Smart Home Energy Management Research Articles

Investigation on Optimization Algorithms for Smart Home Energy Management with Different Electricity Pricing

The focus of this paper is on energy consumption optimization in smart homes (with/without RES) and increasing the user comfort level. The paper presents a functional and adaptable home energy management system with RES and an energy storage device for designing and implementing Demand Response (DR) programs. The four meta-heuristic techniques: Genetic Algorithm (GA), Wind-Driven Optimization (WDO), Grey Wolf Optimization (GWO) and Salp Swarm Optimization (SSA), are used to optimize the energy consumption cost for a home energy environment. In the process of identifying and proposing a dedicated home energy optimization algorithm, this paper investigated four optimization algorithms with four different pricing schemes: Time of Use (TOU) pricing, Real-Time Pricing (RTP), Critical Peak Pricing (CPP), and Day-Ahead Pricing (DAP) schemes. The results obtained using these pricing schemes are validated and compared in a common smart home environment. Further, the results show that by integrating Renewable Energy Sources (RES) and a battery reduces the electricity bill by 10.89% (without RES) and 38.88% (with RES), as well as the peak-to-average ratio (PAR) by 59.97% (without RES) and 64.98% (with RES) when compared to the energy consumption cost obtained without-scheduling technique. Moreover, without RES, the SSA algorithm based home energy management system outperforms the other algorithms particularly with the TOU pricing scheme.

Smart Home Energy Visualizer: A Fusion of Data Analytics and Information Visualization

While technology advancements are continuously improving, the energy efficiency of household appliances, energy consumption analysis, and providing feedback to consumers on this analysis remains a critical issue in ensuring the effectiveness of such improvements. Visual feedback is a promising technique for promoting energy conservation by applying demand response (DR) in smart home energy management systems (SHEMSs). In this article, we propose a smart home energy visualization (SHEV) system, an SHEMS that comprises three components: Appliance Profile Detector with XCorrelation (APDX) that monitors the activation of household appliances, operation modes identification using cycles clustering (OMICC) to identify the operation modes used, and the visualizer to represent the appliance usage-related information to the user using concentric circles representation (CCR). This visualization assists the consumer in applying DR by better understanding the appliance usage so that the consumer makes sense of the consumption, and hence, better decision-making in energy conservation.

Design of Type-2 Fuzzy Logic Controller in a Smart Home Energy Management System with a Combination of Renewable Energy and an Electric Vehicle

Design of Type-2 Fuzzy Logic Controller in a Smart Home Energy Management System with a Combination of Renewable Energy and an Electric Vehicle

Mixed Deep Reinforcement Learning Considering Discrete-continuous Hybrid Action Space for Smart Home Energy Management

This paper develops deep reinforcement learning (DRL) algorithms for optimizing the operation of home energy system which consists of photovoltaic (PV) panels, battery energy storage system, and household appliances. Model-free DRL algorithms can efficiently handle the difficulty of energy system modeling and uncertainty of PV generation. However, discrete-continuous hybrid action space of the considered home energy system challenges existing DRL algorithms for either discrete actions or continuous actions. Thus, a mixed deep reinforcement learning (MDRL) algorithm is proposed, which integrates deep Q-learning (DQL) algorithm and deep deterministic policy gradient (DDPG) algorithm. The DQL algorithm deals with discrete actions, while the DDPG algorithm handles continuous actions. The MDRL algorithm learns optimal strategy by trial-and-error interactions with the environment. However, unsafe actions, which violate system constraints, can give rise to great cost. To handle such problem, a safe-MDRL algorithm is further proposed. Simulation studies demonstrate that the proposed MDRL algorithm can efficiently handle the challenge from discrete-continuous hybrid action space for home energy management. The proposed MDRL algorithm reduces the operation cost while maintaining the human thermal comfort by comparing with benchmark algorithms on the test dataset. Moreover, the safe-MDRL algorithm greatly reduces the loss of thermal comfort in the learning stage by the proposed MDRL algorithm.

