Smart Grid Framework Research Articles

Data-driven and model-based framework for smart water grid anomaly detection and localization

Abstract With increasing adoption of advanced meter infrastructure, smart sensors together with SCADA (Supervisory Control and Data Acquisition) systems, it is imperative to develop novel data analytics and couple the results with hydraulic modeling to improve the quality and efficiency of water services. One important task is to timely detect and localize anomaly events, which may include, but not be limited to, pipe bursts and unauthorized water usages. In this paper, a comprehensive solution framework has been developed for anomaly detection and localization by formulating and integrating data-driven analytics with hydraulic model calibration. Data analysis for anomaly detection proceeds in multiple steps including the following: (1) data pre-processing to eliminate and correct erroneous data records, (2) outlier detection by statistical process control methods and deep machine learning, and (3) system anomaly classification by correlation analysis of multiple sensor events. Classified system anomaly events are subsequently localized via hydraulic model calibration. The integrated solution framework is developed as a user-friendly and effective software tool, tested, and validated on the selected target areas in Singapore.

Introducing a novel approach in one-step ahead energy load forecasting

Energy sector stakeholders, such as Distribution System Operators (DSO) or Aggregators take advantage of improved forecasting methods. Increased forecasting accuracy facilitates handling energy imbalances between generation and consumption. It also supports Smart Grid framework processes, such as Demand-Side or Demand Response Management (DRM). This paper presents a novel approach for One-Step-Ahead Energy Load Forecasting (OSA-ELF), considering several techniques. It utilizes historical data from a state-of-the-art nearly Zero Energy Building (nZEB) smart home, performing multiple tests for improved ELF. It focuses on OSA aspects of ELF, yet it can be utilized regardless of the time resolution. It predicts the “next step” value, regardless of the step’s duration (15-minutes, one-hour, one-day etc.) with high accuracy, and can be used for a wide variety of forecasting applications. To that end, fine-tuned ensemble methods and forecasting algorithms were utilized for experimenting with short term ELF. Forecasting evaluation produced good results with regards to popular accuracy (MAPE, SMAPE and RMSE) and an Execution Time (ET) metrics.

Energy Consumption Patterns and Load Forecasting with Profiled CNN-LSTM Networks

By virtue of the steady societal shift to the use of smart technologies built on the increasingly popular smart grid framework, we have noticed an increase in the need to analyze household electricity consumption at the individual level. In order to work efficiently, these technologies rely on load forecasting to optimize operations that are related to energy consumption (such as household appliance scheduling). This paper proposes a novel load forecasting method that utilizes a clustering step prior to the forecasting step to group together days that exhibit similar energy consumption patterns. Following that, we attempt to classify new days into pre-generated clusters by making use of the available context information (day of the week, month, predicted weather). Finally, using available historical data (with regard to energy consumption) alongside meteorological and temporal variables, we train a CNN-LSTM model on a per-cluster basis that specializes in forecasting based on the energy profiles present within each cluster. This method leads to improvements in forecasting performance (upwards of a 10% increase in mean absolute percentage error scores) and provides us with the added benefit of being able to easily highlight and extract information that allows us to identify which external variables have an effect on the energy consumption of any individual household.

Development of Microcontroller Based Smart Grid Framework

Smart grid technology has been recognized as a promising solution for the next-generation energy efficient electric power systems to mitigate energy crisis. Smart grid provides highly consistent and reliable services, efficient energy management practices, smart metering integration, automation and precision decision support systems and self-healing facilities. The smart power grid introduces a sensing, monitoring, and control system that provides end users with the cost of energy at any moment through real-time pricing. The classical power system operation has no control over the loads except in an emergency situation when a portion of the loads can be dropped as needed to balance the power grid generation with its loads. Furthermore, the smart power grid supplies the platform for the use of renewable energy sources that acts as a safeguard against a complete blackout of the interconnected power grid. In this work, all the concepts involved in smart grid mechanism is implemented with PIC18F452 microcontroller and other supplementary components. A solar module with storage capacity is connected to the proposed system for minimizing grid energy consumption and plays a primary energy source for maximum utilization of green energy. This intelligent device may inherently reduce the consumption of electrical energy during peak hours and allow consumers to sell back electricity into grid using bi-directional technique. Barriers, challenges, benefits and future trends regarding the technologies and the role of users have also been discussed in this paper.

