scholarly journals Efficient Design of Energy Disaggregation Model with BERT-NILM Trained by AdaX Optimization Method for Smart Grid

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4649
Author(s):  
İsmail Hakkı ÇAVDAR ◽  
Vahit FERYAD
Keyword(s):  
Smart Grids ◽  
Energy Demand ◽  
Optimization Technique ◽  
Cost Effective ◽  
Optimization Method ◽  
Long Term Memory ◽  
Successful Implementation ◽  
Efficient Design ◽  
Energy Disaggregation ◽  
Load Monitoring

One of the basic conditions for the successful implementation of energy demand-side management (EDM) in smart grids is the monitoring of different loads with an electrical load monitoring system. Energy and sustainability concerns present a multitude of issues that can be addressed using approaches of data mining and machine learning. However, resolving such problems due to the lack of publicly available datasets is cumbersome. In this study, we first designed an efficient energy disaggregation (ED) model and evaluated it on the basis of publicly available benchmark data from the Residential Energy Disaggregation Dataset (REDD), and then we aimed to advance ED research in smart grids using the Turkey Electrical Appliances Dataset (TEAD) containing household electricity usage data. In addition, the TEAD was evaluated using the proposed ED model tested with benchmark REDD data. The Internet of things (IoT) architecture with sensors and Node-Red software installations were established to collect data in the research. In the context of smart metering, a nonintrusive load monitoring (NILM) model was designed to classify household appliances according to TEAD data. A highly accurate supervised ED is introduced, which was designed to raise awareness to customers and generate feedback by demand without the need for smart sensors. It is also cost-effective, maintainable, and easy to install, it does not require much space, and it can be trained to monitor multiple devices. We propose an efficient BERT-NILM tuned by new adaptive gradient descent with exponential long-term memory (Adax), using a deep learning (DL) architecture based on bidirectional encoder representations from transformers (BERT). In this paper, an improved training function was designed specifically for tuning of NILM neural networks. We adapted the Adax optimization technique to the ED field and learned the sequence-to-sequence patterns. With the updated training function, BERT-NILM outperformed state-of-the-art adaptive moment estimation (Adam) optimization across various metrics on REDD datasets; lastly, we evaluated the TEAD dataset using BERT-NILM training.

scholarly journals A multi-level optimization technique for electricity consumption management and pricing in residential neighborhoods

2021 ◽  
Author(s):  
Ramyar Rashed Mohassel
Keyword(s):  
Smart Grids ◽  
New Technologies ◽  
Power Transmission ◽  
Optimization Technique ◽  
Electricity Consumption ◽  
Optimization Method ◽  
Residential Neighborhood ◽  
Upper Level ◽  
Advanced Metering ◽  
Power Management Unit

With the introduction of new technologies, concepts and approaches in power transmission, distribution and utilization such as Smart Grids (SG), Advanced Metering Infrastructures (AMI), Distributed Energy Resources (DER) and Demand Side Management (DSM), new capabilities have emerged that enable efficient use and management of power consumption. These capabilities are applicable at micro level in households and building complexes as well as at macro level for utility providers in form of resource and revenue management initiatives. On the other hand, integration of Information Technology (IT) and instrumentation has brought Building Management Systems (BMS) to our homes and has made it possible for the ordinary users to take advantage of more complex and sophisticated energy and cost management features as an integral part of their BMS. The idea of combining capabilities and advantages offered by SG, AMI, DER, DSM and BMS is the backbone of this thesis and has resulted in developing a unique, two-level optimization method for effective deployment of DSM at households and residential neighborhoods. The work consists of an optimization algorithm for households to maximize utilization of DER as the lower level of the envisioned two-level optimization technique while using a customized Game Theoretic optimization for optimizing revenue of utility providers for residential neighborhood as the upper level. This work will also introduce a power management unit, called Load Moderation Center (LMC), to host the developed optimization algorithms as an integrated part of BMS. LMC, upon successful completion, will be able to automatically plan consumption, effectively utilize available sources including grid, renewable energies and storages, and eliminate the need for residences to manually program their BMS for different market scenarios.

