Smart Home Energy Research Articles

Data Aging Matters: Federated Learning-Based Consumption Prediction in Smart Homes via Age-Based Model Weighting

Smart homes, powered mostly by Internet of Things (IoT) devices, have become very popular nowadays due to their ability to provide a holistic approach towards effective energy management. This is made feasible via the deployment of multiple sensors, which enables predicting energy consumption via machine learning approaches. In this work, we propose FedTime, a novel federated learning approach for predicting smart home consumption which takes into consideration the age of the time series datasets of each client. The proposed method is based on federated averaging but aggregates local models trained on each smart home device to produce a global prediction model via a novel weighting scheme. Each local model contributes more to the global model when the local data are more recent, or penalized when the data are older upon testing for a specific residence (client). The approach was evaluated on a real-world dataset of smart home energy consumption and compared with other machine learning models. The results demonstrate that the proposed method performs similarly or better than other models in terms of prediction error; FedTime achieved a lower mean absolute error of 0.25 compared to FedAvg. The contributions of this work present a novel federated learning approach that takes into consideration the age of the datasets that belong to the clients, experimenting with a publicly available dataset on grid import consumption prediction, while comparing with centralized and decentralized baselines, without the need for data centralization, which is a privacy concern for many households.

A PROTOTYPE DESIGN OF A DEDICATED SMART HOME ENERGY MANAGEMENT SYSTEM

<em>With the continuous rise of electrical energy costs for heating, cooling, and ventilation and the increasing number of energy-consuming home appliances, designing a cost-effective efficient residential electric energy management system has become crucial. This paper presents a prototype simulated design of a Smart Home Energy Management System (SHEMS), dedicated to the management of residential electrical energy according to the user-preassigned comfort requirements and cost criteria. All planted sensors and home appliances are controlled by one master microcontroller. The Proteus Software ISIS was used for all simulation results. The proposed application collects information from sensors to control the required home appliances by switching them ON or OFF based on a specified design algorithm. The sensors' assigned values and home appliance status are stored in a main database. The proposed design also allows home appliances to be monitored and controlled remotely via the Internet. Simulated results are given for a two-room residential home</em>.

Smart home energy management with mitigation of power profile uncertainties and model errors

The paper proposes a two-stage home energy management system accounting for optimal energy dispatch, power profiles predictability, and building thermal behaviour. The first look-ahead stage aims at minimizing the energy exchanges with the upstream grid based on load and weather predictions. The second step adapts the controls in real-time in order to mitigate forecast errors while remaining as close as possible to the look-ahead commitments. The originality of the paper lies on the use of different granularities of the building models. Especially, this allows to account for the approximations in the system equations embedded in the predictive controllers. Furthermore, a real-time tuning of those model equations is performed based on the deviations observed on the state variables – errors between controller predictions and measurements. Ultimately the proposed approach allows to cope with two generic drawback of traditional model predictive control: i) environment forecast errors and ii) models approximations. Several simulations are carried out to under different weather conditions, demonstrating an average energy exchange reduction of at least 25% and better system predictability. The work is completed with sensitivities analysis of the controller settings, the system parameters and the quality of weather/load forecasts.

Enhancing smart home energy efficiency through accurate load prediction using deep convolutional neural networks

Enhancing smart home energy efficiency through accurate load prediction using deep convolutional neural networks

Coordinated smart home energy sharing with a centralized neighbourhood energy management

This paper presents a centralized neighbourhood energy management with coordinated smart home energy-sharing model for neighbourhood smart homes, which are integrated with in-house renewable energy resources and energy storage systems. The main aim of this neighbourhood energy management model is to minimize the aggregated electricity bill of all smart home consumers in the neighbourhood area by increasing the utilization of local renewable energy generation. The effective combination of time of use pricing, feed-in-tariff scheme and fixed incentive method is considered in this model to encourage the more electricity transactions among the neighbourhood smart homes. A group of ten smart homes with different level of renewable energy integration and load profiles is considered as a test system to determine the performance of the proposed neighbourhood smart home energy management model. The simulation results show that the centralized neighbourhood coordinated smart home energy management model can provide significant economic benefits to all smart home consumers in the neighbourhood area, when compared to the without neighbourhood power-sharing case. From the results, it is noted that all smart homes together get 56.23% of cost savings in a day with the proposed model when compared to the baseline model. Finally, an economic analysis has also done in this paper to investigate the capital investment benefits of all smart home consumers in neighbourhood area. From the economic analysis, it is clearly noticed that with the proposed model the annual profits of all smart homes (SHs) in the neighbourhood area are improved by 54.48% for SH1, 59.88% for SH2, 85.03% for SH3, 41.55% for SH4, 30.68% for SH5, and 34.70% for SH6 respectively when compared to without neighbourhood energy sharing concept.

