Utilities supplying electricity in urban areas tend to get inundated by customer complaints of power outage, low voltage and other issues during summers and monsoon. Telephone helplines manned by humans tend to be inaccessible as small groups of workers who man the helplines cannot respond to the flood of calls. The state-run Bengaluru Electricity Supply Company (Bescom), which supplies power to eight districts in Karnataka, has now turned to an artificial intelligence-powered system to service the over 9,000 complaints it receives on its helpline systems each day. Bescom is tying up with the Medical Intelligence and Language Engineering (or MILE) Lab at the Indian Institute of Science (IISc) to create an AI-based complaint response system than can cater to as many as 500 calls at a time -- much higher than the 60 under the system that the utility employs at present. "What we will have is a technology where when someone calls in the machine will take over and the machine will recognise whatever the speaker says whether it is in Kannada or English. It will understand the complaint -- whether it is with regard to a bill or power outage or concession for solar energy -- and find an answer from the server. It will then synthesise the answer again to text and convert to speech," said A G Ramakrishnan, the head of IISc's MILE.

Editor's Note: This is the first in a four-part series examining the growing role of machine learning and artificial intelligence in the power sector. Tomorrow, we look at how regional grid operators are using AI to optimize operations. The future of the electric grid is undoubtedly cleaner and more efficient and distributed, with hefty doses of technology and machine learning helping to operate it all. But if you're expecting a system dramatically transformed, experts say you'll be left waiting. Artificial intelligence and machine learning are already helping utilities run their networks more efficiently, extending the life of equipment and helping to dispatch energy into markets more efficiently.

Researchers in Switzerland have figured out how to use AI to predict when and where lightning will strike. Researchers from École Polytechnique Fédérale de Lausanne used standard meteorological data and machine learning to build a simple system that can predict lightning strike to the nearest 10 to 30 minutes inside a radius of about 18.6 miles, according to an account in Popular Mechanics. "We have used machine learning techniques to successfully hindcast nearby and distant lightning hazards by looking at single-site observations of meteorological parameters," wrote the authors in a new paper published recently in the journal Climate and Atmospheric Science. The researchers used data about past lightning strikes to build an algorithm that can make predictions about new lightning strikes, in a process called hindcasting, as opposed for forecasting. Estimates based on past events are fed into a model to see how well the output matches known results.

On 17 November, the first edition of the Mint Visionaries series, which seeks to delve into the minds of people inspiring a new future, was kicked off with entrepreneur-philanthropist Bill Gates, who is also the co-chair of the Bill and Melinda Gates Foundation, sharing his thoughts with Wipro Ltd chairman Rishad Premji. The two discussed the challenges of mitigating climate change, eliminating malnutrition, and improving the health and education infrastructure, besides the role of technology, such as artificial intelligence, for social inclusion, something Gates considers a mission statement. Rishad Premji: Climate change will be one of the defining challenges of the 21st century--the impact of weather events, rising sea level, islands getting flooded. It will affect the way people live and potentially impact health and mortality. There is a huge implication of climate change. I know you personally and the Gates Foundation is spending a lot on mitigation--on how to reduce carbon emission. I know you are spending time on breakthrough energy ventures in your personal capacity, investing in technology that can pay off, as well as around adaptation. What are you personally, and through Gates Foundation, doing in these areas? And, what can we do to learn how to leverage science and technology, as governments and as citizens, to be more informed about climate change and its impact, considering that we often have this debate on whether it is real. And, what can come out of it? Bill Gates: I am actually writing a book about climate change.

The recent progress in neural architectures search (NAS) has allowed scaling the automated design of neural architectures to real-world domains such as object detection and semantic segmentation. However, one prerequisite for the application of NAS are large amounts of labeled data and compute resources. This renders its application challenging in few-shot learning scenarios, where many related tasks need to be learned, each with limited amounts of data and compute time. Thus, few-shot learning is typically done with a fixed neural architecture. To improve upon this, we propose MetaNAS, the first method which fully integrates NAS with gradient-based meta-learning. MetaNAS optimizes a meta-architecture along with the meta-weights during meta-training. During meta-testing, architectures can be adapted to a novel task with a few steps of the task optimizer, that is: task adaptation becomes computationally cheap and requires only little data per task. Moreover, MetaNAS is agnostic in that it can be used with arbitrary model-agnostic meta-learning algorithms and arbitrary gradient-based NAS methods. Empirical results on standard few-shot classification benchmarks show that MetaNAS with a combination of DARTS and REPTILE yields state-of-the-art results.