Smart Grid: A Sustainable Smart Approach

In the modern power system, smart grid structure is getting admiration and edify a path of complete greener way of energy generation. This paper highlights each aspects of this framework to justify the energy demand in a sheltered, economical, trustworthy and environmental manner even the absence of storage structure at large level. It also facilitates the simultaneous objectives of demand monitoring and control with the amalgamation of renewable distributed generation having smart devices and storage system. A comprehensive review has been demonstrated with the smart operations unlike traditional power grid even the presence of some limitations for the establishment of advanced grid-based power network. The analysis presented in this paper is driven by the eventuality of relic fuel calamity, ecological contamination, diminution of electrical energy, enlargement necessity of power system, newness to emergent trends in proficient energy utilization and regularly increasing electricity bill. Objective of this presentation is to review and examine the different aspects of smart grid framework for the progression of generation companies and consumer with reference to its development and advancement report, techno-economical contests, conceivable benefits and future scope..

Model predictive control for optimal energy management of connected cluster of microgrids with net zero energy multi-greenhouses

This paper intends to present a cooperative control framework for a connected cluster of microgrids with multi-smart greenhouses creating a smart local electric grid in the framework of smart grids. Each microgrid comprises renewable generators, pumps, advanced communication and metering infrastructure, water reservoir, energy storage device, and a set of greenhouses where each one includes heating, ventilation and air conditioning (HVAC), CO2 injector, artificial lighting, sensors, local pump, and fans. The key objective is to formulate a coordinated optimization framework embedded in a model predictive control (MPC) scheme to optimally control the operation of the clustered microgrids and manage the power flows exchange ensuring a high quality of service. The microgrids are connected permitting the power exchanges to enhance the utilization of local renewable generations. Furthermore, the cluster is connected to the main grid through a power link permitting power exchange in excess/shortage case. The cooperation is achieved throughout a bidirectional communication infrastructure, where a centralized controller is responsible of managing the different control signals. A comprehensive scheduling optimization algorithm is developed and implemented to effectively control the clustered microgrids operation considering the operational constraints, where the purpose is to enhance energy efficiency, and manipulating effectively the microclimate variables defining the optimal environment for crops development in all greenhouses. An MPC-based energy management framework is implemented and applied to a case study to demonstrate its performance and effectiveness through extensive numerical simulations.

EWNet: An early warning classification framework for smart grid based on local-to-global perception

Early warning mechanism is crucial for maintaining the security and reliability of the power grid system. It remains to be a difficult task in a smart grid system due to complex environments in practice. In this paper, by considering the lack of vision-based datasets and models for early warning classification, we constructed a large-scale image dataset, namely EWSPG1.0, which contains 12,113 images annotated with five levels of early warnings. Moreover, 104,448 object instances with respect to ten categories of high-risk objects and power gird infrastructure were annotated with labels, bounding boxes and polygon masks. On the other hand, we proposed a local-to-global perception framework for arly warning classification, namely EWNet. Specifically, a local patch responsor is trained by using image patches extracted from the training set according to the labeled bounding box information of objects. The capability of recognizing high-risk objects and power grid infrastructure is transferred by loading the trained local patch responsor with frozen weights. Features are then fed into a feature integration module and a global classification module for early warning classification of an entire image. In order to evaluate the proposed framework, we benchmarked the proposed framework on our constructed dataset with 11 state-of-the-art deep convolutional neural networks (CNNs)-based classification models. Experimental results exhibit the effectiveness of our proposed method in terms of Top-1 classification accuracy. They also indicate that vision-based early warning classification remains challengeable under power grid surveillance and needs further study in future work.

