As power grids fill up with renewable energy, electric vehicle charging stations and customer-owned generation, they will become too complex and fast-moving for their human operators to keep up with, a group of international researchers warns. The humans will need help from smart machines -- high-performance computers running decisionmaking software systems built with artificial intelligence -- according to researchers at France's grid operator RTE, the U.S. Electric Power Research Institute (EPRI) and other partners. With the proliferation of low-carbon options, "the grid becomes exponentially more challenging to operate," said Jeremy Renshaw, EPRI's AI director. "Grid operators are already stretched to the limit. Getting AI resources to help is going to be critical."

Would you mind sending documentation on model evaluation, carbon footprint, and discrimination prevention controls by 4 pm to the regulatory relations team?" When running an ML or AI function in a regulated industry -- that is pretty much any very soon -- such requests will become more frequent. However, it is not just regulators driving the need for a procedural framework for ML/AI operations. Process and procedures become relevant when considering building AI teams, models, and organizations and running these organizations, justifying their design. This article will shed some light on helpful practices, misleading temptations, and an outlook on emerging aspects.

Encoder-decoder-based recurrent neural network (RNN) has made significant progress in sequence-to-sequence learning tasks such as machine translation and conversational models. Recent works have shown the advantage of this type of network in dealing with various time series forecasting tasks. The present paper focuses on the problem of multi-horizon short-term load forecasting, which plays a key role in the power system's planning and operation. Leveraging the encoder-decoder RNN, we develop an attention model to select the relevant features and similar temporal information adaptively. First, input features are assigned with different weights by a feature selection attention layer, while the updated historical features are encoded by a bi-directional long short-term memory (BiLSTM) layer. Then, a decoder with hierarchical temporal attention enables a similar day selection, which re-evaluates the importance of historical information at each time step. Numerical results tested on the dataset of the global energy forecasting competition 2014 show that our proposed model significantly outperforms some existing forecasting schemes.

Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs. However, most existing methods fail to recover realistic structures due to over-smoothing of fine-grained details. In this paper, we develop a voxel-based network for point cloud completion by leveraging edge generation (VE-PCN). We first embed point clouds into regular voxel grids, and then generate complete objects with the help of the hallucinated shape edges. This decoupled architecture together with a multiscale grid feature learning is able to generate more realistic on-surface details. We evaluate our model on the Figure 1: We propose an edge-guiding and voxel-based publicly available completion datasets and show that it point cloud completion network to reconstruct complete outperforms existing state-of-the-art approaches quantitatively points from incomplete inputs.

Fibre-optic Distributed Acoustic Sensing (DAS) is an emerging technology for vibration measurements with numerous applications in seismic signal analysis, including microseismicity detection, ambient noise tomography, earthquake source characterisation, and active source seismology. Using laser-pulse techniques, DAS turns (commercial) fibre-optic cables into seismic arrays with a spatial sampling density of the order of metres and a time sampling rate up to one thousand Hertz. The versatility of DAS enables dense instrumentation of traditionally inaccessible domains, such as urban, glaciated, and submarine environments. This in turn opens up novel applications such as traffic density monitoring and maritime vessel tracking. However, these new environments also introduce new challenges in handling various types of recorded noise, impeding the application of traditional data analysis workflows.

Multivariate time series (MTS) prediction plays a key role in many fields such as finance, energy and transport, where each individual time series corresponds to the data collected from a certain data source, so-called channel. A typical pipeline of building an MTS prediction model (PM) consists of selecting a subset of channels among all available ones, extracting features from the selected channels, and building a PM based on the extracted features, where each component involves certain optimization tasks, i.e., selection of channels, feature extraction (FE) methods, and PMs as well as configuration of the selected FE method and PM. Accordingly, pursuing the best prediction performance corresponds to optimizing the pipeline by solving all of its involved optimization problems. This is a non-trivial task due to the vastness of the solution space. Different from most of the existing works which target at optimizing certain components of the pipeline, we propose a novel evolutionary ensemble learning framework to optimize the entire pipeline in a holistic manner. In this framework, a specific pipeline is encoded as a candidate solution and a multi-objective evolutionary algorithm is applied under different population sizes to produce multiple Pareto optimal sets (POSs). Finally, selective ensemble learning is designed to choose the optimal subset of solutions from the POSs and combine them to yield final prediction by using greedy sequential selection and least square methods. We implement the proposed framework and evaluate our implementation on two real-world applications, i.e., electricity consumption prediction and air quality prediction. The performance comparison with state-of-the-art techniques demonstrates the superiority of the proposed approach.

