomaly-based security event detection technique that uses indicators such as deviation and directional change in the time series of the proposed anomaly detection metrics to indicate: (i) occurrence, (ii) type of attack, and (iii) attack strategy used, collectively known as attack context . Leveraging the attack context information, we propose three attack response metrics to the inferred attack context: (a) an unbiased mean indicating a robust location parameter; (b) a median absolute deviation indicating a robust scale parameter; and (c) an attack probability time ratio metric indicating the active time horizon of attacks. Subsequently, we propose a trust scoring model based on Kullback-Leibler (KL) divergence, that embeds the appropriate unbiased mean, the median absolute deviation, and the attack probability ratio metric at runtime to produce trust scores for each smart meter. These trust scores help classify compromised smart meters from the non-compromised ones. The embedding of the attack context, into the trust scoring model, facilitates accurate and rapid classification of compromised meters, even under large fractions of compromised meters, generalize across various attack strategies and margins of false data. Using real datasets collected from two different AMIs, experimental results show that our proposed framework has a high true positive detection rate, while the average false alarm and missed detection rates are much lesser than 10% for most attack combinations for two different real AMI micro-grid datasets. Finally, we also establish fundamental theoretical limits of the proposed method, which will help assess the applicability of our method to other domains.

Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid

ABSTRACT The evolution of advanced metering infrastructure (AMI) has increased the electricity consumption data in real-time manifolds. Using this massive data, the load forecasting methods have undergone numerous transformations. In this paper, short-term and mid-term load forecasting (STLF and MTLF) is proposed using smart-metered data acquired from a real-life distribution grid at the NIT Patna campus with different classical and machine learning methods. Data pre-processing is done to transform the raw data into an appropriate format by removing the outliers present in the datasets. The influential meteorological variables obtained by correlation analysis along with the past load are used to train the load forecasting model. The proposed support vector regression (SVR) produces the best forecasting performance for the test system with a minimum mean absolute percentage error (MAPE) and root mean square error (RMSE). The proposed method outperforms the existing approaches for STLF and MTLF by an average MAPE of 3.60.

Advanced Metering Infrastructure with Secure Chord Lookup Protocol for IoT Systems

The advanced metering infrastructure is enhanced in terms of system storage and latency using a secure chord lookup protocol scheme. Privacy of the subscriber and data security is maintained while reducing the memory consumption and data exchange duration using a protected multi-mode computation algorithm in the proposed model. Internet of things (IoT) based advanced metering networks can be greatly benefitted by this model. The production capacity is increased by 25% using the proposed model as per the simulated results, when compared to the existing systems. There is also over 50% reduction in the average data collection time and 15% reduction in the package delivery ratio. Lightweight authentication based secure mechanism is also provided to improve the safety of the model. When compared to the existing algorithms, the memory requirement and utilization of the proposed model is reduced by half.

Intrusion Detection System in the Advanced Metering Infrastructure: A Cross-Layer Feature-Fusion CNN-LSTM-Based Approach.

Among the key components of a smart grid, advanced metering infrastructure (AMI) has become the preferred target for network intrusion due to its bidirectional communication and Internet connection. Intrusion detection systems (IDSs) can monitor abnormal information in the AMI network, so they are an important means by which to solve network intrusion. However, the existing methods exhibit a poor ability to detect intrusions in AMI, because they cannot comprehensively consider the temporal and global characteristics of intrusion information. To solve these problems, an AMI intrusion detection model based on the cross-layer feature fusion of a convolutional neural networks (CNN) and long short-term memory (LSTM) networks is proposed in the present work. The model is composed of CNN and LSTM components connected in the form of a cross-layer; the CNN component recognizes regional features to obtain global features, while the LSTM component obtain periodic features by memory function. The two types of features are aggregated to obtain comprehensive features with multi-domain characteristics, which can more accurately identify intrusion information in AMI. Experiments based on the KDD Cup 99 and NSL-KDD datasets demonstrate that the proposed cross-layer feature-fusion CNN-LSTM model is superior to other existing methods.

