Figure 7 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
In this work, we provide a smart home occupancy prediction technique based on environmental variables such as CO2, noise, and relative temperature via our machine learning method and forecasting strategy. The proposed algorithms enhance the energy management system through the optimal use of the electric heating system. The Long Short-Term Memory (...
Similar publications
In a smart home with distributed energy resources, the home energy management system (HEMS) controls the photovoltaic (PV) storage system by executing the optimization algorithm to achieve the lowest power cost. The existing mixed integer linear programming (MILP) algorithm is not suitable for execution on the end-user side due to its high computat...
Citations
... Many studies have used either the classical LSTM or modified LSTMs. In study [48], both Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) were used for LSTM weights optimization. The model was used to predict multi-variables such as CO 2 , noise, and relative temperature. ...
Accurate occupancy prediction in smart buildings is crucial for optimizing energy management, improving occupant comfort, and effectively controlling building systems, particularly for short- and long-term horizons. Recently, deep learning-based occupancy prediction methods have gained considerable attention. However, the full potential of these methods remains under explored in terms of model architecture variations and prediction horizons. This study introduces cascaded LSTM and cascaded Bi-LSTM models for multi-horizon predictions from 10 minutes to 24 hours, integrating a modified activation function, additional input features, and optimized hyper-parameters using OPTUNA. Traditional performance metrics and various other analyses were conducted to compare the models. Both models performed well for short- and long-term predictions, with minimal differences in the results. Nevertheless, analysis focusing on non-zero data errors (accounting for approximately 11% of occupied periods) and occupancy-wise errors showed a significant performance gap between the two models. The cascaded Bi-LSTM model demonstrated consistent performance across various prediction horizons and occupancy variations, with accuracy approximately 10-15% higher than the cascaded LSTM model, highlighting its superior capability in capturing complex dataset dynamics through a bidirectional process. This study highlights the importance of additional input features, data feature analysis, and multi-perspective result analysis to select the most suitable model for occupancy prediction, validated with pre- and post-modeling feature importance analysis.
... In the literature, LSTM has been widely used for occupancy prediction. The study in [139] introduced a method for predicting occupancy in smart homes, which relied on environmental factors like CO 2 levels, noise, and temperature, and employed a ML method and a forecasting strategy. The proposed algorithms aimed to improve the energy management system by optimizing the use of the electric heating system. ...
In today’s world, a significant amount of global energy is used in buildings. Unfortunately, a lot of this energy is wasted, because electrical appliances are not used properly or efficiently. One way to reduce this waste is by detecting, learning, and predicting when people are present in buildings. To do this, buildings need to become “smart” and “cognitive” and use modern technologies to sense when and how people are occupying the buildings. By leveraging this information, buildings can make smart decisions based on recently developed methods. In this paper, we provide a comprehensive overview of recent advancements in Internet of Things (IoT) technologies that have been designed and used for the monitoring of indoor environmental conditions within buildings. Using these technologies is crucial to gathering data about the indoor environment and determining the number and presence of occupants. Furthermore, this paper critically examines both the strengths and limitations of each technology in predicting occupant behavior. In addition, it explores different methods for processing these data and making future occupancy predictions. Moreover, we highlight some challenges, such as determining the optimal number and location of sensors and radars, and provide a detailed explanation and insights into these challenges. Furthermore, the paper explores possible future directions, including the security of occupants’ data and the promotion of energy-efficient practices such as localizing occupants and monitoring their activities within a building. With respect to other survey works on similar topics, our work aims to both cover recent sensory approaches and review methods used in the literature for estimating occupancy.
... This approach allows buildings to become cognitive and selfadapting, thereby achieving energy efficiency and reducing wastage without compromising privacy concerns. Similarly, another recent study [42] employs a machine learning forecasting approach that utilized an LSTM neural network to predict occupancy in buildings and, accordingly, to optimize the energy management of electric heating systems. The study improves the LSTM algorithm's performance using optimization techniques such as Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). ...
... However, this method also has some disadvantages, such as difficulty in handling nonlinear data and the ability to optimize model parameters to achieve high performance. Hence, applying two deep learning neural networks, Long Short-Term Memory Optimized by Particle Swarm Optimization (PSO-LSTM) and Long Short-Term Memory Optimized by Genetic Algorithms (GA-LSTM), solved the current limitations of the LSTM method [20]. Using PSO and GA optimized hyperparameters such as window size, epochs, neurons, and learning rate of the LSTM network more efficiently. ...
... As mentioned above, many studies demonstrated that the efficiency of the LSTM model increases significantly after applying GA-LSTM and PSO-LSTM [20,26]. However, the experiments on the GPS data to forecast the average velocity of segments of the arterial roads having parallel multiple lanes are limited. ...
Early forecasting of vehicle flow speeds is crucial for sustainable traffic development and establishing Traffic Speed Forecasting (TSF) systems for each country. While online mapping services offer significant benefits, dependence on them hampers the development of domestic alternative platforms, impeding sustainable traffic management and posing security risks. There is an urgent need for research to explore sustainable solutions, such as leveraging Global Positioning System (GPS) probe data, to support transportation management in urban areas effectively. Despite their vast potential, GPS probe data often present challenges, particularly in urban areas, including interference signals and missing data. This paper addresses these challenges by proposing a process for handling anomalous and missing GPS signals from probe vehicles on parallel multilane roads in Vietnam. Additionally, the paper investigates the effectiveness of techniques such as Particle Swarm Optimization Long Short-Term Memory (PSO-LSTM) and Genetic Algorithm Long Short-Term Memory (GA-LSTM) in enhancing LSTM networks for TSF using GPS data. Through empirical analysis, this paper demonstrates the efficacy of PSO-LSTM and GA-LSTM compared to existing methods and the state-of-the-art LSTM approach. Performance metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Median Absolute Error (MDAE) validate the proposed models, providing insights into their forecasting accuracy. The paper also offers a comprehensive process for handling GPS outlier data and applying GA and PSO algorithms to enhance LSTM network quality in TSF, enabling researchers to streamline calculations and improve supposed model efficiency in similar contexts.
