Machine learning driven smart electric power systems: Current trends and new perspectives

Describing methods whereby high quality sound reproduction in auditory perspective can be accomplished over long distances, this discussion centers largely upon a description of the exact technique employed in providing communication transmission circuits for the Philadelphia-Washington demonstration. Problems that might be involved in carrying out such transmission on a more widespread scale also are touched upon.

http://ieeexplore.ieee.org/iel7/6731005/6772223/06772230.pdf

Transmission lines

Trash deposits in aquatic environments have a destructive effect on marine ecosystems and pose a long-term economic and environmental threat. Autonomous underwater vehicles (AUVs) could very well contribute to the solution of this problem by finding and eventually removing trash. This paper evaluates a number of deep-learning algorithms performing the task of visually detecting trash in realistic underwater environments, with the eventual goal of exploration, mapping, and extraction of such debris by using AUVs. A large and publicly-available dataset of actual debris in open-water locations is annotated for training a number of convolutional neural network architectures for object detection. The trained networks are then evaluated on a set of images from other portions of that dataset, providing insight into approaches for developing the detection capabilities of an AUV for underwater trash removal. In addition, the evaluation is performed on three different platforms of varying processing power, which serves to assess these algorithms’ fitness for real-time applications.

Robotic Detection of Marine Litter Using Deep Visual Detection Models

This paper presents a novel garbage pickup robot which operates on the grass The robot is able to detect the garbage accurately and autonomously by using a deep neural network for garbage recognition In addition, with the ground segmentation using a deep neural network, a novel navigation strategy is proposed to guide the robot to move around With the garbage recognition and automatic navigation functions, the robot can clean garbage on the ground in places like parks or schools efficiently and autonomously Experimental results show that the garbage recognition accuracy can reach as high as 95%, and even without path planning, the navigation strategy can reach almost the same cleaning efficiency with traditional methods Thus, the proposed robot can serve as a good assistance to relieve dustman's physical labor on garbage cleaning tasks

Deep Learning Based Robot for Automatically Picking up Garbage on the Grass

This paper presents a novel garbage pickup robot which operates on the grass. The robot is able to detect the garbage accurately and autonomously by using a deep neural network for garbage recognition. In addition, with the ground segmentation using a deep neural network, a novel navigation strategy is proposed to guide the robot to move around. With the garbage recognition and automatic navigation functions, the robot can clean garbage on the ground in places like parks or schools efficiently and autonomously. Experimental results show that the garbage recognition accuracy can reach as high as 95%, and even without path planning, the navigation strategy can reach almost the same cleaning efficiency with traditional methods. Thus, the proposed robot can serve as a good assistance to relieve dustman’s physical labor on garbage cleaning tasks.

Deep Learning Based Robot for Automatically Picking Up Garbage on the Grass

As a large number of distributed devices are connected to the modern smart grid, the traditional centralized connectivity models fail to provide economic value. These models have relied on sending data to the cloud for processing and receiving commands to exert control actions, resulting in an “on-demand system” with high bandwidth, low latency, and an overload of data on the cloud. For realizing a decentralized system, there is a strong need to embed intelligence at the “edge of the network.” These intelligent devices, capable of sensing, local data processing, and exerting control actions, report only actionable information to the cloud, acting as an edge control node. The system can then function autonomously, without constant cloud inputs, tolerating longer delays in communication, and making the overall system ultralow cost. The global asset monitoring, management, and analytics platform is a novel ultralow-cost, secure platform that operates through a Bluetooth-based delay tolerant network. It relies on so-called “data mules” to bridge the last mile connectivity gap in an inherently secure way. Due to this model, the platform requires no in-country certifications, does not rely on a dedicated backhaul technology and is immune to technology migration. This architecture also addresses some gaps identified in traditional Internet of Things-based solutions in remote areas and sparse connectivity. A functional unit of the edge computing node has been built, taking into account various constraints like costs, customizations, data storage, cybersecurity, and power management. The platform has been built, deployed and has demonstrated distributed smart grid applications like power quality sensing, automated metering infrastructure, and utility asset monitoring.

