Smart Microgrid Research Articles

Decentralized energy management system for smart microgrids using reinforcement learning

AbstractThis paper presents a novel fully decentralized and intelligent energy management system (EMS) for a smart microgrid based on reinforcement learning (RL) strategy. The purpose of the proposed EMS is to maximize the benefit of all microgrid entities comprising customers and distributed energy resources (DERs). Due to unpredictable features of renewable energy sources and variability of consumers’ demands, designing the microgrid EMS is a complicated task. To overcome this issue, the multi‐agent hour‐ahead energy management problem is modelled as a finite Markov decision process. The microgrid entities are considered as intelligent agents. The optimal policy of agents is obtained through a newly developed framework of the model‐free Q‐learning algorithm to maximize the benefit of all renewable and non‐renewable energy resources and battery energy storage system. The degradation model of the battery is considered to reduce the number of battery replacements. To ensure customers’ comfort, customers’ expenses are decreased without demand curtailment via introducing two types of load shifting techniques. The microgrid operation is analysed under four scenarios comprising no‐learning, generator‐learning, customer‐learning, and whole‐learning. the performance of the proposed algorithm is compared to the Monte Carlo method and simulation results on the real power‐grid dataset show the superiority of the algorithm.

Microgrid trading mechanism enhancement for smart contract considering reputation values

ABSTRACT In order to reduce the system instability caused by credit risk in microgrid transactions in the blockchain, we propose a smart contract microgrid transaction model considering reputation value. Considering the instability caused by credit risk, the reputation factor is introduced to ensure the secure and stable operation of the microgrid energy trading system. The effectiveness of the scheme is verified by comparing traditional electricity trading and the trading with the introduced credit value scheme through simulation experiments.

A Federated Learning and Blockchain-Enabled Sustainable Energy Trade at the Edge: A Framework for Industry 4.0

Through the digitization of essential functional processes, Industry 4.0 aims to build knowledgeable, networked, and stable value chains. Network trustworthiness is a critical component of network security that is built on positive interactions, guarantees, transparency, and accountability. Blockchain technology has drawn the attention of researchers in various fields of data science as a safe and low-cost platform to track a large number of eventual transactions. Such a technique is adaptable to the renewable energy-trade sector, which suffers from security and trustworthy issues. Having a decentralized energy infrastructure, that is supported by blockchain and artificial intelligence, enables smart and secure microgrid energy trading. The new age of industrial production will be highly versatile in terms of production volume and customization. As such a robust collaboration solution between consumers, businesses, and suppliers must be both secure and sustainable. In this article, we introduce a cooperative and distributed framework that relies on computing, communication, and intelligence capabilities of edge and end devices to enable secure energy trading, remote monitoring, and network trustworthiness. The blockchain and federated learning-enabled solution provide secure energy trading between different critical entities. Such a technique, coupled with 5G and beyond networks, would enable mass surveillance, monitoring, and analysis to occur at the edge. Performance evaluations are conducted to test the effectiveness of the proposed solution in terms of reliability and responsiveness in a vehicular network energy-trade scenario.

Integration of LFP-second life batteries as a storage in a smart microgrid

In recent years, there has been an increasing commitment to give batteries a second life, as they are being consumed for different uses and the recycling methods are not defined. This work aims to show how a storage system based on disused Lithium Iron Phosphate (LFP) batteries has been recovered and integrated into the CE.D.E.R- CIEMAT smart microgrid over a period of ten years during which the operation of the system has been affected. During the recovery process, the cells have been classified according to their voltage, and a series of charge-discharge processes have been carried out on them at different voltages to determine their state of health and capacity. Once characterised, the system was assembled and commissioned with the appropriate cells. In addition, for the storage system, a Supervisory Control And Data Acquisition (SCADA) has been developed in Home Assistant for its integration into the CE.D.E.R.'s microgrid management system. This allows the microgrid to be managed more efficiently, storing surplus energy from distributed generation sources and discharging the stored energy during peak consumption periods to reduce peaks, reduce discharges to the distribution grid and reduce the cost of electricity bills.

