Search

This paper addresses the problem of accurate and interpretable prediction of energy consumption in residential buildings. The solution that we propose in this work employs the knowledge discovery machine learning approach combining fuzzy systems with evolutionary optimization. The contribution of this work is twofold, including both methodology and experimental investigations. As far as methodological contribution is concerned, in this paper, we present an original designing procedure of fuzzy rule-based prediction systems (FRBPSs) for accurate and transparent energy consumption prediction in residential buildings. The proposed FRBPSs are characterized by a genetically optimized accuracy–interpretability trade-off. The trade-off optimization is carried out by means of multi-objective evolutionary optimization algorithms—in particular, by our generalization of the well-known strength Pareto evolutionary algorithm 2 (SPEA2). The proposed FRBPSs' designing procedure is our original extension and generalization (for regression problems operating on continuous outputs) of an approach to designing fuzzy rule-based classifiers (FRBCs) we developed earlier and published in 2020 in this journal. FRBCs operate on discrete outputs, i.e., class labels. The experimental contribution of this work includes designing the collection of FRBPSs for residential building energy consumption prediction using the data set published in 2024 and available from Kaggle Database Repository. Moreover, the comparison with 20 available alternative approaches is carried out, demonstrating that our approach significantly outperforms alternative methods in terms of interpretability and transparency of the energy consumption predictions made while remaining comparable or slightly superior in terms of the accuracy of those predictions. [ABSTRACT FROM AUTHOR]

The paper explores the performance of a sub-slab ground heat exchanger, coupled to a heat pump, and the ability of the system to provide space conditioning and domestic hot water (DHW) for a multi-unit residential building (MURB) located in Ottawa, Ontario. The parametric analysis conducted to optimize the design of the building, as well as the sensitivity analysis performed to optimize the configuration of the sub-slab ground heat exchanger is also presented. According to the simulated results, the ground layer can store some of the rejected energy over medium term, without reducing the long-term performance of the heat pump. The annual energy consumption per dwelling unit (including heat pump, all auxiliary equipment, appliances, and lights) was estimated to be 28.4 GJ, significantly lower than the average annual energy consumption for a low-rise apartment in Canada (46.7 GJ per apartment). To assess the sensitivity of the system to environmental conditions, the simulation was conducted using the weather files for other five locations in Canada. [ABSTRACT FROM AUTHOR]

Behind the meter (BTM) distributed energy resources (DERs), such as photovoltaic (PV) systems, battery energy storage systems (BESSs), and electric vehicle (EV) charging infrastructures, have experienced significant growth in residential locations. Accurate load forecasting is crucial for the efficient operation and management of these resources. This paper presents a comprehensive survey of the state-of-the-art technologies and models employed in the load forecasting process of BTM DERs in recent years. The review covers a wide range of models, from traditional approaches to machine learning (ML) algorithms, discussing their applicability. A rigorous validation process is essential to ensure the model's precision and reliability. Cross-validation techniques can be utilized to reduce overfitting risks, while using multiple evaluation metrics offers a comprehensive assessment of the model's predictive capabilities. Comparing the model's predictions with real-world data helps identify areas for improvement and further refinement. Additionally, the U.S. Energy Information Administration (EIA) has recently announced its plan to collect electricity consumption data from identified U.S.-based crypto mining companies, which can exhibit abnormal energy consumption patterns due to rapid fluctuations. Hence, some real-world case studies have been presented that focus on irregular energy consumption patterns in residential buildings equipped with BTM DERs. These abnormal activities underscore the importance of implementing robust anomaly detection techniques to identify and address such deviations from typical energy usage profiles. Thus, our proposed framework, presented in residential buildings equipped with BTM DERs, considering smart meters (SMs). Finally, a thorough exploration of potential challenges and emerging models based on artificial intelligence (AI) and large language models (LLMs) is suggested as a promising approach. [ABSTRACT FROM AUTHOR]