Enabling a Decentralized Smart Grid Using Autonomous Edge Control Devices

Autrebot; indoor trash detection and collection system using autonomously directed robotic exploration algorithm is presented. The algorithm has linear time complexity and is developed using two ultrasonic sensors. The key feature of this algorithm is the acquisition of object location based on the sensor output. The two sensor interface is specially implemented for intelligent decision making and proper identification of the object of interest, ignoring stray mobile objects or walls. Pneumatic actuators are used for the pickup and disposal of trash once it has been successfully located. Experiments with the algorithm have been conducted in static as well as dynamic environments and its performance analyzed for multiple scenarios. The algorithm can be thus extended for locating a particular object of interest based on its physical attributes.

Robot based indoor autonomous trash detection algorithm using ultrasonic sensors

This paper presents the design and implementation of an advanced metering infrastructure (AMI) platform based on a Bluetooth and a delay tolerant network (DTN) architecture, which has virtually zero cost of communication. The platform is ultra-low-cost, secure, and globally compliant making it suitable for deployment in emerging markets for rural electrification, offering ‘pay-as-you-go (PAYGO)’ billing, remote disconnect and advanced functions such as power factor correction. Intelligence embedded in the edge devices can execute certain control actions autonomously, based on locally measured parameters. The devices are capable of duplex communication, relaying data to the cloud and executing cloud-driven control commands. The cloud-based analytics engine also provides additional value streams that can be unlocked by electric utilities. The AMI platform is suitable for providing higher, event driven visibility into the distribution network. The smart meter itself requires minimal country-specific certification, and is easy to install in the field, making the platform well suited for global deployment.

A Novel Approach to Implement Low-Cost AMI Functionality using Delay-Tolerant Communication

Rogowski coil current sensors are popular solutions for current sensing having several advantages over current transformers (CTs), including size, bandwidth and dynamic range. These sensors have been used by electric utilities for gaining visibility into the electric grid directly helping in grid operations. This paper presents an overview of the design principles and test results for a PCB-based Rogowski coil that can be retrofitted around any existing conductor, resulting in a sensor that can be rapidly installed in the field. Due to the absence of any magnetic components in the coil, Rogowski coils cannot saturate and thus have a very high dynamic range, only limited by the accompanying signal conditioning or data converter circuits. In order to prevent saturation of the signal conditioning stage at higher current levels, a method to auto-tune the sensor has been presented, resulting in a dynamic range that is orders of magnitude higher than state of the art. The method, called dynamic range correction (DRC), uses edge intelligence to detect fault current scenarios and adjust the analog circuit to prevent saturation or distortion, while capturing the fault current waveforms. This feature enables post-event diagnostics for electric utilities at a very low cost.

An Edge-Intelligent, Clip-on Rogowski Current Sensor With Wide Dynamic Range

As the electric grid transitions into a highly distributed and intelligent grid, electric utilities are becoming increasingly concerned with monitoring the health and performance of their distribution assets. As Internet of Things technologies and data analytics become inexpensive and ubiquitous, low-cost asset monitoring becomes more feasible. Moreover, using edge analytics, computations can be off-loaded to these intelligent sensors to report only actionable information to the cloud. This needs to be done in a highly distributed manner using non-intrusive sensors and device physics that seamlessly integrates with legacy infrastructure. This paper reviews existing sensor based solutions, identifies their issues, proposes a novel solution by exploring the required attributes and proposes an approach for low-cost distribution transformer health monitoring.

Shreyas Kulkarni

Papers

Enabling a Decentralized Smart Grid Using Autonomous Edge Control Devices

Robot based indoor autonomous trash detection algorithm using ultrasonic sensors

A Novel Approach to Implement Low-Cost AMI Functionality using Delay-Tolerant Communication

An Edge-Intelligent, Clip-on Rogowski Current Sensor With Wide Dynamic Range

Asset Monitoring using Smart Sensing and Advanced Analytics for the Distribution Network