Prototype of Energy Consumption Monitoring and Energy Theft Detection Based on IoT

Energy management in home is gaining more attention as people try to use sustainable energy sources. This attempt to improve the use of infrastructure for energy production and distribution is expected to include smart grid systems. The incorporation of Internet of Things (IoT)-enabled smart devices into an ecosystem designed for maximum energy efficiency has been proposed for Smart Home Energy Management Systems (SHEMS). Smart homes are expensive, but smart plugs can change normal home devices relatively smart. This paper proposes a prototype design for a SHEMS it monitors and controls the energy consumption of smart devices to reduce the electricity bill and also detect energy theft.

Finite State Machine-Based Load Scheduling Algorithm for Smart Home Energy Management

The problem of scheduling household appliances with the availability of renewable energy is the biggest challenge in the smart home energy management system. The components such as renewable energy resources, household appliances, utility grid, storage batteries are pooled into a nonlinear, time-varying, indefinite, and dynamic structure that is impossible to control and refine. For this, real-time pricing is applied in most nations to withstand the burden on the grid. This requires attention to utilize renewable energy effectively. In this paper, a load scheduling method to schedule the loads based on the availability of solar energy and customer preferences is presented. First, the availability of solar energy is forecasted ahead one day using Regression Analysis. Second, the finite state machine approach-based load scheduling algorithm is implemented and tested using MATLAB Simulink and Lab VIEW. LabVIEW-based GUI is developed to visualize the MATLAB schedule for loads. The problem is divided into several states with the availability of solar power, and if solar power is unavailable, grid power is utilized. The loads preferred by the consumers are scheduled in alignment with the production of solar power with the finite state machine scheduling algorithm. Also, the loads considered are able to consume instantaneous energy with the instantaneous production of energy, thereby reducing CO2 emission by not consuming power from the grid. Finally, the loads are scheduled accordingly, and it is concluded that coordination can be established between energy providers, and the system proposed can flatten out the load profile.

Dynamic and proactive matheuristic for AC/DC hybrid smart home energy operation considering load, energy resources and price uncertainties

This paper addresses the problem of management a residential storage system with distributed generation. With the introduction of a hybrid AC/DC inverter in this system, efficient energy management is realized to achieve the minimization of the cost of the energy balance among purchasing, renewable generation, curtailment and reserve capacity. This cost reduction is achieved by either meeting the load or selling surplus energy, and dispensing a residential demand load controller. To address the dynamic problem and with uncertainties regarding the load, renewable energy, and energy purchase and sale tariffs, a mixed integer linear programming model was developed with adjustable robust programming (ADJ-ROBUST-MILP), and it also involves technical restrictions and criteria for increasing the life cycle of the storage system. The dynamic aspect imparts practical applicability via the permanent correction of the ADJ-ROBUST-MILP solution with a heuristic that acts proactively in the developed dynamics by observing prior conditions. The case studies demonstrate that the mathematical heuristic is able to confer benefit to the energy scheduling of smart home energy management while presenting computational complexity capable of being used in real systems, which is exemplified herein.

Investigation of Smart Home Energy Management System for Demand Response Application

Electricity market reform provides the conditions for demand-side load resources to be incorporated into the supply–demand regulation, and the increase of residential-side electrification level makes residential load resources a high-quality resource for demand response (DR). Resident home appliances participate in the “two-way interaction” of the power grid in the form of DR, which can effectively alleviate the tension of power supply and consume clean energy, to improve the safe and stable operation of the power system. Firstly, this article summarizes the structure and functions of the home energy management system (HEMS). Secondly, it discusses the key technologies of the HEMS, starting from an advanced metering infrastructure (AMI) and DR technology. Finally, it analyzes the control strategies of the HEMS, including component models and various optimal scheduling algorithms, and describes the challenges of the HEMS.

Detecting abnormal electricity usage using unsupervised learning model in unlabeled data