Efficient Structural Design Using a Numerical Optimization Technique

2019 ◽  
Author(s):  
Qian Wang ◽  
Lucas Schmotzer ◽  
Yongwook Kim
Keyword(s):  
Structural Design ◽  
Numerical Optimization ◽  
Optimization Technique ◽  
Optimization Method ◽  
Optimization Techniques ◽  
Convergence Criteria ◽  
Efficient Design ◽  
Concrete Building ◽  
Gradient Based ◽  
Structural Responses

<p>Structural designs of complex buildings and infrastructures have long been based on engineering experience and a trial-and-error approach. The structural performance is checked each time when a design is determined. An alternative strategy based on numerical optimization techniques can provide engineers an effective and efficient design approach. To achieve an optimal design, a finite element (FE) program is employed to calculate structural responses including forces and deformations. A gradient-based or gradient-free optimization method can be integrated with the FE program to guide the design iterations, until certain convergence criteria are met. Due to the iterative nature of the numerical optimization, a user programming is required to repeatedly access and modify input data and to collect output data of the FE program. In this study, an approximation method was developed so that the structural responses could be expressed as approximate functions, and that the accuracy of the functions could be adaptively improved. In the method, the FE program was not required to be directly looped in the optimization iterations. As a practical illustrative example, a 3D reinforced concrete building structure was optimized. The proposed method worked very well and optimal designs were found to reduce the torsional responses of the building.</p>

Design of Optimal CMOS Analog Amplifier Circuits Using a Hybrid Evolutionary Optimization Technique

2017 ◽  
Vol 27 (02) ◽  
pp. 1850029 ◽  
Author(s):  
Bishnu Prasad De ◽  
Kanchan Baran Maji ◽  
Rajib Kar ◽  
Durbadal Mandal ◽  
Sakti Prasad Ghoshal
Keyword(s):  
Power Dissipation ◽  
Optimization Problems ◽  
Optimization Technique ◽  
Optimization Method ◽  
Vlsi Circuits ◽  
Optimal Designs ◽  
Efficient Design ◽  
Mos Transistors ◽  
Evolutionary Technique ◽  
Random Particle

This paper proposes an efficient design technique for two commonly used VLSI circuits, namely, CMOS current mirror load-based differential amplifier circuit and CMOS two-stage operational amplifier. The hybrid evolutionary method utilized for these optimal designs is random particle swarm optimization with differential evolution (RPSODE). Random PSO utilizes the weighted particles for monitoring the search directions. DE is a robust evolutionary technique. It has demonstrated an exclusive performance for the optimization problems which are continuous and global but suffers from the uncertainty issues. PSO is a robust optimization method but suffers from sub-optimality problem. This paper effectively hybridizes the random PSO and DE to remove the limitations related to both the techniques individually. In this paper, RPSODE is employed to optimize the sizes of the MOS transistors to reduce the overall area taken by the circuit while satisfying the design constraints. The results obtained from RPSODE technique are validated in SPICE environment. SPICE-based simulation results justify that RPSODE is a much better technique than other formerly reported methods for the designs of the above mentioned circuits in terms of MOS area, gain, power dissipation, etc.

Energy Optimization in Net-Zero Energy Building Clusters

2014 ◽  
Author(s):  
Philip Odonkor ◽  
Kemper Lewis ◽  
Jin Wen ◽  
Teresa Wu
Keyword(s):  
Smart Grids ◽  
Energy Demand ◽  
Energy Optimization ◽  
Cost Effective ◽  
Energy Utilization ◽  
Valuable Insight ◽  
Zero Energy ◽  
Net Zero Energy ◽  
Net Zero ◽  
Building Energy Optimization

Traditionally viewed as mere energy consumers, buildings have in recent years adapted, capitalizing on smart grid technologies and distributed energy resources to not only efficiently use energy, but to also output energy. This has led to the development of net-zero energy buildings, a concept which encapsulates the synergy of energy efficient buildings, smart grids, and renewable energy utilization to reach a balanced energy budget over an annual cycle. This work looks to further expand on this idea, moving beyond just individual buildings and considering net-zero at a community scale. We hypothesize that applying net-zero concepts to building communities, also known as building clusters, instead of individual buildings will result in cost effective building systems which in turn will be resilient to power disruption. To this end, this paper develops an intelligent energy optimization algorithm for demand side energy management, taking into account a multitude of factors affecting cost including comfort, energy price, Heating, Ventilation, and Air Conditioning (HVAC) system, energy storage, weather, and on-site renewable resources. A bi-level operation decision framework is presented to study the energy tradeoffs within the building cluster, with individual building energy optimization on one level and an overall net-zero energy optimization handled on the next level. The experimental results demonstrate that the proposed approach is capable of significantly shifting demand, and when viable, reducing the total energy demand within net-zero building clusters. Furthermore, the optimization framework is capable of deriving Pareto solutions for the cluster which provide valuable insight for determining suitable energy strategies.

scholarly journals A Hierarchical Game Theory Based Demand Optimization Method for Grid-Interaction of Energy Flexible Buildings