Intelligent Optimization Framework for Efficient Demand-Side Management in Renewable Energy Integrated Smart Grid

The implementation of real-time price-based demand response program and integration of renewable energy resources (RESs) improves efficiency and ensure stability of electric grid. This paper proposes a novel intelligent optimization based demand-side management (DSM) framework for smart grid integrated with RESs. In the intelligent DSM framework the artificial neural network (ANN) forecasts energy usage behavior of consumers and real-time price-based demand response program (RTPDRP) of electric utility company (EUC). The smart energy management controller of the proposed intelligent DSM framework adapts forecasted energy usage behavior of consumers using forecasted RTPDRP to create operation schedule. The consumers implement the created schedule to minimize energy cost, peak load, carbon emission subjected to improving user comfort and avoiding rebound peaks. Simulations are conducted using our proposed hybrid genetic ant colony (HGAC) optimization algorithm to create schedule for three cases: EUC without RESs, EUC with RESs, and EUC with both RESs and storage technologies. To endorse the applicability and productivity of the proposed DSM framework based on HGAC optimization algorithm with five existing algorithms based frameworks. Simulation results show that the proposed DSM framework is superior compared with the existing frameworks in terms of energy cost minimization, peak load mitigation, carbon emission alleviation, and user discomfort minimization. The proposed HGAC optimization algorithm reduced electricity cost, carbon emission, and peak load by 12.16%, 4.00%, and 19.44% in case I; by 26.8%, 20.71%, and 33.3% in case II; and by 24.4%, 16.44%, and 37.08% in case III, respectively, compared to without scheduling.

An Innovative Smart Grid Framework for Integration and Trading

Smart Grids (SGs) are at the forefront of the renewable resources transformative change for power generation. Due to its decentralised energy generation approach and potential reduction of the cost of power, its relevance for the energy sector is insurmountable. However, new business models and processes are necessary, and they come with integration, implementation, and operation-specific challenges. This work offers a broad analysis of SG’ main architectural aspects concerning security issues, integration bottlenecks and standardisation shortcomings in the development of an efficient platform for local energy (generation and storage) surplus trading. Through a multi-layered smart grid architecture description, this work develops an in-depth depiction of the interoperability between these layers (from top business layer passing through information and communications layers, and down to generation and storage layers). Therefore, this paper encompasses a comprehensive framework to address central smart grids design aspects and suggests a path to integrate the smart grid components into a cohesive and manageable trading platform. Finally, this work demonstrates how the proposed framework can be applied to real market study cases to highlight its solutions, provide a critical evaluation of potential implementation pitfalls, and identify opportunities for further stateof-the-art research.

Editorial for special issue on security, trust, and privacy in internet of things: Challenges and solutions

Editorial for special issue on security, trust, and privacy in internet of things: Challenges and solutions

Green Industrial Internet of Things from a smart industry perspectives

The goal of industrial revolutions is not only to improve and respond directly to the needs of industry in a productive side fact, but also to improve the standard of living of society and make life easier for customers. Therefore, economic growth should always go hand in hand with each industrial revolution. In this context, the increasing demand for electricity, the non-renewable nature of conventional sources and the rising price of fuel, are considered the constraints of the 21st century and need to be definitively managed in order to meet the constantly increasing demand for electricity from the population in the best possible conditions. Information and Communication Technologies (ICTs) are the foundation on which tomorrow’s innovative solutions are created. However, smart embedded systems and the internet are two major players driving ICT technologies forward. These technologies have impacted several sectors, where we find a crossroads of several industrial sectors: medical, manufacturing, automation, energy and others. The application these technologies in a smart grid framework with the integration of renewable energy sources and used for an optimization and efficiency mission let Internet of Things (IoT) to take the sustainable and industrial character and named Green Industrial Internet of Things (GIIoT). This last, seems to be a promoting axis for the development of future applications. In this paper, we present an overview of the impact of the Internet of Things on the evolution of applications in relation to the different revolutions, an inventory of the different industrial revolutions, an overview of the GIIoT as well as some applications and perspectives.