A Hybrid Short-Term Load Forecasting Approach for Individual Residential Customer

This article proposes a hybrid method (HM) to improve the accuracy of short-term individual residential load forecasting. The HM includes an ensemble model (EM), deep ensemble model (DEM), and thermal dynamic model expressed by resistance-capacitance (RC). The EM consists of three predictors of support vector machine (SVM), back propagation neural network (BPNN), and generalized regression neural network (GRNN). The genetic algorithm (GA) is used to optimize SVM and BPNN to enhance their performance. The DEM includes multiple bi-directional long-short term memory (Bi-LSTM) networks. The Bayesian algorithm (BA) is used to optimize the hyperparameters of the Bi-LSTM. The outputs of individual predictors are aggregated using an optimal trimmed algorithm. At first, the total load is separated into the heater and air conditioning (HAC), and non-HAC loads. Then, the RC model is presented to predict the indoor temperature, which integrates outdoor weather and less HAC historical data as the input of the EM to forecast the HAC load. After that, non-HAC loads are further divided into electric lighting and other loads. A daylight equation is used to calculate the illuminance, which is combined with less lighting historical data as the input of DEM to predict electric lights usage. Then, other loads are captured by DEM through less historical data. Finally, the total load is obtained by combining the predicted HAC and non-HAC loads. The datasets from the UMass Smart Microgrid and Flexhouse projects are used to test the proposed method. The comparison with existing models proves that the presented model can provide accurate short-term individual load forecasting.

Predictive models development using gradient boosting based methods for solar power plants

Being able to predict the power to be generated by solar power plants in a smart grid, microgrid or nanogrid with high accuracy and speed brings a lot of advantages in the decisions to be made for these systems. Making power generation forecasts, which are strictly dependent on the dynamic energy management of these grids, influences many factors from the amount of energy to be stored to the cost of energy. In this study, the development and analysis of three gradient boosting machine learning-based methods for power prediction are carried out. Innovative and fast predictive models are designed with XGBoost, LightGBM and CatBoost algorithms. These models, which have a training set consisting of several meteorological features, offer considerable benefits such as high accuracy and fast learning. Further, the performances of these models are compared and their applicability is discussed.

A multi-agent reinforcement learning approach for investigating and optimising peer-to-peer prosumer energy markets

Current power grid infrastructure was not designed with climate change in mind, and, therefore, its stability, especially at peak demand periods, has been compromised. Furthermore, in light of the current UN’s Intergovernmental Panel on Climate Change reports concerning global warming and the goal of the 2015 Paris climate agreement to constrain global temperature increase to within 1.5–2 °C above pre-industrial levels, urgent sociotechnical measures need to be taken. Together, Smart Microgrid and renewable energy technology have been proposed as a possible solution to help mitigate global warming and grid instability. Within this context, well-managed demand-side flexibility is crucial for efficiently utilising on-site solar energy. To this end, a well-designed dynamic pricing mechanism can organise the actors within such a system to enable the efficient trade of on-site energy, therefore contributing to the decarbonisation and grid security goals alluded to above. However, designing such a mechanism in an economic setting as complex and dynamic as the one above often leads to computationally intractable solutions. To overcome this problem, in this work, we use multi-agent reinforcement learning (MARL) alongside Foundation – an open-source economic simulation framework built by Salesforce Research – to design a dynamic price policy. By incorporating a peer-to-peer (P2P) community of prosumers with heterogeneous demand/supply profiles and battery storage into Foundation, our results from data-driven simulations show that MARL, when compared with a baseline fixed price signal, can learn a dynamic price signal that achieves both a lower community electricity cost, and a higher community self-sufficiency. Furthermore, emergent social–economic behaviours, such as price elasticity, and community coordination leading to high grid feed-in during periods of overall excess photovoltaic (PV) supply and, conversely, high community trading during overall low PV supply, have also been identified. Our proposed approach can be used by practitioners to aid them in designing P2P energy trading markets.