The evolution of the smart grid has enabled residential users to manage the ever-growing energy demand in an efficient manner. The smart grid plays an important role in managing this huge energy demand of residential households. A home energy management system enhances the efficiency of the energy infrastructure of smart homes and provides an opportunity for residential users to optimize their energy consumption. Smart homes contribute significantly to reducing electricity consumption costs by scheduling domestic appliances effectively. This residential appliance scheduling problem is the motivation to find an optimal appliance schedule for users that could balance the load profile of the home and helps in minimizing electricity cost (EC) and peak-to-average ratio (PAR). In this paper, we have focused on appliance scheduling on the consumer side. Two novel home energy management models are proposed using multiple scheduling options. The residential appliance scheduling problem is formulated using the multiple knapsack technique. Serial and parallel scheduling algorithms of home appliances namely MKSI (Multiple knapsacks with serial implementation) and MKPI (Multiple knapsacks with parallel implementation) are proposed to reduce electricity cost and PAR. Price-based demand response techniques are incorporated to shift appliances from peak hours to off-peak hours to optimize energy consumption. The proposed algorithms are tested on real-time datasets and evaluated based on time of use pricing tariff and critical peak pricing. The performance of both the algorithms is compared with the unscheduled scenario and existing algorithm. Simulations show that both proposed algorithms are efficient methods for home energy management to minimize PAR and electricity bills of consumers. The proposed MKSI algorithm achieves cost reduction of 20.26% and 42.53% for TOU and CPP, respectively as compared to the unscheduled scenario while PAR is reduced by 45.07% and 39.51% for TOU and CPP, respectively. The proposed MKPI algorithm achieves 22.33% and 46.36% cost reduction compared to the unscheduled case for TOU and CPP while the PAR ratio is reduced by 46.47% and 41.16% for TOU and CPP respectively. [ABSTRACT FROM AUTHOR]

Due to different and frequently competing goals, managing multiple energy carriers in residential buildings in a coordinated manner is one of the key obstacles to the optimal operation of smart cities. This paper offers a novel conceptual cost-based scheme for optimal energy-gas use in a smart home in the context of residential energy hubs in response to this challenge, considering a significant trade-off between cost reduction and environmental conservation. The suggested model takes into account a variety of energy conversion resources, including energy and heat storage systems, rooftop photovoltaic modules, combined heat and power units, as well as responsible electrical and thermal loads. In addition, an effective stochastic scenario-based approach is used to address the significant uncertainty related to photovoltaic production. By incorporating a weighted summation mixed objective function under various system constraints and user preferences, the suggested framework lowers domestic energy consumption and utility costs while also providing the resident with optimal task scheduling and comfort, which can ensure a high quality of life. The suggested scheme is tested on a real-world case study with energy hubs, and as anticipated, it introduces its applicability and effectiveness in the proposed residential energy hub problem's optimal energy management. The simulation results show that it is possible to reduce energy procurement costs by up to 47.86% and emissions costs by up to 31.29% while still providing the desired level of comfort for the households. [ABSTRACT FROM AUTHOR]

In this article, multitrial vector-based differential evolution algorithm (MTDE) is proposed as energy and cost management controller under Time of Use (TOU) tariff in grid associated domestic PV-wind power system tied with battery storages. To enrich the energy efficiency of a proposed power system, two optimisation algorithms are proposed in the scheduling operation. TOU billing is a cost- reflective power pricing strategy that has been found as an effective way to reduce peak energy consumption in the residential segment everywhere the world, mainly in industrialised nations. In the optimisation maximizing the cost benefit of the household energy is taken as the objective and the dispatching ratio of electricity sold to the grid and used locally is treated as the optimisation variable. Using MATLAB, the performance of proposed MTDE in the aspect of daily cost benefit and revenue growth rate are presented with the comparative analysis of gravitational search algorithm and conventional self-made for self-consumed and rest for sale (SFC&RFS) mode-based energy management controller. In comparison to the SFC&RFS mode, the GSA-based cost optimization offers a 21.46% increase in revenue growth, while it is improved to 38.7% using proposed MTDE algorithm. The paper also addresses the significance of fuzzy logic based maximum power point tracking (MPPT) of solar PV in enhancing the energy management of the proposed system. The prototype of fuzzy logic MPPT for 10 W solar panel is presented and the tracked maximum power is visualized using Thingspeak IoT cloud server. The tracking speed of the MPPT can be increased by introducing machine learning algorithms at the cost of memory and complexity. In this article, the linear regression-based machine learning algorithm is implemented in the hardware prototype by utilizing the dataset aggregated from fuzzy MPPT and hence the proposed MPPT inherits the characteristics of the fuzzy MPPT with increased tracking speed. Around 75 % data are used for training, 25% of data are used to test the model and it is observed that the root mean square error (rmse) is 5.1334 and mean square error is 26.3521 and the model is utilized as MPPT for the real-time inputs. [ABSTRACT FROM AUTHOR]

