Bidgely is an AI-powered SaaS Company that enables utilities to create greater business value and accelerate our path towards zero carbon by delivering personalized customer experience. Powered by our unique patented technology, Bidgely's UtilityAI platform transforms multiple dimensions of customer data - such as energy consumption, demographic, and interactions - into deeply accurate and actionable consumer energy insights. We leverage these insights to empower each customer with personalized recommendations, tailored to their individual personality and lifestyle, usage attributes, behavioral patterns, purchase propensity, and beyond. From smart thermostats to EV chargers, solar PVs or personalized / ToU tariffs, UtilityAI recommends new value-added products and services to the right customer at the right time. With roots in Silicon Valley, Bidgely has over 14 energy patents, $50M in funding, retains 30 data scientists, and brings a passion for AI to utilities serving residential customers around the world.

Bidgely CEO and Co-founder Abhay Gupta will deliver a keynote address at the inaugural Utility Analytics Institute Leadership Forum happening during Utility Analytics Week 2019, which will be held in Phoenix, Ariz., from October 21-25, 2019. Joined by top Bidgely executives in attendance, Gupta will highlight at the Leadership Forum how artificial intelligence (AI) can help utilities understand each consumer in depth to create a personalized energy experience during his keynote on October 22 at 9am local time, titled "Utility AI - Transitioning the Utility Business Model from Kilowatts to Kilobytes." This press release features multimedia. "Explanatory AI for the energy industry has become critical for empowering utilities to drive a hyper-personalized customer journey - guiding customers from engagement to experience to trust in their utility as a transformational digital brand," said Bidgely CEO Abhay Gupta. "Utility Analytics Week promises to be a powerful event for driving forward utilities into the next data-driven industrial revolution and placing them in the center of the new energy universe for consumers."

Reliance Jio has announced a new Artificial Intelligence (AI) based Video Call Assistant (Bot) at the ongoing India Mobile Congress (IMC) 2019. The new service aims to transform customer support and customer communication systems. According to the company, the assistant can be accessed via a 4G phone call, and customers don't need to install any app. The customer engagement video assistant solution has been developed by Jio in partnership with US-based company Radisys, a Reliance Industries Ltd subsidiary that provides open telecom solutions to service providers worldwide. The company says that with this new launch it will addressing the current customer pain points like endless call-hold music or seemingly never-ending IVR wait times.

Fully autonomous robots that are able to inspect damaged wind farms have been developed by Scots scientists. Unlike most drones, they don't require a human operator and could end the need for technicians to abseil down turbines to carry out repairs. The multi-million pound project is showing how the bots can walk, dive, fly and even think for themselves. They're being developed by Orca - the Offshore Robotics for Certification of Assets hub. The hub bills itself as the largest academic centre of its kind in the world and is led from Heriot-Watt and Edinburgh universities through its Centre for Robotics.

A plethora of problems in AI, engineering and the sciences are naturally formalized as inference in discrete probabilistic models. Exact inference is often prohibitively expensive, as it may require evaluating the (unnormalized) target density on its entire domain. Here we consider the setting where only a limited budget of calls to the unnormalized density oracle is available, raising the challenge of where in the domain to allocate these function calls in order to construct a good approximate solution. We formulate this problem as an instance of sequential decision-making under uncertainty and leverage methods from reinforcement learning for probabilistic inference with budget constraints. In particular, we propose the TreeSample algorithm, an adaptation of Monte Carlo Tree Search to approximate inference. This algorithm caches all previous queries to the density oracle in an explicit search tree, and dynamically allocates new queries based on a "best-first" heuristic for exploration, using existing upper confidence bound methods. Our non-parametric inference method can be effectively combined with neural networks that compile approximate conditionals of the target, which are then used to guide the inference search and enable generalization across multiple target distributions. We show empirically that TreeSample outperforms standard approximate inference methods on synthetic factor graphs.

