A review of hierarchical control for building microgrids
مروری بر کنترل سلسله مراتبی برای میکرو گریدهای ساختمان-2020
Building microgrids have emerged as an advantageous alternative for tackling environmental issues while enhancing the electricity distribution system. However, uncertainties in power generation, electricity prices and power consumption, along with stringent requirements concerning power quality restrain the wider development of building microgrids. This is due to the complexity of designing a reliable and robust energy management system. Within this context, hierarchical control has proved suitable for handling different requirements simultaneously so that it can satisfactorily adapt to building environments. In this paper, a comprehensive literature review of the main hierarchical control algorithms for building microgrids is discussed and compared, emphasising their most important strengths and weaknesses. Accordingly, a detailed explanation of the primary, secondary and tertiary levels is presented, highlighting the role of each control layer in adapting building microgrids to current and future electrical grid structures. Finally, some insights for forthcoming building prosumers are outlined, identifying certain barriers when dealing with building microgrid communities.
Index Terms: Electricity market | Energy management system | Optimisation algorithms | Renewable energy source | Prosumer
Remote sensing and social sensing for socioeconomic systems: A comparison study between nighttime lights and location-based social media at the 500m spatial resolution
سنجش از دور و سنجش اجتماعی برای سیستمهای اقتصادی اقتصادی: مطالعه مقایسه ای بین چراغ های شب و رسانه های اجتماعی مبتنی بر مکان در وضوح مکانی 500 متر-2020
With the advent of “social sensing” in the Big Data era, location-based social media (LBSM) data are increasingly used to explore anthropogenic activities and their impacts on the environment. This study converts a typical kind of LBSM data, geo-tagged tweets, into raster images at the 500m spatial resolution and compares them with the new generation nighttime lights (NTL) image products, the Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) monthly image composites. The results show that the monthly tweet images are significantly correlated with the VIIRS-DNB images at the pixel level. The tweet images have nearly the same ability on estimating electric power consumption and better performance on assessing personal incomes and population than the NTL images. Tweeted areas (i.e. the pixels with at least one posted tweet) are closer to satellite-derived built-up/urban areas than lit areas in NTL imagery, making tweet images an alternative to delimit extents of human activities. Moreover, the monthly tweet images do not show apparent seasonal changes, and the values of tweet images are more stable across different months than VIIRS-DNB monthly image composites. This study explores the potential of LBSM data at relatively fine spatiotemporal resolutions to estimate or map socioeconomic factors as an alternative to NTL images in the United States
Keywords: Nighttime lights imagery | Geo-tagged tweets | Socioeconomic factors | Social sensing
AI Aided Noise Processing of Spintronic Based IoT Sensor for Magnetocardiography Application
پردازش نویز به کمک هوش مصنوعی مبتنی بر حسگر اینترنت اشیا بر Spintronic برای کاربرد مغناطیسی قلب-2020
As we are about to embark upon the highly hyped “Society 5.0”, powered by the Internet of Things (IoT), traditional ways to monitor human heart signals for tracking cardio-vascular conditions are challenging, particularly in remote healthcare settings. On the merits of low power consumption, portability, and non-intrusiveness, there are no suitable IoT solutions that can provide information comparable to the conventional Electrocardiography (ECG). In this paper, we propose an IoT device utilizing a spintronic-technology-based ultra-sensitive Magnetic Tunnel Junction (MTJ) sensor that measures the magnetic fields produced by cardio-vascular electromagnetic activity, i.e. Magentocardiography (MCG). We treat the low-frequency noise generated by the sensor, which is also a challenge for most other sensors dealing with low-frequency bio-magnetic signals. Instead of relying on generic signal processing techniques such as moving average, we employ deep-learning training on biomagnetic signals. Using an existing dataset of ECG records, MCG signals are synthesized. A unique deep learning model, composed of a one-dimensional convolution layer, Gated Recurrent Unit (GRU) layer, and a fully-connected neural layer, is trained using the labeled data moving through a striding window, which is able to smartly capture and eliminate the noise features. Simulation results are reported to evaluate the effectiveness of the proposed method that demonstrates encouraging performance.