Utilizing Private LTE to Increase Grid Resiliency

Utilities have long relied on telecommunication systems and infrastructure to perform critical functions such as teleprotection (TP), supervisory control and data acquisition (SCADA), distribution automation (DA), advanced metering infrastructure (AMI), and workforce communications. The information provided by these systems allows utility operators to gather real‐time information on the performance of the transmission and distribution (T&D) systems, protect against electric faults, and allow the workforce to communicate during emergencies and restoration events. Many of these operational systems are reliant on telecommunications technologies that were installed decades ago. While they have been reliable and served their purpose for years, these devices are beginning to fail and in some cases manufacturers no longer support legacy technologies.

Impact of data availability and pseudo‐measurement synthesis on distribution system state estimation

The influence of the advanced metering infrastructure (AMI) set-up and of the related modelling of pseudo-measurements on the accuracy of state estimation (SE) in distribution grids, especially at the low-voltage level, is studied herein. A comprehensive sensitivity analysis is carried out that accounts for the type, the penetration level, and the placement of the metering devices that compose state-of-the-art AMIs. Special care is given to the synthesis of active and reactive power pseudo-measurements, which substantially impacts the estimation of peak values. Although crucial for system operators, peak values are very often neglected in the SE literature. For that purpose, this study promotes realistic approaches to generate synthetic load profiles and relies on evaluation metrics that are not purely based on the point-wise precision but consider the statistical properties of the SE outcomes. This is tested on an actual 971-bus distribution grid with the corresponding smart meter data and is evaluated with respect to the accuracy of active and reactive power injections, bus voltages, and line loadings.

Novel certificateless Chebyshev chaotic map-based key agreement protocol for advanced metering infrastructure

The integration of information technologies into the current power grid has raised significant security concerns for the advanced metering infrastructure (AMI). Evidently, without employing proper security measures, illegal or malicious entities could launch miscellaneous attacks. Thus, scholars have presented several key agreement schemes, which can be used by different parties in the AMI guaranteeing their subsequent secure communications. However, after careful deliberation, we found that their efficiency could be still improved while keeping the desired security properties. Thus, in this paper, utilizing the Chebyshev chaotic maps, as one of the most efficient security methods, we first propose a novel certificateless anonymous authentication and key agreement scheme that both enhances the security and reduces the overhead on the computationally constrained measurement devices. To be more specific, we propose a novel signature scheme in the Chebyshev cryptosystem in order to make our protocol certificateless eliminating the key escrow issue and certificate management overhead. By the way, the proposed scheme is the first Chebyshev chaotic map-based key agreement protocol that is certificateless. Then, we validate the security of the proposed scheme using the random oracle model and ProVerif tool as two well-known and popular formal techniques. Our comprehensive functionality, communication cost, and execution time comparisons indicate the superiority of our scheme compared to the all related schemes in terms of both security and efficiency. For a key agreement, the execution time of the proposed scheme is just 539 microseconds, and its communication overhead is only 1088 bits, much better than the existing related ones.

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).

Hybrid machine learning based energy policy and management in the renewable-based microgrids considering hybrid electric vehicle charging demand

In this paper, a secured energy management architecture for both islanded and grid-connected operation modes of renewable hybrid AC-DC microgrids considering various renewable energy sources, distributed power generation units, energy storage, and plug-in hybrid electric vehicles (PHEV) is proposed. In this architecture, whale optimization algorithm (WOA) is employed to minimize the operation cost of the grid and also an intrusion detection system (IDS) based on the sequential hypothesis testing (SHT) approach is introduced to detect identity-based cyber-attacks (i.e. Sybil attack, masquerading attack) on the wireless-based advanced metering infrastructures (AMI). The proposed IDS makes use of the received signal strength (RSS) value to distinguish different signal sources and detect cyber-attacks. The feasibility and performance of the proposed architecture are tested on a practical hybrid microgrid, which is constructed based on the IEEE 33-bus test system. the results are provided for both islanded and grid-connected operation modes.