Flooding is a destructive and dangerous hazard and climate change appears to be increasing the frequency of catastrophic flooding events around the world. Physics-based flood models are costly to calibrate and are rarely generalizable across different river basins, as model outputs are sensitive to site-specific parameters and human-regulated infrastructure. In contrast, statistical models implicitly account for such factors through the data on which they are trained. Such models trained primarily from remotely-sensed Earth observation data could reduce the need for extensive in-situ measurements. In this work, we develop generalizable, multi-basin models of river flooding susceptibility using geographically-distributed data from the USGS stream gauge network. Machine learning models are trained in a supervised framework to predict two measures of flood susceptibility from a mix of river basin attributes, impervious surface cover information derived from satellite imagery, and historical records of rainfall and stream height. We report prediction performance of multiple models using precision-recall curves, and compare with performance of naive baselines. This work on multi-basin flood prediction represents a step in the direction of making flood prediction accessible to all at-risk communities.

As a powerful tool to improve their efficiency and sustainability, most electricity systems worldwide are deploying advanced metering infrastructures to collect relevant operational data. In particular, smart meters play a key role in this transformation as they allow tracking electricity load consumption at a very disaggregated level and at high frequency rates. This data opens the possibility of developing new forecasting models with a potential positive impact in both electricity distribution and retailing activities. In this work, we present a general methodology that is able to process and forecast a large number of smart meter time series. Instead of using traditional and univariate approaches for each time series, we develop a single but complex recurrent neural network model with long short-term memory that is able to capture individual consumption patterns and also the cross-sectional relations among different households. The resulting model can accurately predict future loads (short-term) of individual consumers, even if these were not included in the original training set (out-of-sample consumers). This entails a great potential for large scale applications (Big Data) as once the single network is trained, accurate individual forecast for new consumers can be obtained at almost no computational cost. The performance of the proposed model is tested under a large set of numerical experiments by using a real world dataset with thousands of disaggregated electricity consumption time series. Furthermore, we exploit the considered dataset to explore how geo-demographic segmentation of consumers can improve the forecasting accuracy of the proposed model.

Neural Networks (NNs) are steering a new generation of artificial intelligence (AI) applications at the micro-edge. Examples include wireless sensors, wearables and cybernetic systems that collect data and process them to support real-world decisions and controls. For energy autonomy, these applications are typically powered by energy harvesters. As harvesters and other power sources which provide energy autonomy inevitably have power variations, the circuits need to robustly operate over a dynamic power envelope. In other words, the NN hardware needs to be able to function correctly under unpredictable and variable supply voltages. In this paper, we propose a novel NN design approach using the principle of pulse width modulation (PWM). PWM signals represent information with their duty cycle values which may be made independent of the voltages and frequencies of the carrier signals. We design a PWM-based perceptron which can serve as the fundamental building block for NNs, by using an entirely new method of realising arithmetic in the PWM domain. We analyse the proposed approach building from a 3x3 perceptron circuit to a complex multi-layer NN. Using handwritten character recognition as an exemplar of AI applications, we demonstrate the power elasticity, resilience and efficiency of the proposed NN design in the presence of functional and parametric variations including large voltage variations in the power supply.

The customer engagement video assistant solution has been developed by Reliance Jio in conjunction with US-based Radisys, a Reliance Industries Ltd subsidiary, a statement said. The video bot can be customised to meet various customer engagement requirements while providing a human-like interaction, and has the potential to revolutionise customer support and customer communication use cases, it added. "AI-based Jio Video Call Assistant empowers businesses and other users with a speedy and effortless resolution of repetitive queries from their customers, making their frontend communication smooth. It also helps brands to offer an efficient and effortless high-quality customer engagement experience," it said. In addition, the platform has an auto-learning feature that helps improve answering accuracy.

Berkeley Lab researchers Vahe Tshitoyan, Anubhav Jain, Leigh Weston, and John Dagdelen used machine learning to analyze 3.3 million abstracts from materials science papers. Sure, computers can be used to play grandmaster-level chess, but can they make scientific discoveries? Researchers at the U.S. Department of Energy's Lawrence Berkeley National Laboratory have shown that an algorithm with no training in materials science can scan the text of millions of papers and uncover new scientific knowledge. A team led by Anubhav Jain, a scientist in Berkeley Lab's Energy Storage & Distributed Resources Division, collected 3.3 million abstracts of published materials science papers and fed them into an algorithm called Word2vec. By analyzing relationships between words the algorithm was able to predict discoveries of new thermoelectric materials years in advance and suggest as-yet unknown materials as candidates for thermoelectric materials.