Index Terms: Smart health | IoT | ECG | MCG | deep learning | noise | spintronic sensor | convolution | GRU | medical analytics
A collaborative energy management among plug-in electric vehicle, smart homes and neighbors’ interaction for residential power load profile smoothing
مدیریت انرژی مشارکتی بین خودروهای برقی پلاگین ، خانه های هوشمند و تعامل همسایگان برای هموار کردن مشخصات بار توان مسکونی-2020
With the modernization of the smart grid, Plug-in Electric Vehicles (PEVs) have attracted attention thanks to the effective energy support through the bi-directional power flow exchanging. In particular, vehicle-to-home technology has drawn a significant interest in PEVs’ parked at smart home to enhance the power consumption profile. This paper proposes a collaborative energy management among PEVs, smart homes and neighbors’ interaction. For that, a new supervision strategy based on PEVs power scheduling for smoothing the residential power load profile is developed. The objective of this study is to improve the power demand profile by controlling the PEV power charging/discharging amount to fill the valley of the power consumption curve or by providing power to home especially during peak periods to shave peak. The home energy management for achieving a flattened power load profile is divided into two parts: a local control according to the base demand profile of the considering home, the availability of their PEVs, their arrival and departure times and their initial state of charge (SOC) values. A global control according to the power demand of the specific home, the total power demand of neighbors and the availability of PEVs’ neighbors (arrival and departure times, initial energy of the battery). The simulation results of the power load profile of such smart homes highlights the interaction between PEVs, smart home and their neighbors in order to flatten the power demand curve to the greatest extent possible.
Keywords: Plug-in electric vehicles (PEVs) | Smart home | Neighbors’ interaction | Collaborative energy management | Fill the valley | Shave peak | Smooth
FaaVPP: Fog as a virtual power plant service for community energy management
FaaVPP: مه به عنوان یک سرویس نیروگاه مجازی برای مدیریت انرژی جامعه-2020
The fossil fuel based power generators emit CO2 and expensive electricity. In this paper, fog as a virtual power plant (FaaVPP) is proposed to integrate power of distributed renewable power generators and the utility for a community. A prosumer–consumer and service providing company oriented linear model is proposed to minimize power consumption cost for prosumers and maximize profit for the company. The mathematical proof of linear model validates the significance for service provider and energy users. Moreover, outcome of case studies advocate the efficiency of the model. Efficient resource utilization techniques of fog resources ensure the near-real time service provision to the community. In the paper, effects of resource utilization techniques e.g., processing time (PT), response time (RT), computing cost and energy consumed by the resources are also analyzed.
Keywords: Virtual power plant | Fog as a service | FaaVPP | Computational energy | Response time | Processing time | Virtual retail energy provider
An IoT based Intelligent Smart Energy Management System with accurate forecasting and load strategy for renewable generation
یک سیستم مدیریت انرژی هوشمند مبتنی بر IoT با پیش بینی دقیق و استراتژی بار برای نسل های تجدید پذیر-2020
The challenge in demand side energy management lays focus on the efficient utilization of renewable sources without limiting the power consumption. To deal with the above issue, it seeks for design and development of an intelligent system with day-ahead planning and accurate forecasting of energy availability. In this work, an Intelligent Smart Energy Management Systems (ISEMS) is proposed to handle energy demand in a smart grid environment with deep penetration of renewables. The proposed scheme compares several prediction models for accurate forecasting of energy with hourly and day ahead planning. PSO based SVMregressionmodel outperforms over several other predictionmodels in terms of performance accuracy. Finally, based on the predicted information, the demonstration of ISEMS experimental set-up is carried out and evaluated with different configurations considering user comfort and priority features. Also, integration of the IoT environment is developed for monitoring at the user end.
Keywords: Demand Side Management (DSM) | Internet of Things (IoT) | Intelligent Smart Energy Management | Systems (ISEMS) | Prediction | Renewable generation
SmartFCT: Improving power-efficiency for data center networks with deep reinforcement learning
SmartFCT: بهبود بهره وری انرژی برای شبکه های مرکز داده با یادگیری تقویتی عمیق-2020
Reducing the power consumption of Data Center Networks (DCNs) and guaranteeing the Flow Completion Time (FCT) of applications in DCNs are two major concerns for data center operators. However, existing works cannot realize the two goals together because of two issues: (1) dynamic traffic pattern in DCNs is hard to accurately model; (2) an optimal flow scheduling scheme is computationally expensive. In this paper, we propose SmartFCT, which employs the Deep Reinforcement Learning (DRL) coupled with Software-Defined Networking (SDN) to improve the power efficiency of DCNs and guarantee FCT. SmartFCT dynamically collects traffic distribution from switches to train its DRL model. The well-trained DRL agent of SmartFCT can quickly analyze the complicated traffic characteristics using neural networks and adaptively gen- erate a action for scheduling flows and deliberately configuring margins for different links. Following the gen- erated action, flows are consolidated into a few of active links and switches for saving power, and fine-grained margin configuration for active links avoids FCT violation of unexpected flow bursts. Simulation results show that SmartFCT can guarantee FCT and save up to 12.2% power consumption, compared with the state-of-the-art solutions.
