Search

Electrochemical capacitors (ECs) have only recently been considered as an alternative power source for telemetry sensors of drilling equipment for geothermal or oil and gas exploration. The lifecycle analysis and modelling of ECs is underrepresented in literature in comparison to other storage devices e.g. Li-ion batteries. This paper investigates the degradation of ECs when cycled outside the manufacturer-specified operating temperature envelope and proposes a machine learning-based approach for modelling the degradation. Experimental results show that end of life, defined as a 30% decrease in capacitance, occurs at 1,000 cycles when the environmental temperature exceeds the maximum operating temperature by 30%. The life-cycle test data is then used as an input to a Gaussian process regression (GPR) algorithm to predict the capacitance fade trend. The GPR is validated on a total of nine commercial cells from two different manufacturers, achieving an average root mean squared percent error of less than 2% and a mean calibration score of 93% when referenced to a 95% confidence interval. The model can be utilized to determine the EC degradation rate at a range of operating temperature values.

Low Voltage (LV) networks are increasingly required to cope with challenges they were not designed for, requiring for more active network management (ANM). Crucially, ANM solutions require the availability of accurate network information. In practice, available data on LV networks can be incomplete, a problem often overlooked in prior ANM research. For example, in the U.K. and many developed countries, the lifetime of distribution networks assets spans several decades, with some of the available asset data gathered and maintained over many years. This can often lead to incomplete cable data being available to network operators. To overcome this, we propose a novel machine learning technique to autonomously approximate the missing cable information in LV networks. Our proposed algorithm uses a tree-based search methodology, which approximates the missing cable’s cross section area (XSA) data based on rules engineers used when designing the LV networks. We validate our approach using a large database of real LV networks, where some of the cables’ XSA are treated as unknown and used as ground truth to evaluate the accuracy of the predictions. Moreover, we propose a mechanism that scores the confidence level of the prediction, information which is then presented to the human network planners. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries power numerous systems from consumer electronics to electric vehicles, and thus undergo qualification testing for degradation assessment prior to deployment. Qualification testing involves repeated charge–discharge operation of the batteries, which can take more than three months if subjected to 500 cycles at a C-rate of 0.5C. Accelerated degradation testing can be used to reduce extensive test time, but its application requires a careful selection of stress factors. To address this challenge, this study identifies and ranks stress factors in terms of their effects on battery degradation (capacity fade) using half-fractional design of experiments and machine learning. Two case studies are presented involving 96 lithium-ion batteries from two different manufacturers, tested under five different stress factors. Results show that neither the individual (main) effects nor the two-way interaction effects of charge C-rate and depth of discharge rank in the top three significant stress factors for the capacity fade in lithium-ion batteries, while temperature in the form of either individual or interaction effect provides the maximum acceleration. [ABSTRACT FROM AUTHOR]

Recent years have seen an increasing interest in Demand Response (DR) as a means to provide flexibility, and hence improve the reliability of energy systems in a cost-effective way. Yet, the high complexity of the tasks associated with DR, combined with their use of large-scale data and the frequent need for near real-time decisions, means that Artificial Intelligence (AI) and Machine Learning (ML) — a branch of AI — have recently emerged as key technologies for enabling demand-side response. AI methods can be used to tackle various challenges, ranging from selecting the optimal set of consumers to respond, learning their attributes and preferences, dynamic pricing, scheduling and control of devices, learning how to incentivise participants in the DR schemes and how to reward them in a fair and economically efficient way. This work provides an overview of AI methods utilised for DR applications, based on a systematic review of over 160 papers, 40 companies and commercial initiatives, and 21 large-scale projects. The papers are classified with regards to both the AI/ML algorithm(s) used and the application area in energy DR. Next, commercial initiatives are presented (including both start-ups and established companies) and large-scale innovation projects, where AI methods have been used for energy DR. The paper concludes with a discussion of advantages and potential limitations of reviewed AI techniques for different DR tasks, and outlines directions for future research in this fast-growing area. • Review of Artificial Intelligence/Machine Learning for energy demand-side response. • Sub-areas of energy demand response for which AI/ML techniques have been used. • Discussion of pros and cons of using specific AI/ML techniques in each sub-area. • Insights into commercial initiatives/industrial R&D projects using AI techniques. • Discussion of the field's evolution and potential future research paths. [ABSTRACT FROM AUTHOR]