The transition from conventional methods of energy production to renewable energy production necessitates better prediction models of the upcoming supply of renewable energy. In wind power production, error in forecasting production is impossible to negate owing to the intermittence of wind. For successful power grid integration, it is crucial to understand the uncertainties that arise in predicting wind power production and use this information to build an accurate and reliable forecast. This can be achieved by observing the fluctuations in wind power production with changes in different parameters such as wind speed, temperature, and wind direction, and deriving functional dependencies for the same. Using optimized machine learning algorithms, it is possible to find obscured patterns in the observations and obtain meaningful data, which can then be used to accurately predict wind power requirements . Utilizing the required data provided by the Gamesa's wind farm at Bableshwar, the paper explores the use of both parametric and the non-parametric models for calculating wind power prediction using power curves. The obtained results are subject to comparison to better understand the accuracy of the utilized models and to determine the most suitable model for predicting wind power production based on the given data set.

In yet another step toward running its operations entirely on carbon-free energy sources by 2030, Google is now deploying machine learning technology that will help automatically shift workloads between data centers, depending on the availability of renewable energy resources, which can vary by type, location or the time of day. The move is part of Google's plan to transition to what it calls Carbon-Intelligent Compute Management, a system that will use artificial intelligence to automatically maximize clean electricity use across their data centers -- and therefore minimize the carbon footprint and operational costs. The system functions by delaying non-urgent workloads that aren't time-sensitive, such as encoding and analyzing videos that are uploaded to YouTube, or processing images that are uploaded to Google Photos and Drive. The company says that these "temporally flexible" tasks will still be completed within 24 hours, while critical production tasks and user-facing services that need to run around the clock -- such as Search, Maps, YouTube and cloud customers' workloads running in allocated Virtual Machines (VMs) -- will not be changed by the new system. "Workloads are comprised of compute jobs," explained the team of Google engineers in their recent paper on the new platform.

AI Researcher, Cognitive Technologist Inventor - AI Thinking, Think Chain Innovator - AIOT, XAI, Autonomous Cars, IIOT Founder Fisheyebox Spatial Computing Savant, Transformative Leader, Industry X.0 Practitioner Efforts to make the algorithms more explainable could also help utility operators interpret their outputs. This could, help create solar fuels, which can store energy from sunlight, or identify more efficient carbon dioxide absorbents or structural materials that take a lot less carbon to create. Algorithms can improve battery energy management to increase the mileage of each charge and reduce "range anxiety," 5. Help make buildings more efficient, A smart building could communicate directly with the grid to reduce how much power it is using if there's a scarcity of low-carbon electricity supply at any given time. Nudge consumers to change how we shop, Techniques that advertisers have successfully used to target consumers can be used to help us behave in more environmentally aware ways. Consumers could receive tailored interventions to promote their enrollment in energy saving programs.

Convolutional Neural Networks (CNNs) are widely used in deep learning applications, e.g. visual systems, robotics etc. However, existing software solutions are not efficient. Therefore, many hardware accelerators have been proposed optimizing performance, power and resource utilization of the implementation. Amongst existing solutions, Field Programmable Gate Array (FPGA) based architecture provides better cost-energy-performance trade-offs as well as scalability and minimizing development time. In this paper, we present a model-independent reconfigurable co-processing architecture to accelerate CNNs. Our architecture consists of parallel Multiply and Accumulate (MAC) units with caching techniques and interconnection networks to exploit maximum data parallelism. In contrast to existing solutions, we introduce limited precision 32 bit Q-format fixed point quantization for arithmetic representations and operations. As a result, our architecture achieved significant reduction in resource utilization with competitive accuracy. Furthermore, we developed an assembly-type microinstructions to access the co-processing fabric to manage layer-wise parallelism, thereby making re-use of limited resources. Finally, we have tested our architecture up to 9x9 kernel size on Xilinx Virtex 7 FPGA, achieving a throughput of up to 226.2 GOp/S for 3x3 kernel size.