Correcting “PALK: Password-based anonymous lightweight key agreement framework for smart grid”

Very recently in 2020, Khan et al. proposed an authentication scheme (PALK) for the smart grid infrastructure. Based on elliptic curve cryptography (ECC), symmetric hash functions and block cipher based encryption/decryption operations, the scheme was argued to work efficiently and securely in smart grid based infrastructure. However, in this paper, we prove that PALK has incorrect login and authentication phase; mainly, due to a superficial ECC operation involving the multiplication of two points over the curve. Moreover, in the scheme of Khan et al. the responding entity without knowing any clue of the initiator, uses the public key of the initiator for the completion of the authentication process, which is also not possible in the presence of multiple communicating devices. These design flaws lead to the situation, where the smart grid entities are unable to complete even a single cycle of authentication. Finally, we propose a quick solution to fix the pertinent flaws of the PALK. The security and correctness of the proposed solution iPALK is proved using formal BAN logic, automated tool ProVerif along with a brief discussion on the correctness of the scheme. The performance comparisons also show that the iPALK not only provides the correctness, but it is more efficient in terms of computation and communication costs.

Increasing Penetration of DERs in Smart Grid Framework: A State-of-the-Art Review on Challenges, Mitigation Techniques and Role of Smart Inverters

The world is witnessing a transformation from the conventional electrical grid into the smart grid. The smart grid can provide an effective solution to alarming problems associated with a conventional grid with increased reliability, efficiency, and sustainability. Integration of distributed energy resources (DERs) comprising of renewable energy sources (RESs) is a vital component of the smart grid. DERs not only can provide a viable solution for environmental concerns arising due to conventional fossil fuel-based plants, but can also contribute towards the system reliability. However, the integration of DERs is associated with several challenges. Thus, the successful deployment of DERs in smart grid framework calls for a comprehensive analysis. This paper presents an exhaustive review of various challenges associated with increased penetration of DERs. An organized classification of various technical challenges along with their mitigation measures has been critically reviewed. Smart inverters equipped with advanced control structure are emerging as a potential solution to address these challenges effectively. Hence, a review of smart inverter along with its functional capabilities has also been discussed in this paper.

PALK: Password-based anonymous lightweight key agreement framework for smart grid

Smart grid (SG) is a highly efficient and more reliable framework that controls the computer, automation, new technologies and equipment. In SG, electricity utilization and communication are exchange between consumers and the power grid. Security and privacy are essential components of SG communication. Various key agreement protocols have been presented for SG communication. Among these some protocols have security issues or high computational overhead. In the proposed paper, we design a password-based anonymous lightweight key agreement framework for smart grid (PALK) by using elliptic curve cryptography. We provide a formal security analysis of the PALK which is based on the random oracle model and informal security analysis. Moreover, we prove that PALK is security against man-in-the-middle attack and replay attack using the simulation tool “AVISPA”. Also, we demonstrate that PALK has better computation and communication costs than other related protocols in the same environment. The proposed framework is a real-life application in SG communication.

A Study and Analysis of Load Optimization Framework for Smart Grid

A Study and Analysis of Load Optimization Framework for Smart Grid

A fog‐based collaborative intrusion detection framework for smart grid

SummaryWith the rapid development of information and communication technologies (ICTs), the conventional electrical grid is evolving towards an intelligent smart grid. Due to the complexity, how to protect the security of smart grid environments still remains a practical challenge. Currently, collaborative intrusion detection systems (CIDSs) are one important solution to help identify various security threats, through allowing various IDS nodes to exchange data and information. However, with the increasing adoption of ICT in smart grid, cloud computing is often deployed in order to reduce the storage burden locally. However, due to the distance between grid and cloud, it is critical for smart grid to ensure the timely response to any accidents. In this work, we review existing collaborative detection mechanisms and introduce a fog‐based CIDS framework to enhance the detection efficiency. The results show that our approach can improved the detection efficiency by around 21% to 45% based on the concrete attacking scenarios.