Accurately predicting residential solar energy consumption is crucial for efficient electricity production, supply, and power dispatch. However, conventional forecasting methods often struggle to handle complex energy consumption data. In response to this challenge, this study develops a pioneering two-stage error-corrected combined forecasting model that integrates traditional linear methods, seasonal processing techniques, deep learning models, and intelligent optimization algorithms to outperform other combined forecasting methods in terms of performance. This research analyzes the combined weight values, shedding light on why the proposed model consistently outperforms its counterparts. To confirm its superiority, the proposed model and five benchmark models are rigorously tested in this paper using four evaluation metrics and a hypothesis testing method. The empirical results show that the proposed combined model performs well in terms of accuracy and stability. Notably, the average absolute percentage error of its 24-step ahead prediction is 2.9053 %, which outperforms all comparative models, both single and combined model. These results fully illustrate the advantages of the combined model and reaffirm the excellence of its prediction performance in predicting energy consumption. • A novel forecasting combined model is proposed for solar energy consumption. • The proposed combined model outperforms the five benchmark models. • The interpretation of combination weight in the combined model is elaborated. • Four experiments, hypothesis test and multi-step prediction are performed. [ABSTRACT FROM AUTHOR]

• Novel layout to be easily adopted by existing residential districts. • The novel layout can reduce the primary energy consumption of the residential district. • A primary energy saving index of 38 % and payback period of 2.2 years is achieved. • Power to heat strategy increases the district self-consumed electricity by 15%. • The power to heat strategy is able to further exploit the excess renewable electricity. This paper aims at reducing both electricity and space heating demands of residential districts. It specifically investigates the emerging paradigm, based on renewable energy communities, for existing residential districts. In particular, a novel renewable energy community layout is analyzed. This layout integrates a district heating network and the power to heat control strategy. The proposed system is designed to prevent any major refurbishment inside the apartments, using the existing high temperature space heating system. This arrangement is compared with more conventional renewable energy community layouts. Detailed dynamic models for both the residential district and the proposed layouts are developed using the TRNSYS software. Results show that renewable energy community is an extremely profitable paradigm for promoting the use of renewables at residential buildings scale. Moreover, the layout integrating energy community, district heating network, and Power-to-Heat strategy achieves the best results with a payback period of 2.2 years and a primary energy saving of 38 %. [ABSTRACT FROM AUTHOR]

In a context of massive renovation of residential buildings, stakeholders need decision-support models based on knowledge of the current building stock and accurate simulation of energy demand. This paper presents a new strategy for reducing energy consumption in the building sector, a key factor in combating climate change and promoting sustainability. We introduce an approach to (1) plan retrofits at community level, with a building resolution, for different years of an optimization period and (2) assist local authorities in selecting effective measures to improve the environmental performance of their building stock. The focus is on creating trajectory retrofit plans creation for a building stock with three main retrofit options: improving insulation, heating systems and hot water systems. We adapt a complex but linear approach, a type of problem-solving structure known as a multidimensional multiple-choice knapsack problem, which manages to handle a large number of possible retrofit combinations without becoming unwieldy. The planning process is streamlined as a single-objective optimization task that aims to reduce the total cost of retrofits by reducing their net present value. The efficiency of the model is demonstrated by simulating retrofit scenarios for 4,000 buildings in a French region to prove its ability to tackle large problems. France's targets for decarbonizing the residential sector are taken into account, with a target of reducing GHG emissions by a factor of 10 and a building stock consuming 80kWhEP/m2/year. The results show that these plans are feasible, but that they will require 50% of all buildings to undergo major renovation with abatement costs of around €200/tGES. Our practical application to an actual community demonstrates the model's ability to identify appropriate retrofitting measures and compile building data. • Development of an energy optimization framework integrating a linear simulation model. • Multi-stage optimization generalizing the knapsack problem for building renovation dynamics. • Bridging the gap in energy retrofit strategies by comparing decision-maker and model proposals. [ABSTRACT FROM AUTHOR]

Lack of capital hindered the development of agricultural production and the residential energy consumption transition in rural areas, but, with the continuous advancement of digital finance technologies, rural digital credit eased the liquidity constraint of agricultural production, which influenced residential energy consumption. However, few studies explored the relationship between rural digital credit and residential energy consumption. Hence, the instrumental variable (IV) method, the mediation effect model and the survey data that covered 295 effective samples were used to analyze the impact of rural digital credit on residential energy consumption from the agricultural production perspective in this study. The results indicated that rural digital credit resulted in a significant decline of the consumption of traditional energy products, but impacts of rural digital credit on electricity consumption and the new-style energy products consumption were not significant. Further, rural digital credit reduced traditional energy products consumption via boosting the level of agricultural mechanization and the adoption of precision fertilizer applying technique. This paper was conducive to not only developing the green credit markets in rural areas, but also enhancing the residential energy consumption transition and sustainable development. • Digital credit resulted in a significant decline of the consumption of traditional energy products. • Impacts of digital credit on electricity consumption and the new-style energy products consumption were not significant. • Digital credit reduced traditional energy products consumption via boosting agricultural mechanization. • Digital credit reduced traditional energy products consumption by adopting precision fertilizer applying technique. [ABSTRACT FROM AUTHOR]