Artificial Intelligence Based Smart Home Energy Management System

Recently, countries are faced with an unreliable electric power supply to homes and the industry due to insufficient supply from the utility, causing load shedding. With the power utilities struggling to keep the lights on, there are initiatives to invest in backup power solutions and home energy management systems (HEMS) to manage this development. This paper analyzes energy consumption with the existing infrastructure of typical equipment used in homes. An approach called smart home energy management systems (SHEMS) is implemented to balance the power demand and the supply more effectively throughout the smart micro-grid by utilizing control algorithms simulated using MATLAB Simulink. This is achieved by utilizing real data from a home with commercial and residential load features in an urban area. The SHEMS revealed greater management and efficiency in electric power savings by reducing the utilities power demand. The framework adopts a local information management terminal as the core of data storage and scheduling in the home. Based on the timely purchase of electricity from the grid and the generation of electricity in combination with PV systems, an optimized simulation model for the scheduling of a new home energy management system is established. In addition, the application prospects of artificial intelligence in the HEMS are overviewed. Key Words: Balance of Power Demand, Energy efficiency, Smart Distribution Board (SDB), Smart Home Energy Management System (SHEMS), Artificial Intelligence.

Exploring Energy Trading Markets in Smart Grid and Microgrid Systems and Their Implications for Sustainability in Smart Cities

Smart cities are aimed at connecting urban infrastructures to enhance the efficiency of their operation and services while taking sustainability goals into consideration. As a result of the intermittency associated with renewable generation, smart city systems such as smart grids and microgrids may not be able to ensure the security of supply. This can be mitigated by allowing these systems to trade surplus energy with other neighboring systems through local energy markets based on peer-to-peer schemes. Such an approach can play an important role on achieving sustainability due to the positive impacts at the economic, social, and environmental level. Therefore, this work explores the design of local energy markets to help determine how they are relevant to smart grid and microgrid applications and what their contributions are to sustainability in smart cities. Essentially, this is achieved by performing a literature review to address key characteristics related to the design of local energy markets while considering their relationship with urban sustainability. In addition, the concept of game theory and its potential to evaluate market designs are also introduced and discussed. Finally, the suitability of centralized, decentralized, and distributed market designs for each dimension of sustainability is estimated based on their design characteristics.

Per-Phase Power Controller for Smooth Islanded Transitions in Three-Phase Three-Wire Systems

This manuscript describes the operation of a droop-based controller for three-phase converters in the case of the absence of a neutral connection to the grid. The controller is capable of output power tracking and smooth transitions into the islanded operation. While independent per-phase control of the converter output power is possible if a neutral connection is present, its absence implies additional constraints to be considered. Focusing on this latter case, the controller described herein allows the independent control of the active power at the output of each phase of the converter and a smooth transition to the islanded operation. These features are paramount in future smart power systems, such as smart microgrids, for implementing demand–response, power-flow management, and uninterrupted power operation.

Digital Twin-Based economic assessment of solar energy in smart microgrids using reinforcement learning technique

Utility companies recognize the importance and necessity of demand response (DR) programs for reducing the increased production costs associated with rising energy demand. The advent of smart information and communication systems has made DR programs on the basis of cost a viable option to control load in smart microgrids. Small domestic consumers are rapidly using stochastic renewable energy resources such as photovoltaic (PV). The study examines an integrated layout for residential load scheduling or load commitment problems (LCP) with renewable energy resources no matter what kind of tariff is applied. Uncertainty-based decision-making problems are effectively solved using reinforcement learning (RL). The paper proposes an RL-enabled solution to the LCP in smart microgrids. An innovative aspect of the study is the development of an integrated layout containing an implementable solution that takes into account user satisfaction, stochastic renewable power, and tariffs. In simulation tests, the suggested layout is tested for its effectiveness and flexibility. An analysis of the algorithm's efficiency using a household user with schedule-able and non-schedulable devices, together with a PV resource, has been presented.