Research on the Medium and Long Term Development Framework of Smart Grid under the Background of Energy Internet

Abstract This paper focuses on the development of smart grid in the trends of the energy Internet, analyze the development situation of smart grid and studies the requirements for the construction of major advanced smart grid demonstration areas in China. Under this background, this paper proposes medium and long term China smart grid development strategies, key tasks, technical routes and implementation plans. And planning practices in typical regions are carried out to support the implementation of major national strategic decision-making deployments.

Data-driven framework for energy-efficient smart cities

Energy management is one of the greatest challenges in smart cities. Moreover, the presence of autonomous vehicles makes this task even more complex. In this paper, we propose a data-driven smart grid framework which aims to make smart cities energy-efficient focusing on two aspects: energy trading and autonomous vehicle charging. The framework leverages deep learning, linear optimization, semantic technology, domain-specific modelling notation, simulation and elements of relay protection. The evaluation of deep learning module together with code generation time and energy distribution cost reduction performed within the simulation environment also presented in this paper are given. According to the results, the achieved energy distribution cost reduction varies and depends from case to case.

SECURE AND SUSTAINABLE SMART GRID FRAMEWORK USING THE CLOUD COMPUTING

The smart grid developments turning out to a promising technology for the two way communication of the electricity and the information are becoming more prominent in the present scenario due to the increasing demands in the power requirements. The smart grid utilizing the modern communication and the computing infrastructure makes this possible. This utilization of the modern communication and the computing systems make them even prone to the vulnerabilities, mishandlings and the miscommunications and necessary for a complex frame work for managing of the power distribution and generation to make them sustainable. So the paper proposes the cloud computing for the proper management and the protection of the smart grids to make them more secure against threats and sustainable by reducing the Co2 emission by the perfect management. The validation of the smart grid frame work using cloud computing by monitoring the power distribution, management and the security achieved over multiple usages show the enhanced power management and the security services provided by the cloud for the smart grid.

Time Horizon-Based Model Predictive Volt/VAR Optimization for Smart Grid Enabled CVR in the Presence of Electric Vehicle Charging Loads

This paper investigates the need of coordinated operation of conservation voltage reduction (CVR) in the presence of electric vehicle (EV) penetration in the active distribution network. In order to analyze the impact of both the technologies (CVR and EV), a time horizon-based model predictive Volt/VAR optimization (VVO) methodology has been introduced in smart grid framework. The proposed VVO methodology operates in centralized as well as local controls under different time scale of operation, including cloud transient effects on solar photovoltaic (PV) power output. Moreover, the control algorithms also consider the uncertainties in load demand and PV power generation. The VVO methodology has been validated with and without presence of EV loads in the distribution network. The VVO includes the impact of different EV charging loads having the ability of participation in reactive power support at selected charging points. This is also referred to as vehicle-to-grid operation in terms of reactive power dispatch only. Besides, the voltage and VAR regulation through smart inverters of PVs and EV charging station has been fruitfully utilized in global as well as local domain. A real-time Volt/VAR droop based controller has been introduced to control the smart inverters reactive power dispatch. To validate the developed methodology, a real-time cosimulation framework, using real-time digital simulator and Python interface, has been built. The proposed model predictive VVO algorithm has been tested and validated on a modified IEEE 34 bus test system. The simulated results reveal that significant CVR energy savings and losses reduction has been achieved without violating the system constraints. The voltage control algorithm works well in both slow and fast time scales.