Variable Refrigerant Flow (VRF) systems are becoming increasingly popular in commercial and residential buildings due to their flexibility and efficiency. Building design and operational parameters play an important role in the process of predicting cooling loads, and these variables contain a variety of uncertainties that must be taken into account when seeking to obtain a reliable prediction. It is common practice to oversize the Heating, Ventilation, and Air Conditioning (HVAC) system installed in a building in order to reduce uncertainties in its performance. However, oversizing is undesirable due to additional capital and operating costs, inefficient space utilization, and excessive emissions of greenhouse gases. This study provided a comprehensive literature review on previous uncertainly analysis studies from six perspectives: classification of uncertainty factors, sensitivity analysis methods, building energy model for uncertainty analysis, sampling method, the most effective parameter, and distribution of uncertainty parameters., and then developed a framework to investigate the effects of uncertainty of operational and design parameters on annual cooling load, total energy consumption, HVAC electricity use per conditioned floor area, VRF system cost, and the cooling-to-total electricity consumption ratio (R) in residential buildings equipped with VRF systems located in the Middle East (ME) region (Kuwait City, Tehran, and Istanbul). Artificial Neural Network (ANN) model was also developed to predict output parameters in residential building. Latin Hypercube Sampling (LHS) simulation was also applied to generate near-random samples of uncertainty parameter values from a multidimensional distribution. It should be mentioned that a correlation was derived in this study to predict VRF cost. The study evaluated thirteen uncertainty parameters related to building characteristics, occupants, building energy systems, VRF variables, and lighting conditions. Several methods were used to evaluate the effects of input uncertainty parameters on the output variables, namely, the Standardized Regression Coefficient (SRC), Partial Correlation Coefficient (PCC), and Spearman Rank Correlation Coefficient (SRCC) or Pearson Product-Moment Correlation Coefficient (PPMCC). The results indicated that VRF cost and HVAC electricity use per area have a greater coefficient of variation compared with other output parameters. The density distribution of output parameters indicated that uncertainty parameters had the greatest impact on output parameters in Kuwait (hyper arid climate), whereas in Istanbul (humid subtropical climate), they were the least. Among the variables examined in the Sensitivity Analysis (SA), cooling setpoint had the greatest impact on residential building energy consumption in ME climates. Finally, this paper highlights emerging trends and offers recommendations for advancing future research in the realm of building energy uncertainty analysis. • Comprehensive review of previous uncertainty analysis studies was provided. • VRF systems operational and design parameters effect on cooling load were reviewed. • Investigate an impact of uncertainties on building performance in various climates. • Energy consumption in building was most influenced by cooling setpoints. • Results show a more significant impact of uncertainty in hyper-arid climates. [ABSTRACT FROM AUTHOR]

Energy retrofitting of residential buildings is considered a challenge to be tackled not only at building level, but also at urban scale, to give a stronger impulse for a concrete transition towards climate neutrality. This paper presents an easy-to-use analysis method based on the elaboration and scaling-up of data collected through the energy performance certificates (EPCs) to identify different urban energy zones distinguished by their energy performance index. This method is therefore conceived for better informing urban planning decisions, thus boosting more effective energy-sensitive urban planning strategies and eventually to foresee dedicated financial instruments to act in the more energy demanding areas of the city, establishing priorities for integrated strategies. This analytical method has been applied and tested in one municipality in the Emilia-Romagna region, Italy, where the recent urban planning law is pushing municipalities towards the development of urban planning strategies oriented to drastically improve the energy efficiency of the existing building stock. Results show that only a small number of areas manage to reach a good performance with fairly low levels of energy performance index, with the most critical situation found in the most central areas of the capital and in the hamlets. • Easy-to-use method for assessing energy performance of residential building at urban scale is proposed • Method based on data easily available for local authorities, like energy performance certificates (EPCs) and urban morphology • The method supports urban planners in municipalities in taking more targeted decisions for improving energy efficiency • The main output of the method is the definition of an energy performance index (EPI) for different urban contexts • EPI allows to wisely balance economic incentives, identifying areas where multi-purpose interventions are recommended [ABSTRACT FROM AUTHOR]