Quantum computing is a computational paradigm with the potential to outperform classical methods for a variety of problems. Proposed recently, the Quantum Approximate Optimization Algorithm (QAOA) is considered as one of the leading candidates for demonstrating quantum advantage in the near term. QAOA is a variational hybrid quantum-classical algorithm for approximately solving combinatorial optimization problems. The quality of the solution obtained by QAOA for a given problem instance depends on the performance of the classical optimizer used to optimize the variational parameters. In this paper, we formulate the problem of finding optimal QAOA parameters as a learning task in which the knowledge gained from solving training instances can be leveraged to find high-quality solutions for unseen test instances. To this end, we develop two machine-learning-based approaches. Our first approach adopts a reinforcement learning (RL) framework to learn a policy network to optimize QAOA circuits. Our second approach adopts a kernel density estimation (KDE) technique to learn a generative model of optimal QAOA parameters. In both approaches, the training procedure is performed on small-sized problem instances that can be simulated on a classical computer; yet the learned RL policy and the generative model can be used to efficiently solve larger problems. Extensive simulations using the IBM Qiskit Aer quantum circuit simulator demonstrate that our proposed RL- and KDE-based approaches reduce the optimality gap by factors up to 30.15 when compared with other commonly used off-the-shelf optimizers.

Synthetic biology allows us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels or anticancer drugs. However, traditional synthetic biology approaches involve ad-hoc non systematic engineering practices, which lead to long development times. Here, we present the Automated Recommendation Tool ( ART), a tool that leverages machine learning and probabilistic modeling techniques to guide synthetic biology in a systematic fashion, without the need for a full mechanistic understanding of the biological system. Using sampling-based optimization, ART provides a set of recommended strains to be built in the next engineering cycle, alongside probabilistic predictions of their production levels. We demonstrate the capabilities of ART on simulated and real data sets and discuss possible difficulties in achieving satisfactory predictive power. 2 Introduction Metabolic engineering 1 enables us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels 2,3 or anticancer drugs.

We consider wireless transmission of images in the presence of channel output feedback. From a Shannon theoretic perspective feedback does not improve the asymptotic end-to-end performance, and separate source coding followed by capacity achieving channel coding achieves the optimal performance. Although it is well known that separation is not optimal in the practical finite blocklength regime, there are no known practical joint source-channel coding (JSCC) schemes that can exploit the feedback signal and surpass the performance of separate schemes. Inspired by the recent success of deep learning methods for JSCC, we investigate how noiseless or noisy channel output feedback can be incorporated into the transmission system to improve the reconstruction quality at the receiver. We introduce an autoencoder-based deep JSCC scheme that exploits the channel output feedback, and provides considerable improvements in terms of the end-to-end reconstruction quality for fixed length transmission, or in terms of the average delay for variable length transmission. To the best of our knowledge, this is the first practical JSCC scheme that can fully exploit channel output feedback, demonstrating yet another setting in which modern machine learning techniques can enable the design of new and efficient communication methods that surpass the performance of traditional structured coding-based designs.

With the ever-increasing reliance on data for data-driven applications in power grids, such as event cause analysis, the authenticity of data streams has become crucially important. The data can be prone to adversarial stealthy attacks aiming to manipulate the data such that residual-based bad data detectors cannot detect them, and the perception of system operators or event classifiers changes about the actual event. This paper investigates the impact of adversarial attacks on convolutional neural network-based event cause analysis frameworks. We have successfully verified the ability of adversaries to maliciously misclassify events through stealthy data manipulations. The vulnerability assessment is studied with respect to the number of compromised measurements. Furthermore, a defense mechanism to robustify the performance of the event cause analysis is proposed. The effectiveness of adversarial attacks on changing the output of the framework is studied using the data generated by real-time digital simulator (RTDS) under different scenarios such as type of attacks and level of access to data.

This paper presents an automated peer-to-peer negotiation strategy for settling energy contracts among prosumers in a Residential Energy Cooperative considering heterogeneity prosumer preferences. The heterogeneity arises from prosumers' evaluation of energy contracts through multiple societal and environmental criteria and the prosumers' private preferences over those criteria. The prosumers engage in bilateral negotiations with peers to mutually agree on periodical energy contracts/loans consisting of the energy volume to be exchanged at that period and the return time of the exchanged energy. The negotiating prosumers navigate through a common negotiation domain consisting of potential energy contracts and evaluate those contracts from their valuations on the entailed criteria against a utility function that is robust against generation and demand uncertainty. From the repeated interactions, a prosumer gradually learns about the compatibility of its peers in reaching energy contracts that are closer to Nash solutions. Empirical evaluation on real demand, generation and storage profiles -- in multiple system scales -- illustrates that the proposed negotiation based strategy can increase the system efficiency (measured by utilitarian social welfare) and fairness (measured by Nash social welfare) over a baseline strategy and an individual flexibility control strategy representing the status quo strategy. We thus elicit system benefits from peer-to-peer flexibility exchange already without any central coordination and market operator, providing a simple yet flexible and effective paradigm that complements existing markets.