A multi-agent model of urban microgrids: Assessing the effects of energy-market shocks using real-world data

The shift towards renewable energy sources (RES) in energy systems is becoming increasingly important. Residential energy generation and storage assets, smart home energy management systems, and peer-to-peer (P2P) electricity trading in microgrids can help integrate and balance decentralized renewable electricity supply with an increasingly electrified power, heat, and transport demand, reducing costs and CO2 emissions. However, these microgrids are difficult to model because they consist of autonomous and interacting entities, leading to emergent phenomena and a high degree of complexity. Agent-based modeling is an established technique to simulate the complexity of microgrids. However, the existing literature still lacks real-world implementation studies and, as a first step, models capable of validating the existing results with real-world data. To this end, we present an agent-based model and analyze the corresponding microgrid performance with real-world data. The model quantifies economic, technical, and environmental metrics to simulate microgrid performance holistically and, in line with state-of-the-art research, consists of self-interested, autonomous agents with specific load profiles, RES generation, and demand-response potential. The model can simulate a P2P marketplace where electricity is traded between agents. In the second part of the paper, we validate the model with data from a medium-sized German city. In this case study, we also compare microgrid performance in 2022, during the energy market crisis in Europe, with historical data from 2019 to assess the effects of energy market shocks. Our results show how microgrids with P2P trading can reduce electricity costs and CO2 emissions. However, our trading mechanism illustrates that the benefits of energy-community trading are almost exclusively shared among prosumers, highlighting the need to consider distributional issues when implementing P2P trading.

Design and Implementation of Smart Energy Management System

It is crucial to create systems that lessen our reliance on non-renewable resources in a world with declining energy reserves and escalating economic crises. Smart Home Energy Management Systems, which employ smart switches to actively monitor energy use by each load, available power, and other parameters to transition between renewable resources and the primary power grid, are becoming more and more popular. The results of several methodologies were combined and analysed after a thorough literature review. The approach described is a synthesis of all the most well-liked approaches. The suggested methodology aims to implement demand response management simultaneously on grid electricity and solar power. The issue was divided into two scheduling scenarios: one assuming only solar power is available, the other assuming just grid power. In order to use the resources available as effectively as possible, the two halves are then combined.

Renewable energy management in smart home environment via forecast embedded scheduling based on Recurrent Trend Predictive Neural Network

Smart home energy management systems help the distribution grid operate more efficiently and reliably, and enable effective penetration of distributed renewable energy sources. These systems rely on robust forecasting, optimization, and control/scheduling algorithms that can handle the uncertain nature of demand and renewable generation. This paper proposes an advanced ML algorithm, called Recurrent Trend Predictive Neural Network based Forecast Embedded Scheduling (rTPNN-FES), to provide efficient residential demand control. rTPNN-FES is a novel neural network architecture that simultaneously forecasts renewable energy generation and schedules household appliances. By its embedded structure, rTPNN-FES eliminates the utilization of separate algorithms for forecasting and scheduling and generates a schedule that is robust against forecasting errors. This paper also evaluates the performance of the proposed algorithm for an IoT-enabled smart home. The evaluation results reveal that rTPNN-FES provides near-optimal scheduling 37.5 times faster than the optimization while outperforming state-of-the-art forecasting techniques.

Lens-oppositional duck pack algorithm based smart home energy management system for demand response in smart grids

Smart grid (SG) is one of the emergent technologies providing effective solutions for increased power demand globally. Due to the advances of Internet of Things (IoT), smart devices are integrated with the smart home (SH) environment which actively participates in electricity market through demand response (DR) programs for energy management. DR refers to the modifications in the electricity utilization of the end user from the common utilization pattern in response to the variation in electricity prices. An effective energy management system (EMS) with price-based DR model is essential for IoT enabled SH environment. In this view, this article develops a Lens-Oppositional Duck Pack Algorithm based Smart Home Energy Management System (LODPA-SMEMS) for DR in SGs. The major focus of the LODPA-SMEMS model is to achieve optimal management of energy usage by scheduling process. The LODPA is derived by the incorporation of lens-oppositional based learning (LOBL) with conventional DPA. The LODPA-SMEMS model is mainly derived to reduce peak-to-average ratio (PAR) and electricity price with maximum user comfort (UC). The experimental outcome of the LODPA-SMEMS model outperforms the other methods under several aspects. The results reported that the LODPA-SMEMS model improves overall energy usage and consequently, the sustainability of IoT enabled SH gets enhanced. According to the findings, the LODPA-SMEMS model increases overall energy efficiency, hence increasing the sustainability of IoT-enabled SH. The experimental values demonstrated that the LODPA-SMEMS model has accomplished lower PAPR of 2.10 whereas GA, BPSO, GWDO, GBPSO, and WBFA models have attained higher PAPR of 3.70, 3.10, 3.80, 3.60, and 2.40 respectively. Also, EEC analysis of LODPA-SMEMS on DAPS, RTPS, TUPS: 3.53kWh, 1.81kWh, 1.85kWh. Similarly, LODPA-SMEMS model has achieved superior performance with least ET of 68 s.