2021 ◽  
Vol 9 ◽  
Author(s):  
Jinyi Xu ◽  
Chengchu Yan ◽  
Yizhe Xu ◽  
Jingfeng Shi ◽  
Kai Sheng ◽  
...  
Keyword(s):  
Game Theory ◽  
Smart Grids ◽  
Energy Demand ◽  
Power Grid ◽  
Management Strategies ◽  
Interaction Model ◽  
Optimization Method ◽  
Equilibrium Solutions ◽  
Electrical Grids ◽  
Nash Equilibrium Solutions

Building demand-side management is an effective solution for relieving the peak and imbalance problems of electrical grids. How to explore the energy flexibility of buildings and to coordinate a variety of buildings with different energy flexibilities for effective interactions with smart grids are a great challenge. This paper proposes a game theory–based hierarchical demand optimization method for energy flexible buildings for achieving better grid interactions. This method consists of two optimization strategies at the grid and building levels. At the grid level, a demand-price interaction model for buildings and the grid is established to identify the Nash equilibrium solutions based on game theory; these solutions are used to determine the optimized energy demand of buildings and the associated electricity prices by accommodating the interests of all participants involved. At the building level, three types of buildings with different energy flexibilities are investigated to analyze the influence of building management strategies on grid interactions. The effectiveness of the proposed method is verified in a simulated case study. The results show that the optimization method can reduce building operational cost by 3–18%, reduce the fluctuation of the power grid by 30–50%, and ensure that the power grid increases income by 8–20%.

scholarly journals Evaluation of a LoRa Mesh Network for Smart Metering in Rural Locations

Electronics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 751
Author(s):  
Anup Marahatta ◽  
Yaju Rajbhandari ◽  
Ashish Shrestha ◽  
Ajay Singh ◽  
Anup Thapa ◽  
...  
Keyword(s):  
Smart Grids ◽  
Cost Effective ◽  
Energy System ◽  
Mesh Network ◽  
Smart Metering ◽  
Monitoring And Control ◽  
Smart Meters ◽  
Load Monitoring ◽  
Iot Devices ◽  
And Control

Accompanying the advancement on the Internet of Things (IoT), the concept of remote monitoring and control using IoT devices is becoming popular. Digital smart meters hold many advantages over traditional analog meters, and smart metering is one of application of IoT technology. It supports the conventional power system in adopting modern concepts like smart grids, block-chains, automation, etc. due to their remote load monitoring and control capabilities. However, in many applications, the traditional analog meters still are preferred over digital smart meters due to the high deployment and operating costs, and the unreliability of the smart meters. The primary reasons behind these issues are a lack of a reliable and affordable communication system, which can be addressed by the deployment of a dedicated network formed with a Low Power Wide Area (LPWA) platform like wireless radio standards (i.e., LoRa devices). This paper discusses LoRa technology and its implementation to solve the problems associated with smart metering, especially considering the rural energy system. A simulation-based study has been done to analyse the LoRa technology’s applicability in different architecture for smart metering purposes and to identify a cost-effective and reliable way to implement smart metering, especially in a rural microgrid (MG).

Sustainability through Optimization: The Future of Watershed Management

2012 ◽  
Vol 260-261 ◽  
pp. 876-881
Author(s):  
Thambirajah Saravanapavan ◽  
Guo Shun Zhang ◽  
Mark Voorhees
Keyword(s):  
Watershed Management ◽  
Stormwater Management ◽  
Management Practices ◽  
Traditional Approach ◽  
Optimization Technique ◽  
Low Impact Development ◽  
Cost Effective ◽  
Optimization Method ◽  
Phosphorus Loading ◽  
Optimization Approach

A quantitative comparison of total costs between the traditional approach and the optimization approach for stormwater management is presented in this study. As the uniform sizing method is always associated with the traditional stormwater management practices, the optimization approach is well suited for the more recent stormwater management paradigm of low impact development (LID) practices. In the case study conducted for the town of Franklin in the Upper Charles River Watershed, Massachusetts, USA, the optimization method is able to identify stormwater management alternatives that cost 60% less than the traditional approach for meeting the Phosphorus loading reduction targets. The study highlights the comprehensive benefits from coupling optimization with the LID practices in stormwater management: 1. The LID practices’ focus on restoring the predevelopment runoff conditions ensures sustainable stormwater management, and 2. The optimization technique guarantees that the most cost-effective LID practices are selected throughout the decision-making process. The approaches outlined in this study can be very informative to many Asian countries that are under fast development and are in urgent need of scientific and sound approaches for achieving sustainable watershed management.

scholarly journals A multi-level optimization technique for electricity consumption management and pricing in residential neighborhoods