Keywords: Data center networks | Software-Defined networking | Power efficiency | Flow completion time | Deep reinforcement learning
Implementation of Multi Spin-Thread Architecture to Fully-Connected Annealing Processing AI Chips
پیاده سازی معماری چند نخ چرخشی برای تراشه های پردازش هوش مصنوعی با پردازش آنیل کاملاً همبند-2020
Artificial intelligence (AI) processing on edge computing in the Internet of Things (IoT) society requires our focus on the Ising model to enable advanced information processing with low-power consumption, small area, and thorough implementation in LSI chips. The configuration is such that the fully-connected interaction layer (memory) and the spin and calculation layers of the Ising model are separated and directly connected in parallel. A stochastic operation is performed in the Ising model because annealing is used to obtain a solution. However, an optimal solution cannot always be obtained using one calculation. Therefore, we devised and implemented the concept of a multi spin-thread by taking advantage of the fact that multiple spin sets and calculation layers are possible. In the multi spin-thread, multiple threads can be calculated simultaneously with spin required for calculation being one thread. Therefore, the state of the other spin-threads can be adjusted to the state of the spin-thread with the smallest Hamiltonian, and a state with a lower Hamiltonian can be searched. This improves the accuracy of the solution. A 28-nm CMOS LSI (AI chip) with 512 spins and eight spin-threads was tested. In a 22-city traveling salesman problem (TSP), the average path length could be reduced by 19% and the dispersion reduced by 70% on average, and the number of cuts in the 512-node max-cut problem could be increased by 1.6% on average and the dispersion reduced by 84%. The time required to obtain the solution was 128 ms.
Keywords: IoT | Edge Computing | Artificial Intelligence | Ising Model | Fully-Connected | Multi spin-thread
Multi-agent based multi objective renewable energy management for diversified community power consumers
مدیریت انرژی تجدید پذیر چند منظوره مبتنی بر چند عامل برای مصرف کنندگان انرژی متنوع جامعه-2020
This paper proposes a multi-objective renewable energy management scheme to satisfy the needs of diversified community power consumers, wherein the multi-agent system is employed for coordinating and controlling the power generation and consumption units. Firstly, a multi-agent based microgrid and home energy management system is constructed. Subsequently, system models for renewable energy sources, electrical vehicles, residential loads and the cost function are constructed to form the microgrid operation constraints. With these constraints, three optimization models are proposed to minimize the electricity bills, the power purchased from the main grid, and optimize the power quality. The three objectives are proposed to reflect the power consumer’s needs for cost saving, green consumption, and power reliability, respectively. Meanwhile, a coordination strategy which balances the three objectives is proposed. After that, a novel multi agent system is proposed to realize the proposed objectives. Four case studies and a sensitivity analysis are conducted to verify the effectiveness of the proposed method. The case study results show that: in electricity minimization, 2–6.5% of total electricity bills can be saved; in main grid power consumption minimization, the peaks of the power consumption profiles are shaved while the valleys of the profiles are filled; in power quality enhancement, the steady state frequency drop is reduced for 0.35 Hz to 0.38 Hz. The sensitivity analysis shows that communities equipped with energy storage systems accounting for 30% of the total load can achieve best optimization outcomes; the increase in renewable energy usage will lead to higher electricity bills and poorer power quality if the renewable energy sources are limited, while the availability of more renewable energy sources will compensate for the negative effects of using renewable energy sources.
Keywords: Renewable energy management | Multi-agent system | Power scheduling | Residential consumers | Energy storage system
Predictive scheduling of wet flue gas desulfurization system based on reinforcement learning
برنامه ریزی پیش بینی سیستم گوگردزدایی گاز دودکش مرطوب بر اساس یادگیری تقویتی-2020
With the development of renewable energy, loads of thermal power units fluctuate, resulting in the trade- offbetween the frequent switching of auxiliary equipment and the economic-emission benefits in the wet flue gas desulfurization (WFGD) system. In this paper, the predictive scheduling problem is formalized, considering the power consumption, emission punishment and the switching frequency of slurry circula- tion pumps with finite prediction sequence of load and sulfur in coal. Model-free off-policy reinforcement learning (RL) is applied to solve the unclear and drifting system dynamic. Considering a real system, the framework setting and an emulator is introduced. Compared with traditional scheduling policies and the case without prediction, the proposed framework shows obvious advantages in terms of comprehensive performance and approximates the theoretical optimal solution at the steady-state. Moreover, the policy keeps the performance by adapting to the drifting without manual intervention, which demonstrates a broad application prospect in similar scenarios.
Keywords: WFGD system | Adaptive predictive scheduling | Reinforcement learning | Power plant | Operation optimization