A Privacy-Preserving Homomorphic Scheme With Multiple Dimensions and Fault Tolerance for Metering Data Aggregation in Smart Grid

Advanced Metering Infrastructure (AMI) facilitates the communication between smart meters and network operators in smart grid. For better demand-response management, smart meters are supposed to send live or sometimes periodic consumption reports. If such reports are intercepted or eavesdropped by a malicious entity, customers’ privacy is compromised, since vital information can be inferred from power consumption data. In this article, we propose a novel homomorphic privacy-preserving protocol (called NHP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> ) for data aggregation that has a low computational cost compared to its rivals. It is fault-tolerant, supports multi-category aggregation, and can do batch verification at the intermediate aggregator as well as the central system. The proposed protocol is secure even when the gateway or aggregator turns malicious. It does not allow any compromised meter to find other users’ consumption information either. Moreover, in this scheme, the central system cannot infer any usage data even if it is curious and gains access to the data packets sent from meters to the intermediate aggregator. A comprehensive and comparative analysis is carried out at the end of this article which shows the advantages of the proposed scheme in terms of security features and cost.

Clustering Algorithm-Based Network Planning for Advanced Metering Infrastructure in Smart Grid

Nowadays, legacy electrical distribution systems are migrating to a new modern electric grid with the capability of supporting different applications such as advanced metering infrastructure (AMI), distributed energy resources, and electric vehicles. Among these applications, AMI is playing an important role in delivering data from customers to power utilities, supporting reliable real-time monitoring, and remote operation of power quality data and voltage profile. The AMI consists of smart meters, data aggregation points (DAPs), the utility control center, and communication networks. Appropriate network planning plays an essential role in facilitating the exchange of data between consumers and power utilities as well as accommodating new smart grid applications and future growth. This work proposes an optimal placement of DAPs for AMI based on machine learning clustering techniques in residential grids. Network partitioning is introduced to create sub-networks and graph algorithms generate a deployment topology given optimization constraints. A new measurement metric called coverage density is considered to indicate neighborhood area networks (NAN) zones with the appropriate coverage. Three real scenarios of NAN are considered: urban, suburban, and rural. The proposed algorithm is evaluated and compared with conventional heuristic optimization methods with respect to average and maximum distance between smart meters and DAPs, coverage density, and execution time.

A Case Study to Quantify Variability in Building Load Profiles

Recent technology development and penetration of advanced metering infrastructure (AMI), advanced building control systems, and the internet-of-things (IoT) in the built environment are providing detailed information on building operation, performance, and user’s comfort and behavior. Building owners can obtain a wide range of energy consumption details at various levels of time granularity to augment their decisions as they manage the building operation and interact with the grid. AMI data are providing a new level of detail and visibility that may enhance building services and assets in the smart grid domain and make buildings inch closer to becoming a grid-interactive energy efficient buildings (GEB). While utility-installed AMI typically records energy consumption at a 15, 30, or 60-minute resolution, building-owner-installed metering can record energy consumption at one-minute or sub-minute time scales, providing information about how much the energy consumption varies from one sub-minute to the other (i.e. variability) at a finer time resolutions than typically available from AMI. This paper examines one-minute building load profile data sets and presents a framework to study, define, extract, quantify and analyze variability in buildings’ load profiles. The discussion of variability and its analysis is based on a case study of an actual sub-minute time-resolution data set, collected in 2019, for two buildings in a Midwest state in the USA. The result shows that for the case studies, the level of variability in an end-use category is not simply proportional to its consumption. Furthermore, distinct and predictable daily variability patterns emerge in end-use load categories. This information is useful for a host of applications including prediction, forecasting, and modeling.

Forensic Analysis on False Data Injection Attack on IoT Environment

False Data Injection Attack (FDIA) is an attack that could compromise Advanced Metering Infrastructure (AMI) devices where an attacker may mislead real power consumption by falsifying meter usage from end-users smart meters. Due to the rapid development of the Internet, cyber attackers are keen on exploiting domains such as finance, metering system, defense, healthcare, governance, etc. Securing IoT networks such as the electric power grid or water supply systems has emerged as a national and global priority because of many vulnerabilities found in this area and the impact of the attack through the internet of things (IoT) components. In this modern era, it is a compulsion for better awareness and improved methods to counter such attacks in these domains. This paper aims to study the impact of FDIA in AMI by performing data analysis from network traffic logs to identify digital forensic traces. An AMI testbed was designed and developed to produce the FDIA logs. Experimental results show that forensic traces can be found from the evidence logs collected through forensic analysis are sufficient to confirm the attack. Moreover, this study has produced a table of attributes for evidence collection when performing forensic investigation on FDIA in the AMI environment.