“It's never telling me that I'm good!” Household experiences of testing a smart home energy management system with a personal threshold on energy use in Sweden

Although smart technologies are widely promoted as enabling flexibility in households' energy demand, they often fail to achieve substantial impact. How smart technologies are actually used and to what extent they enable changes of energy-reliant practices in everyday life therefore needs to be better understood. This paper evaluates a smart home energy management system, Ero 2.0, which was tested by households in a multi-residential building in Sweden. To our knowledge, apart from its forerunner, Ero 2.0 is the first of its kind to include a personal threshold on energy use varying with the availability of preferred energy sources. Semi-structured interviews were conducted with 15 participants, complemented by pre and post surveys, answered by 39 and 32 participants respectively. Overall, Ero 2.0 contributed to raised awareness regarding electricity and water use. To some extent, it also contributed to changes in practices, mainly through changed or reduced use of certain functions. However, it was less effective in enabling shifting practices in time. Difficulties to change practices were found to depend on: (1) lack of flexibility in everyday life, (2) limitations in size and layout of the dwelling, (3) lack of incentives and perceived impact, (4) lack of guidance and (5) lack of possibilities to control devices through the interface. The second point is an aspect that to date has received little attention in smart energy research. Design opportunities for future smart home energy management systems are discussed while acknowledging that such technologies cannot alone achieve the transition to more sustainable energy systems.

A Transfer Reinforcement Learning Framework for Smart Home Energy Management Systems

Transfer learning (TL) is widely used as a solution to overcome the huge amount of time required to train a deep learning model. However, a number of challenges are associated with transferring the knowledge between the same and different target domains (TDs), for instance, designing efficient mapping functions, correlating the source and target datasets, identifying necessary parameters for enabling TL, and so on. In this article, we, therefore, present a solution to enable TL for home energy management systems (HEMSs) in smart homes consisting of multiple residents and appliances. This led to eliminating the training time and data requirements associated with training home appliances. A mapping function is designed based on correlating the source and target datasets before transferring the knowledge. Furthermore, a training model is designed to iteratively train a source model, i.e., expert home (EH) and expert appliance (EA), with source dataset and feedback knowledge from the target model, i.e., learner home (LH) and leaner appliance (LA). An extensive set of simulations is carried out to evaluate the performance of the proposed scheme. Simulation results show that transferring knowledge in both the same and different domains significantly reduces the energy consumption of individual home appliances and smart homes. In the future, we will expand the research using new models to promote TL effectiveness.

Design of type-2 fuzzy logic controller in a smart home energy management system with a combination of renewable energy and an electric vehicle

Home energy management is one of the most important parts of a smart home that manages the efficient use of energy in the smart home. This paper aims to design two type-2 fuzzy logic controllers in the demand-side energy management system. For this purpose, a combination of renewable energy sources, such as fuel cells, photovoltaic solar panels, vertical axis wind turbines with a helical savonius rotor, and an electric vehicle and energy storage system along with an external grid are utilized to supply the electricity usage of home appliances in a smart home. By using the proposed method, higher quality, more economical, and environmentally friendly energy can be accomplished. To this end, the outputs of the proposed controllers are defined to make appropriate decisions about the generated energy, how to supply energy for own consumption, and controllable loads. The number and distribution of membership functions of type-2 fuzzy logic controllers are selected according to the measured real input data over a year in Tehran, Iran. To demonstrate the effectiveness of the proposed method it is simulated by MATLAB/Simulink software, which indicates that the proposed system causes the smart home to receive 49.186 kWh less electricity energy from the grid to supply daily power for home appliances and therefore can weekly consume approximately 343.95 kWh less electricity energy from the grid. it is shown that after applying the proposed strategy, electricity costs were reduced by 71.5%, and the peak-to-average ratio was reduced by 64.6%.

Development of a Multi-Asset Risk Assessment Algorithm in the Context of Home Energy Management

Risk management has become an important concern in the light of current developments in the home energy management sector as well as within the broader considerations regarding the building sector’s energy production and consumption paradigm. The current multi-parameter energy ecosystem structure raises a number of new challenges that require a reliable and robust risk management framework to assist in building management decision making. This paper presents a multi asset risk assessment algorithm, which is part of a risk management application developed for residential buildings within the framework of energy communities and digital energy markets. It describes the logic, principles, and operation of the algorithm, as well as the functionalities related to risk analysis and result visualization. This underpins the necessary means to monitor elements of a home energy system as well as tools for risk prevention and mitigation. The proposed application provides accurate, detailed, and easy to use information to assist decision makers and stakeholders in the context of smart home energy management systems.