Optimizing the Operation and Coordination of Multi-Carrier Energy Systems in Smart Microgrids Using a Stochastic Approach

Optimizing the Operation and Coordination of Multi-Carrier Energy Systems in Smart Microgrids Using a Stochastic Approach

A Novel Method of Vector Shift Criterion Utilization in Power System Automation

The article describes the new application of a well-known protection criterion - Vector Shift (VS). In the paper, technical problems related to the utilization of this criterion have been described. Additionally, the authors conducted laboratory tests of a digital protection relay. The impact of different disturbances occurring in the power systems on the operation of the Vector Shift criterion has been examined. The obtained results have proved the validity of banning the Vector Shift criterion in some countries. Furthermore, a novel application of the Vector Shift criterion has been presented. This criterion could be utilized to determine the degree of balance of a separated island. This information may be helpful in novel power system protection devices used in Smart Grids or microgrids.

Machine learning enabled learning based optimization algorithm in digital twin simulator for management of smart islanded solar-based microgrids

The key element of tomorrow's smart islanded microgrids (SMG) is Demand Side Management (DSM). Global energy awareness has led to an increase in SMGs' performance and peak balancing capabilities. DSMs are the control layout in these grids, and they aim at optimizing loads in various ways. The SMG includes batteries and distributed photovoltaics. This paper combines an Elephant Herding optimization algorithm (EHOA) and support sector machine (SVM) to the decision-making method in batteries for reducing the electric bill. EHOA could be an effective method for finding a nearly optimum solution to the load scheduling issue in order to reduce the consumers' expenses. Particularly, energy costs could be decreased if the consumer responds to prices that vary with the time of day. Therefore, The EHOA has been applied to assign the battery's optimum energy storage range. The SVM has been trained as a powerful machine learning method using optimal information from the EHOA. It has been employed to determine the amount of energy that has been transmitted into and out of batteries in order to take the lowest possible electric bills. In comparison to the current approach of 2.3 at the consumption of 8.2 kWh/day, the cost of the suggested method of mean generation oscillation (Gosc) has been equated to 2.27 dollars for the residential load. EHOA-SVM decreases 11.2% of energy costs, thereby assisting the decision-maker to balance the stability of demand-side measures.

Energy management in smart inter-connected micro-grids using Archimedes optimization algorithm

This paper produces a modern meta-heuristic optimization technique based on the buoyancy principle called the Archimedes optimization algorithm (AOA). The proposed algorithm is used here to determine the optimal economic operation of interconnected micro-grids (IMGs). Each micro-grids (MG) includes different types of distributed generation (DG) units such as solar photovoltaic (PV), wind turbine (WT), and micro-turbine (MT) and aims for achieving minimization of total power generation cost as the main objective function taking into consideration the power exchange between the IMGs and utility with special emphasis on technical constraints. To prove the effectiveness of the proposed AOA algorithm, it is compared with another optimization method based on the particle swarm optimization algorithm (PSO). Results obtained with the AOA algorithm show how managing energy transfer between utility and each MG. For various daily loads, it can reduce electricity consumption while lowering the cost of overall electricity generation, minimizing utility bills, and maximizing micro turbine (MT) efficiency.

