Abstract--The problem of state estimation for unobservable distribution systems is considered. A Bayesian approach is proposed that implements Bayesian inference with a deep neural network to achieve the minimum mean squared error estimation of network states for real-time applications. The proposed technique consists of distribution learning for stochastic power injection, a Monte Carlo technique for the training of a deep neural network for state estimation, and a Bayesian bad data detection and cleansing algorithm. Structural characteristics of the deep neural networks are investigated. Simulations illustrate the accuracy of Bayesian state estimation for unobservable systems and demonstrate the benefit of employing a deep neural network. Numerical results show the robustness of Bayesian state estimation against modeling and estimation errors of power injection distributions and the presence of bad data. Comparing with pseudo-measurement techniques, direct Bayesian state estimation with deep neural networks outperforms existing benchmarks. We consider the problem of state estimation for distribution systems that have limited measurements. This problem is motivated by the need of coping with the rising presence of distributed energy resources (DER) in distribution systems.

We propose a multi-armed bandit algorithm that explores based on randomizing its history. The key idea is to estimate the value of the arm from the bootstrap sample of its history, where we add pseudo observations after each pull of the arm. The pseudo observations seem to be harmful. But on the contrary, they guarantee that the bootstrap sample is optimistic with a high probability. Because of this, we call our algorithm Giro, which is an abbreviation for garbage in, reward out. We analyze Giro in a $K$-armed Bernoulli bandit and prove a $O(K \Delta^{-1} \log n)$ bound on its $n$-round regret, where $\Delta$ denotes the difference in the expected rewards of the optimal and best suboptimal arms. The main advantage of our exploration strategy is that it can be applied to any reward function generalization, such as neural networks. We evaluate Giro and its contextual variant on multiple synthetic and real-world problems, and observe that Giro is comparable to or better than state-of-the-art algorithms.

Abstract-- The energy output of photovoltaic (PV) power plants depends on the environment and thus fluctuates over time. As a result, PV power can cause instability in the power grid, in particular when increasingly used. Limiting the rate of change of the power output is a common way to mitigate these fluctuations, often with the help of large batteries. A reactive controller that uses these batteries to compensate ramps works in practice, but causes stress on the battery due to a high energy throughput. In this paper, we present a deep learning approach that uses images of the sky to compensate power fluctuations predictively and reduces battery stress. In particular, we show that the optimal control policy can be computed using information that is only available in hindsight. Based on this, we use imitation learning to train a neural network that approximates this hindsight-optimal policy, but uses only currently available sky images and sensor data. We evaluate our method on a large dataset of measurements and images from a real power plant and show that the trained policy reduces stress on the battery. Photovoltaic (PV) power generation has grown at a rate of roughly 30% per year in recent years and reached a global capacity of over 400 GW at the end of 2017 [1].

Scientists have found a way to boost the battery life of your smartphone or tablet by several hours. They claim that shifting reams of data from your favourite apps to cloud storage services could cut the power they burn through by up to 60 per cent. Tools would identify the most power-hungry parts of a mobile app and then move them to the cloud using a technique called code-offloading. For an average smartphone with an average battery capacity, applying the technology to every app could extend the battery life by up to six hours in a'best-case scenario', researchers said. The technology could be used to build the next generation of disaster relief or search and rescue robots, where battery life is critical.

Adopting'Big Data technologies' – including advances in analytics, machine-learning and artificial intelligence – could help the upstream sector save $75 billion per year by 2023, Wood Mackenzie said in a report on Monday. Digitalisation in the development of oil and gas fields could take the form of better processing of seismic data or new understanding of well logs and chemical analysis. This would help producers discover new resources in existing acreage, or give a competitive advantage when bidding in...

When leaders describe how advances in automation will affect job prospects for humans, predictions typically fall into one of two camps. Optimists say that machines will free human workers to do higher-value, more creative work. Pessimists predict massive unemployment, or, if they have a flair for the dramatic, a doomsday scenario in which humans' only job is to serve our robot overlords. What almost everyone gets wrong is focusing exclusively on the idea of automation "replacing" humans. Simply asking which humans will be replaced fails to account for how work and automation will evolve.

The optimization of high dimensional functions is a key issue in engineering problems but it frequently comes at a cost that is not acceptable since it usually involves a complex and expensive computer code. Engineers often overcome this limitation by first identifying which parameters drive the most the function variations: non-influential variables are set to a fixed value and the optimization procedure is carried out with the remaining influential variables. Such variable selection is performed through influence measures that are meaningful for regression problems. However it does not account for the specific structure of optimization problems where we would like to identify which variables most lead to constraints satisfaction and low values of the objective function. In this paper, we propose a new sensitivity analysis that accounts for the specific aspects of optimization problems. In particular, we introduce an influence measure based on the Hilbert-Schmidt Independence Criterion to characterize whether a design variable matters to reach low values of the objective function and to satisfy the constraints. This sensitivity measure makes it possible to sort the inputs and reduce the problem dimension. We compare a random and a greedy strategies to set the values of the non-influential variables before conducting a local optimization. Applications to several test-cases show that this variable selection and the greedy strategy significantly reduce the number of function evaluations at a limited cost in terms of solution performance.

Astrimar is delighted to again be invited to be an EI media partner for their upcoming Interactive Conference on "Digital Transformation in the Oil and Gas Industry" to be held on the 6 December 2018 at the Aberdeen Exhibition and Conference Centre. The Energy Institute is holding this 1-day interactive conference to explore the adoption of digital technologies to transform the oil and gas industry to become better connected, more intelligent, efficient, reliable and sustainable. The use of data analytics, blockchain, internet of things (IoT) and artificial intelligence (AI) is increasingly important to keep up with the growing energy demand. Expertise and effective technology development and assurance are key to the successful implementation of these and other digital technologies. The workshop will facilitate discussion with digital companies and consultancies on the latest technologies, to explore how they can transform oil and gas operations with the potential positive impact on efficiency and costs.

Thank you for your lessons. But it is time we move on. I look forward to you and for the best things that are yet to come. "Everything remains as it never was" Change and transformation are the only constants, always driving us into the future, right from the time fire was discovered, the wheel was invented. Industries have been undergoing massive transformation right from the industrial revolution.

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from pixels and chooses actions through online planning in latent space. To achieve high performance, the dynamics model must accurately predict the rewards ahead for multiple time steps. We approach this problem using a latent dynamics model with both deterministic and stochastic transition function and a generalized variational inference objective that we name latent overshooting. Using only pixel observations, our agent solves continuous control tasks with contact dynamics, partial observability, and sparse rewards. PlaNet uses significantly fewer episodes and reaches final performance close to and sometimes higher than top model-free algorithms.