2021 ◽  
Author(s):  
Ramyar Rashed Mohassel
Keyword(s):  
Smart Grids ◽  
New Technologies ◽  
Power Transmission ◽  
Optimization Technique ◽  
Electricity Consumption ◽  
Optimization Method ◽  
Residential Neighborhood ◽  
Upper Level ◽  
Advanced Metering ◽  
Power Management Unit

With the introduction of new technologies, concepts and approaches in power transmission, distribution and utilization such as Smart Grids (SG), Advanced Metering Infrastructures (AMI), Distributed Energy Resources (DER) and Demand Side Management (DSM), new capabilities have emerged that enable efficient use and management of power consumption. These capabilities are applicable at micro level in households and building complexes as well as at macro level for utility providers in form of resource and revenue management initiatives. On the other hand, integration of Information Technology (IT) and instrumentation has brought Building Management Systems (BMS) to our homes and has made it possible for the ordinary users to take advantage of more complex and sophisticated energy and cost management features as an integral part of their BMS. The idea of combining capabilities and advantages offered by SG, AMI, DER, DSM and BMS is the backbone of this thesis and has resulted in developing a unique, two-level optimization method for effective deployment of DSM at households and residential neighborhoods. The work consists of an optimization algorithm for households to maximize utilization of DER as the lower level of the envisioned two-level optimization technique while using a customized Game Theoretic optimization for optimizing revenue of utility providers for residential neighborhood as the upper level. This work will also introduce a power management unit, called Load Moderation Center (LMC), to host the developed optimization algorithms as an integrated part of BMS. LMC, upon successful completion, will be able to automatically plan consumption, effectively utilize available sources including grid, renewable energies and storages, and eliminate the need for residences to manually program their BMS for different market scenarios.

scholarly journals New Design of a Supervised Energy Disaggregation Model Based on the Deep Neural Network for a Smart Grid

Energies ◽  
2019 ◽  
Vol 12 (7) ◽  
pp. 1217 ◽  
Author(s):  
İsmail ÇAVDAR ◽  
Vahid FARYAD
Keyword(s):  
Neural Network ◽  
Smart Grid ◽  
Convolutional Neural Network ◽  
Energy Demand ◽  
Short Term Memory ◽  
Fog Computing ◽  
Processing Unit ◽  
Demand Side ◽  
Energy Disaggregation ◽  
Load Monitoring

Energy management technology of demand-side is a key process of the smart grid that helps achieve a more efficient use of generation assets by reducing the energy demand of users during peak loads. In the context of a smart grid and smart metering, this paper proposes a hybrid model of energy disaggregation through deep feature learning for non-intrusive load monitoring to classify home appliances based on the information of main meters. In addition, a deep neural model of supervised energy disaggregation with a high accuracy for giving awareness to end users and generating detailed feedback from demand-side with no need for expensive smart outlet sensors was introduced. A new functional API model of deep learning (DL) based on energy disaggregation was designed by combining a one-dimensional convolutional neural network and recurrent neural network (1D CNN-RNN). The proposed model was trained on Google Colab’s Tesla graphics processing unit (GPU) using Keras. The residential energy disaggregation dataset was used for real households and was implemented in Tensorflow backend. Three different disaggregation methods were compared, namely the convolutional neural network, 1D CNN-RNN, and long short-term memory. The results showed that energy can be disaggregated from the metrics very accurately using the proposed 1D CNN-RNN model. Finally, as a work in progress, we introduced the DL on the Edge for Fog Computing non-intrusive load monitoring (NILM) on a low-cost embedded board using a state-of-the-art inference library called uTensor that can support any Mbed enabled board with no need for the DL API of web services and internet connectivity.

Towards Low-Cost Energy Monitoring

2015 ◽  
pp. 2965-2970
Author(s):  
Aqeel H. Kazmi ◽  
Michael J. O'Grady ◽  
Gregory M.P. O' Hare
Keyword(s):  
Energy Demand ◽  
Low Cost ◽  
Cost Effective ◽  
Future Research ◽  
Energy Prices ◽  
Energy Usage ◽  
Energy Monitoring ◽  
Load Monitoring ◽  
Future Research Directions ◽  
Residential And Commercial Sectors

A number of energy problems including limited energy resources, increased energy demand, and rising energy prices, have motivated energy conservation in the residential and commercial sectors. Access to real-time energy usage information is perceived as a prerequisite for energy usage reductions. A variety of computational approaches have been proposed to monitor energy usage within buildings. Currently, Non-intrusive Load Monitoring (NILM) is perceived as the most cost-effective and scalable solution. In this article, a technological profile of this technique is constructed through the provision of key background developments, revision of existing solutions, consideration of outstanding problems, and identification of some pertinent future research directions.

Sign in / Sign up

Export Citation Format

Share Document