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.

Multi-Objective Energy Management of a Smart Home in Real Time Environment

In home energy management, the occupants schedule the operating appliances to achieve lowest optimal energy cost with minimum discomfort. Smart home energy management turns out to be challenging due to the penetration of rooftop intermittent solar power generations. This article develops a multi-objective and real time smart residential load management and hence energy management topology considering variation in rooftop solar power generation with variation in price of distribution grid energy. Primarily, the optimization problem is established as a time average stochastic optimization formulation and then simplified to mixed integer linear programming (MILP) using Lyapunov optimization. The energy cost minimization objective is added with ocular and thermal discomfort minimization which also lowers the discomfort level for occupants due to actions caused by real time load management. The home loads are managed by an Internet-of-Things (IoT) based controller which also alerts the occupants for any incipient malfunction in the household loads. The proposed control technique is authenticated on a real-life smart residential data with simulations and experiments. The resultant controller can thus optimally control the smart residential loads in real time.

A Smart Home Energy Monitoring System Based on Internet of Things and Inter Planetary File System for Secure Data Sharing

A Smart Home Energy Monitoring System Based on Internet of Things and Inter Planetary File System for Secure Data Sharing

Strategic Peer-to-peer Energy Trading Framework Considering Distribution Network Constraints

With the development of smart home energy management technology, prosumers are endowed with increased initiative in peer-to-peer (P2P) transactions, bringing new potential for cost savings. In this study, a novel strategic P2P energy trading framework is proposed considering the impact of network constraints on personal transaction strategies. Prosumers can estimate the allowed power injection before engaging in the P2P energy trading, which is solved in a distributed manner based on the sharing form alternating direction method of multipliers (ADMM) algorithm. To quantify the network usage cost for each prosumer and promote local transactions among prosumers at the same bus, a modified continuous double auction (CDA) matching algorithm is proposed including a transaction fee. An adaptive aggressiveness-based bidding strategy is generated considering the risk of uncertainty in real-time energy delivery amount under the limitations of the distribution network. The proposed strategic P2P energy trading framework is tested with the IEEE 37-bus distribution network and it is effective in creating profits for prosumers and supporting distribution network operations.

An Innovative Machine Learning Technique for the Prediction of Weather Based Smart Home Energy Consumption

An Innovative Machine Learning Technique for the Prediction of Weather Based Smart Home Energy Consumption

Design and Implementation of a Smart Home Energy Management System Using IoT and Machine Learning

The paper “Design and Implementation of a Smart Home Energy Management System Using IoT and Machine Learning” proposes a system that aims to optimize energy consumption in a smart home environment. The system uses Internet of Things (IoT) devices to collect real-time data on energy usage and machine learning algorithms to predict future consumption patterns. This paper proposes the use of deep neural networks (DNNs) for the design and implementation of a smart home energy management system using IoT and machine learning techniques. The authors demonstrate the effectiveness of the system through experimental results, showing significant energy savings compared to traditional methods. The DNN is built using Keras or Tensor Flow and is trained on extracted features from energy consumption data collected using IoT sensors. The system is implemented with a real-time monitoring system and a user interface for remote access. The proposed system has the potential to save energy and reduce energy costs for households while providing real-time feedback to the user.

Activity and efficiency of the building sector in Morocco: A review of status and measures in Ifrane

<abstract> <p>One-third of all greenhouse gas emissions come from the world's building stock while accounting for 40% of global energy use. There is no way to combat global warming or attain energy independence without addressing the inefficiency of the building sector. This sector is the second consumer of electricity after the industrial sector in Morocco and is ranked third emitter after the energy sector and transportation sector. Using Ifrane as a case study, this paper examines and reviews the city's energy use and the initiatives taken to improve building efficiency. The findings showed that, during the analyzed period, i.e., from 2014 to 2022, Ifrane's annual electricity consumption climbed steadily from 35 to 43 GWh. The government of Morocco has implemented effective laws, guidelines and regulations, as well as publicized ways to reduce energy consumption and increase energy efficiency. However, gathered data and survey results revealed opportunities and challenges for enhancing Ifrane's efficient energy use.</p> <p>The study also evaluates government programs, codes/standards and related actions for the improvement of household energy efficiency. As part of the review, the available literature was analyzed to assess the effectiveness of energy behavior and awareness, the impact of an economical and sustainable building envelope, the impact of building retrofitting programs, the importance of energy-performing devices and appliances, the adoption of smart home energy management systems, the integration of renewable energies for on-site clean energy generation and the role of policies and governance in the building sector in Ifrane. A benchmark evaluation and potential ideas are offered to guide energy policies and improve energy efficiency in Ifrane and other cities within the same climate zone.</p> </abstract>