Smart-home systems achieved great popularity in the last decade as they increase the comfort and quality of life. Reduction of energy consumption became a very important desiderate in the context of the explosive technological development of modern society with a major impact on the future development of mankind. Moreover, due to the large amount of data available from smart meters installed in households. It makes leverage to able to find data abnormalities for better monitoring and forecasting. Detecting data anomalies helps in making a better decision for reducing energy usage wasted. In recent years, machine learning models are widely used for developing intelligent systems. Currently, researchers’ main focus is on developing supervised learning models for predicting anomalies. However, there are challenges to train models with unlabeled data indicating data anomaly or not. In this paper, abnormalities are detected in electricity usage using unsupervised learning and evaluated using Excess Mass. The unsupervised anomaly detection model is based on Gaussian Mixture Model (GMM) and Isolation Forest (iForest). The models are compared with Local Outlier Factor (LOF) and One-class support vector machine (OCSVM). The proposed framework is tested with actual electricity usage and temperature data obtained from Numenta Anomaly Benchmark (NAB), which contains normal and anomaly data in time series. Finally, it has been observed that the iForest out-performed as the detection model for the selected use case. The outcome showed that the iForest can quickly detect anomalies in electricity usage data with only a sequence of data without feature extraction. The proposed model is suitable for the Smart Home Energy Management System's practical requirement and can be implemented in various houses independently. The proposed system can also be extended with the various use cases having similar data types.

Design and implementation of smart home energy management systems using green energy

Design and implementation of smart home energy management systems using green energy

Design and implementation of a smart metering infrastructure for low voltage microgrids

The distributed generation (DG) and the integration of renewable energy sources (RESs) have leveraged the improvement of the smart grid for a few decades. The smart home energy management systems (HEMSs) have also attracted attention in increasing the use of information and communication technologies in the context of smart grid applications. This paper proposes a smart metering infrastructure with DC and AC analog front ends (AFEs), wired and wireless communication interfaces, and remote monitoring software coded in Visual C#. The implemented metering device has been comprised of isolated measurement transducers for detecting the current and voltage rates of sources and various types of loads either in a microgrid or smart home application. The signal conditioning tier has been comprised of highly accurate and sensitive operational amplifiers, and signal processing has been accomplished by a PIC microcontroller which is capable to interface USB and ZigBee based wireless communication protocols. The processed measurement data have been transmitted with wireless communication, and a graphical user interface (GUI) software has been coded at the receiving end host computer. The measurement case studies have been experimentally performed in microgrid and HEMS infrastructures to validate the accuracy of the proposed smart metering device and software operated at the host computer.

Intelligent energy management: Evolving developments, current challenges, and research directions for sustainable future

In the last decade, there have been significant developments in the field of intelligent energy management systems (IEMSs), with various methods and new solutions proposed for managing the energy resources intelligently. An important issue related to finding the desired outcomes remains unexplored, i.e., how to determine key insights from the sparse academic literature in the age of digital publishing. To mitigate the issue, this study proposes a novel strategy to systematically survey the relevant studies by converting the sparse literature into visual presentations. We first apply a systematic approach called a PRISMA (Preferred Reporting Items for Systematic reviews and Meta-analyses) statement to provide the insights from the published literature of the past decade (2010–2020). Then, VOSviewer experiments are conducted to transform these sparse scholarly data into visual representations. In total, eighty-one papers published in high-impact journals are identified based on their scientific soundness and relevance, and a VOSviewer analysis is applied. The analysis revealed the existence of three research clusters focused on the following main thematic areas: the energy management in smart homes and smart grids (35 journal papers); the emerging concept of context-awareness (26 journal papers); and the role of privacy preservation in IEMSs (20 journal papers). This analysis uncovers the current state of IEMSs and explores existing issues, methods, findings, and gaps. Thus, future research directions have been recommended to fill the existing gaps. This systematic literature review is to assist both researchers and industry practitioners to understand the research gaps of previous studies.

An integrated smart home energy management model based on a pyramid taxonomy for residential houses with photovoltaic-battery systems

Smart home energy management (SHEM) with residential photovoltaic (PV)-battery systems is a complicated issue with different facets. An integrated SHEM model covering the essential functions is missing. Meanwhile, residential PV-battery systems' optimal operations with renewable energy exchanges and imperfect forecasts are still open challenges. In this study, the research activities in SHEM are firstly organized by a pyramid with four functional layers: (i) Monitoring; (ii) Analyzing and forecasting; (iii) Scheduling; and (iv) Coordinating, which can serve as a standard pathway for developing SHEM. Second, guided by the pyramid taxonomy, an integrated SHEM model is developed for residential houses with PV-battery systems. Assuming a perfect Monitoring layer, we obtain the probabilistic load/PV forecasts and user preference vectors of shiftable appliances based on historical data. Then, we develop a two-stage stochastic programming model for optimal scheduling of single houses with a grid-connected PV-battery system, incorporating the probabilistic forecasts and user preference vectors. A retail electricity market with day-ahead (DA) and real-time (RT) markets is employed for leveraging imperfect forecasts. Finally, we design a distributed coordinating algorithm - Asynchronous Scheduling and Iterative Pricing for PV power-sharing among multiple prosumers based on the single-house scheduling model. Numerical simulations based on realistic loads and PV generation data validated the two-stage stochastic programming model's economic superiority and the distributed PV power-sharing approach compared with the rule-based dispatching and selfish scheduling strategies. We concluded that 1) the modeling of load/PV forecast uncertainties is valuable than averaging or ignoring them, 2) the two-stage stochastic programming model and the DA-RT retail electricity market are beneficial for utilizing imperfect forecasts, and 3) coordinating multiple prosumers could benefit each household by sharing PV and battery investments for revenue or trading with local small prosumers for cost reductions.