... Due to the advancement of machine/deep learning-based techniques, several scholars have begun to concentrate on these tactics [6], [7]. A unique deep learning method for processing time series predictions, the LSTM neural network, has recently shown encouraging prediction results [8], [9]. The gated unit mechanism used in this model improves the conventional recurrent neural network (RNN) by preventing the vanishing gradient issue. ...
A smart city utilizes vast data collected through electronic methods, such as sensors and cameras, to improve daily life by managing resources and providing services. Moving towards a smart grid is a step in realizing this concept. The proliferation of smart grids and the concomitant progress made in the development of measuring infrastructure have garnered considerable interest in short-term power consumption forecasting. In reality, predicting future power demands has shown to be a crucial factor in preventing energy waste and developing successful power management techniques. In addition, historical time series data on energy consumption may be considered necessary to derive all relevant knowledge and estimate future use. This research paper aims to construct and compare with original deep learning algorithms for forecasting power consumption over time. The proposed model, LSTM-GRU-PPCM, combines the Long -Short-Term -Memory (LSTM) and Gated- Recurrent- Unit (GRU) Prediction Power Consumption Model. Power consumption data will be utilized as the time series dataset, and predictions will be generated using the developed model. This research avoids consumption peaks by using the proposed LSTM-GRU-PPCM neural network to forecast future load demand. In order to conduct a thorough assessment of the method, a series of experiments were carried out using actual power consumption data from various cities in India. The experiment results show that the LSTM-GRU-PPCM model improves the original LSTM forecasting algorithms evaluated by Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) for various time series. The proposed model achieved a minimum error prediction of MAE=0.004 and RMSE=0.032, which are excellent values compared to the original LSTM. Significant implications for power quality management and equipment maintenance may be expected from the LSTM-GRU-PPCM approach, as its forecasts will allow for proactive decision-making and lead to load shedding when power consumption exceeds the allowed level
... While traditional approaches to occupancy prediction often rely on centralized data aggregation and analysis, recent research has explored the use of FL to address privacy concerns and enable distributed prediction models. For instance, the work by Mahjoub et al. [32] introduces a novel technique for predicting occupancy in smart homes utilizing environmental variables such as CO 2 levels, noise, and relative temperature. The proposed method and forecasting strategy optimize the energy management system by effectively utilizing the electric IEEE DASC/CyberSciTech/PICom/CBDCom 2023 heating system. ...
Energy efficiency and energy saving have become crucial issues in the face of increasing energy demand, the need for sustainable solutions, and concerns about climate change. Buildings, as significant contributors to energy consumption and greenhouse gas emissions, require effective measures for energy optimization that can also be reached by predicting the usage of the building spaces. This paper introduces a data-driven approach combining Internet of Things sensors, Machine Learning, Edge computing, and Federated Learning to predict multi-occupancy in buildings. The proposed approach is used on real data from the ICAR-CNR IoT Laboratory in order to extract insights into occupancy patterns within a multi-occupant environment. Finally, a comparative analysis conducted by varying Federated Learning configurations demonstrates the robustness of the solution.
... Thus, to enhance the LSTM forecasting model's accuracy, many authors combined the features of different optimization algorithms with LSTM models to get the best optimal parameters, such as [33][34][35][36]. However, according to [36], when the optimized hyperparameters return, the time slots need to be taken out concerning the real-time data. ...
... Paper [6] proposed a smart home occupancy prediction technique using environmental variables such as CO 2 , noise, and relative temperature via an ML forecasting strategy. The LSTM neural network was used to process time series prediction, and two metaheuristic optimization algorithms (GA and PSO) were used to enhance the performance of the LSTM algorithm. ...
A modern power system is a complex network of interconnected components, such as generators, transmission lines, and distribution subsystems, that are designed to provide electricity to consumers in an efficient and reliable manner [...]
As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R ² ) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability.
Nowadays, data are more and more used for intelligent modeling and prediction, and the comprehensive evaluation of data quality is getting more and more attention as a necessary means to measure whether the data are usable or not. However, the comprehensive evaluation method of data quality mostly contains the subjective factors of the evaluator, so how to comprehensively and objectively evaluate the data has become a bottleneck that needs to be solved in the research of comprehensive evaluation method. In order to evaluate the data more comprehensively, objectively and differentially, a novel comprehensive evaluation method based on particle swarm optimization (PSO) and grey correlation analysis (GCA) is presented in this paper. At first, an improved GCA evaluation model based on the technique for order preference by similarity to an ideal solution (TOPSIS) is proposed. Then, an objective function model of maximum difference of the comprehensive evaluation values is built, and the PSO algorithm is used to optimize the weights of the improved GCA evaluation model based on the objective function model. Finally, the performance of the proposed method is investigated through parameter analysis. A performance comparison of traffic flow data is carried out, and the simulation results show that the maximum average difference between the evaluation results and its mean value (MDR) of the proposed comprehensive evaluation method is 33.24% higher than that of TOPSIS-GCA, and 6.86% higher than that of GCA. The proposed method has better differentiation than other methods, which means that it objectively and comprehensively evaluates the data from both the relevance and differentiation of the data, and the results more effectively reflect the differences in data quality, which will provide more effective data support for intelligent modeling, prediction and other applications.