A Review of Machine Learning Approaches in Synchrophasor Technology

As power systems (PS) move toward smart grids and microgrids in modern times, complexity eventually rises as a result of integration with various distributed energy resources, demand-side management, and cybersecurity issues. Additionally, frequent PS network blackouts will have an impact on a country’s social, economic, and financial position. To ensure the reliability as well as security of the network’s smart-driven power system, more advanced monitoring and measurement technology, which is dominated by SCADA systems, is required. This is where synchrophasor-based phasor measurement units (PMUs) come into play, which process and analyze massive amounts of data in real-time more precisely to identify systemic anomalies. Due to their quick response times, high computing speeds, accuracy, and scalability, machine learning (ML)-based techniques are becoming more popular for handling real-time big data. The many ML algorithms used recently in synchrophasor technology, which enhances cybersecurity, fault detection and classification, transient stability assessment, voltage stability assessment, and forced oscillation localization are thoroughly reviewed in this paper. With the help of more than 190 pertinent papers, this work effectively discusses the ML applications in the synchrophasor technology where PMUs and μPMUs are deployed. The article also shows that several concerns have not yet been resolved and are still up for consideration by researchers in the future. One of them is the detection and observation of oscillation and line-tripping occurrences in the distribution area where μPMUs are installed. To address these problems, sophisticated DL approaches are recommended. Future possibilities to decrease bandwidth usage and improve processing delay using edge computing technology are also mentioned in this paper. The research potential for ML and DL approaches also extends to power line communication, wide area monitoring systems, and 5G and 6G network communications.

A new reinforcement learning approach for improving energy trading management for smart microgrids in the internet of things

A new reinforcement learning approach for improving energy trading management for smart microgrids in the internet of things

A Robust Renewable Energy Source-oriented Strategy for Smart Charging of Plug-in Electric Vehicles Considering Diverse Uncertainty Resources

Nowadays, the notion of plug-in electric vehicle (PEV) as a valuable tool of energy management has been extensively employed in smart distribution grids. The main advantage of clean energy as well as elastic behaviour of operation in both electrical load/generation modes can sufficiently justify the utilization of such emerging technology. Moreover, the specific capability of renewable energy sources (RESs) in terms of contribution in PEV smart charging/discharging scheme would cause to remarkable techno-economic benefits in smart grids. However, the load demand, RES generation and also the electrical energy price encounter with uncertainty in practice required to be properly handled. Hence, a non-deterministic optimization model based on information gap decision theory (IGDT) is proposed in this paper to specify a robust PEV smart charging pattern. To solve the multi-objective proposed IGDT-based PEV smart charging (IGDT-PSC) model, the multi-objective version of particle swarm optimization (MOPSO) is utilized to define a set of Pareto optimal solutions. Furthermore, the final solution among the Pareto solutions is selected by means of a linear fuzzy satisfaction rule. The simulation results for a test smart microgrid comprising a PEV, a set of RES units and a load demand verify the effectiveness of the proposed IGDT-PSC model.

Optimizing Decision-Making of A Smart Prosumer Microgrid Using Simulation

Distributed renewable energy sources offer significant alternatives for Qatar and the Arab Gulf region’s future fuel supply and demand. Microgrids are essential for providing dependable power in difficult-to-reach areas while incorporating significant amounts of renewable energy sources. In energy-efficient data centers, distributed generation can be used to meet the facility’s overall power needs. This study primarily focuses on the best energy management practices for a smart microgrid in Qatar while taking demand-side load management into account. This article looked into a university microgrid in Qatar that primarily aimed to get all of its energy from the grid. While diesel generators are categorized as a dispatchable distributed generation with energy storage added to handle solar radiation from the sun and high grid power operating costs in the suggested scenario, wind turbines and solar Photovoltaic (PV) are classified as non-dispatchable distributed generators. The resulting linear math issues are assessed and displayed in MATLAB optimization software using a mixed-integer linear programming (MILP) strategy. According to the simulation results, the suggested energy management strategy reduced the university microgrid’s grid power costs by 38.8%, making it an affordable solution which is somehow greater than the prior case scenario’s 23% savings. The installed solar system capacity’s effects on the economy, society, and finances were also assessed, and it became clear that the best option for the smart microgrid was determined that would be 325 kW of solar PV, 25 kW of wind turbine, and 600 kW of diesel generators, respectively. Given the current situation, university administrators are urged to participate in distributed generators and adopt cutting-edge designs for energy storage technologies due to the significant environmental and financial benefits.

A new reinforcement learning approach for improving energy trading management for smart microgrids in the internet of things

A new reinforcement learning approach for improving energy trading management for smart microgrids in the internet of things