Enhanced System Architecture for Smart Home Energy Management System Using Knapsack Algorithm with Integration of Solar Photovoltaic Energy Source

Enhanced System Architecture for Smart Home Energy Management System Using Knapsack Algorithm with Integration of Solar Photovoltaic Energy Source

Optimal two-level active and reactive energy management of residential appliances in smart homes

The optimal performance of the smart home energy management system (SHEMS) in coordinating and integrating the equipment in the house plays a significant role in increasing the efficiency and economic benefits of the smart home. This paper proposes a two-level optimization algorithm for the energy management of residential appliances within a smart home, including interruptible, uninterruptible, thermostatically controlled, and non-schedulable loads, as well as the charging/discharging strategies of electric vehicles (EVs) and energy storage systems (ESSs) in the presence of distributed energy resources (DERs). In the first level of optimization, to minimize the cost of electricity, the operating time of smart home components is determined by SHEMS, and active power is exchanged between equipment. At this level, the impact of demand response (DR) constraints on the cost and load factor (LF) of the smart home have also been investigated. In the second level, considering the optimal cost obtained in the first level, in addition to the active power, the reactive power required by loads is also provided by using the additional capacity of EV and ESS inverters and improves the power factor (PF) of the house at the connection point to the grid. Day-ahead electricity costs are calculated depending on different pricing signals (TOU, RTP) with the power exchange capacity (buying/ selling) with the grid. The effectiveness of the proposed strategy is examined on a typical smart home over a 24-h. By reviewing the numerical results obtained for the cost and the LF in different scenarios, and observing the increase of the PF of home from 0.65 to 0.94 and also examining the performance of the equipment during the planning time, the efficiency of the model is proved.

Cyber security framework for smart home energy management systems

Smart homes provide reliable automation control over different applications and appliances that are connected through intelligent networks. The concern of energy management is improved by providing connected and one-touch services with energy systems knowledge. External and internal attacks over the energy management systems degrade its performance by energy exploitations or increasing energy demands. This paper proposes an online security framework (OSF) for smart energy management systems (EMS). The proposed framework is responsible for monitoring EMS operations and mitigating security threats at different time intervals. The proposed OSF Monitoring aims to inform consumers of their use pattern, which uses energy Monitoring systems to store, analyze, and subsequently provide the systems to the service provider with valuable information. For this purpose, the proposed framework monitors the variations in energy distribution and consumption based on the routine factor. It then determines the variations based on the appliances/applications’ functional requirements using differential predictive learning. The OSF-based predictive learning performance monitoring is used to detect early faults, improve productivity, minimize downtime, and reduce energy costs. This helps align the distribution and consumption factors for different appliances to identify the fluctuating threats through fore-hand predictions. The entire process is administered using a centralized cybersecurity system coupled with the EMS. The proposed framework’s performance is verified using the metrics energy efficiency, distribution interruption, failures, and detection rate.

A Prosumer Model Based on Smart Home Energy Management and Forecasting Techniques

This work presents an optimization framework based on mixed-integer programming techniques for a smart home’s optimal energy management. In particular, through a cost-minimization objective function, the developed approach determines the optimal day-ahead energy scheduling of all load types that can be either inelastic or can take part in demand response programs and the charging/discharging programs of an electric vehicle and energy storage. The underlying energy system can also interact with the power grid, exchanging electricity through sales and purchases. The smart home’s energy system also incorporates renewable energy sources in the form of wind and solar power, which generate electrical energy that can be either directly consumed for the home’s requirements, directed to the batteries for charging needs (storage, electric vehicles), or sold back to the power grid for acquiring revenues. Three short-term forecasting processes are implemented for real-time prices, photovoltaics, and wind generation. The forecasting model is built on the hybrid combination of the K-medoids algorithm and Elman neural network. K-medoids performs clustering of the training set and is used for input selection. The forecasting is held via the neural network. The results indicate that different renewables’ availability highly influences the optimal demand allocation, renewables-based energy allocation, and the charging–discharging cycle of the energy storage and electric vehicle.

Improved residential energy management system using priority double deep Q-learning

In the current era, electricity demand has skyrocketed. Power grids have to face a lot of uneven power demand daily. During a certain period in a day, the power demand peaks, making it difficult for the grid to meet the demand. To deal with this problem, an intelligent Home Energy Management (HEM) can be beneficial. Smart HEM systems can schedule loads from peak to low peak hours. Thereby reducing peak load on the grid as well as reducing decreasing the costs incurred by a user. In this paper, we proposed a Deep Reinforcement Learning model with prioritized experience sampling (PQDN-DR) for appropriate demand response, and the problem of load shifting is simulated as a game. We also propose a novel reward system for better convergence of the DRL model to near-optimal strategies and a DR adapted Epsilon Greedy Policy to guide the agent in exploration phase for faster convergence. The proposed system minimizes power demand peak and consumers’ bills simultaneously. The proposed method has successfully reduced the peak load and peak costs in smaller DR environment. The agent reduced costs and overall variance of the load profile for all customers for 24 h in the standard DR environment.

Smart Home Energy Management Systems in Internet of Things networks for green cities demands and services

Today, 44% of global energy has been derived from fossil fuel, which currently poses a threat to inhabitants and well-being of the environment. In a recent investigation of the global demand for energy consumption across various energy consumption sectors, the building sector has been shown to be one of the primary energy consumers, with a high percentage of energy consumption deemed as unnecessary. This as a result of poor management practice and implementation of strategies to avoid excess energy consumption. Over the years, researchers in both academia and industries have focused on various techniques to deal with unnecessary energy consumption and ensuring a healthy living environment for green smart cities. Among these techniques is Smart Home Energy Management Systems (SHEMs), which transform electric home appliances, sensor nodes, into autonomous devices in order to manage energy consumption effectively. This study presents an analysis of smart home energy management system with the goal to identify current trends and challenges for future improvement. The result reveals lack of quality attributes such as security, privacy, scalability, interoperability, and difficulty in managing and adapt to the thermal comfort satisfaction of residents, exposing them to health risks. Lastly, the study described opportunities for future research that ensure energy-efficient smart homes free of unnecessary energy consumption, health challenges, and cyber security attacks. • In this work, we study Smart Home Energy Management Systems. • Researchers have focused on how to deal with unnecessary energy consumption. • This study explores the top 10 SHEMs available in the market today. • The result reveals a lack of quality attributes such as security and privacy. • This study review analysis on smart home energy management.

A new fuzzy logic based approach for optimal household appliance scheduling based on electricity price and load consumption prediction

ABSTRACT Smart Home Energy Management Systems (HEMS) constitute a vital necessity for optimizing electricity usage and saving energy in smart grids. However, these systems rely on dynamic factors that are stochastic and difficult to predict, such as the load consumption and electricity prices. Therefore, constructing an efficient control system for residential buildings requires an accurate prediction process of the associated parameters. This paper proposes an integrated predictive control system that consists of both predictive model and Demand Response (DR) scheme to predict and control the daily electricity usage in the residential sector. First, a Long Short-Term Memory-based (LSTM) optimized predictive model is implemented for predicting both the hourly load consumption and electricity price for a typical smart home. Then, the predicted data are transmitted to a DR fuzzy logic-based controller that can optimally schedule the home appliances usage. In comparison with the state-of-the-art prediction techniques for the residential load consumption and electricity price, the proposed LSTM predictive model outperforms Linear Regression (LR), Decision Tree (DT), Support Vector Regression (SVR), and Ensembled Boosted Trees (EBT). Moreover, the proposed DR-FIS controller has shown good results in terms of reducing the electricity cost by selecting the optimal time schedule.