Western Power Distribution (United Kingdom)

This article used Random forest (RF) classifier, decision tree (DT) classifier, K-nearest neighbors (KNN) classifiers, extra tree (ET) classifier and extreme gradient boosting (XGB) classifier for fault prediction and classification in power distribution transformer to predict the phase line voltages, line currents, line-to-line voltages, neutral current, ambient temperature indicator, oil temperature indicator, oil level indicator, and various other alarm indicators like oil temperature indicator trip oil temperature indicator alarm and magnetic oil guage alarm. The findings demonstrate that XGB and ET classifier, provide superior predictive capabilities compared to other methods.

Abstract AIBTBF (Artificial Intelligence and Big data Techniques Based Framework) is a framework designed to enhance the DSS (Decision Support System) of MDAS (Metering Data Acquisition System) in electricity consumption for improved energy efficiency. The core processes of the Revenue Management System (RMS) i.e., Metering, Billing, and collection (Mare) are addressed in the context of the Electricity Consumption. This paper proposed an efficient framework after reviewing & analyzing various methods in practice along with their impacts on electricity consumption. The framework integrates Information Technology (IT) with Operation Technology (OT) of the electrical system to handle the challenges of high volume of data that needs velocity in processing and accumulated variety of data in structured, semi-structured, and unstructured variables. The proposed framework implemented big data analytics and artificial intelligence to enhance the decision support system with real-time accurate and effective decisions. The direct variables for energy efficiency i.e. billing efficiency and collection efficiency are minutely studied in context with IoT techniques. Key indicators for energy efficiency and demand management are also studied to achieve the primary goals of the distribution companies to provide quality supply 24X7 to their valued consumers. It introduces novel methodologies by integrating external factors like weather conditions, seasonal and geographical diversity and socio-economic indicators into predictive models, thereby addressing gaps in traditional forecasting approaches. The framework is structured into four key parts: Extraction & Preparation, Transformation, Analysis, and Suggestions & Recommendations Generation. The paper analyzes the current emerging techniques with limitations and suggested recommendations for best use case scenarios in the prediction and optimization of the existing business process. The contributions of the framework include Efficient data management and processing from diverse sources. Advanced analysis using deep learning algorithms for forecasting and optimization. Real-time decision support for energy management and operational efficiency. Reduction of commercial and technical losses in power distribution. Similarly, the proposed framework uses MapReduce and Parallelization packages. The data is stored at the data lake on HDFS. The framework is evaluated through a series of practical case studies and performance metrics, demonstrating its effectiveness in improving energy management and operational processes. AIBTBF framework not only meets the primary goals of reducing technical and commercial losses but also provides a scalable solution for modernizing legacy systems in power distribution.

TAQA Distribution Company in Al Ain City currently uses a Siemens Spectrum 7 system for monitoring and controlling its power network, which was upgraded from the older Spectrum 4.4. The system now includes 439 monitoring stations connected to the SCADA system via remote terminal units (RTUs) and fully controlled from the control room, alongside approximately 4330 non-monitoring stations. The primary challenge encountered is fault detection and receiving tripping signals from the non-monitoring stations, which make up about 90% of the total stations. To identify unplanned outages in these areas, the company often relies on customer complaints through the call center. This approach results in significant delays in addressing power interruptions at non-monitoring stations, ultimately impacting the company's overall performance. This paper discusses the shift from traditional fault detection methods to a smarter, more efficient approach by leveraging the advanced capabilities of the Siemens Spectrum 7, incorporating the Advanced Distribution Management System (ADMS) and several supporting applications and technologies.

Every substation in a power grid system has its own sewerages to convey the storm water or rainwater into the environment. However, when the pumping station does not work on time, the water level may significantly rise causing the flooding of the electrical equipment and consequently its damage. Therefore, keeping track of the water level inside the sewerage system and controlling the pump on time can prevent unexpected errors in the power grids. This paper proposes an Internet of Things (IoT) based water level monitoring and controlling system to solve the issue. This research model is applied at 220 kV Tra Noc substation, in Vietnam to prevent flooding in the rainy season on during the high tide days. The proposed system is a low-cost in design and easy to maintenance. The system operates reliably and efficiently, serving as a basic solution for flooding prevention to substations experiencing similar flooding.

This paper addresses the impact of the increasing penetration of renewable solar photovoltaic (PV) in the power distribution grids. A collaborative project between the university and the local power distribution grid-s operator (PDO) led to this assessment, which addressed the operator-s specific concerns about how renewable energy-based generators might affect the power quality (PQ) in its grid system. There was evaluated the interaction between PV prosumers' installations and the hosting low voltage (LV) network, specifically the variations in voltage produced or amplified by prosumers, as well as the events experienced by these ones. For the purpose of the analysis, one-weekinterval PQ measurement have been processed at the outputs of real PV prosumers located in the LV network, as well as at the LV buses of the supplying substations. The behavior of different solar inverter technologies in the power grid is also examined. The bi-directional prosumer-grid influence is analyzed and the origin of PQ events are estimated. Measurements-based observations revealed a shared responsibility between PV generation conditions, solar inverter operation, and the hosting power grid. Lastly, general conclusions about measurement, analysis, and mitigation are provided.

This paper presents a Western Power Distribution network innovation allowance (NIA) project that utilises Long Term Evolution (LTE) technology for multi service and multi-vendor connectivity to a range of distributed energy network assets. The trial LTE system covers a 25km radius from the central base station located in Taunton, South West England on the Western Power Distribution (WPD) network. Greater awareness of distributed energy network flows, more active management and interconnectivity control are creating more challenges as the power network facilitates flexibility in services by dynamically adding, removing power or time shifting energy demand customers. In order to manage this new energy landscape and support legacy assets, new communication technologies must be investigated. As the electricity distribution system evolves, there is a need for enhanced real time monitoring and control to facilitate real time asset monitoring. This communication must support many application characteristics: throughput, quality of service, latency and redundancy while balancing economic and investment dimensions in order to deliver maximum value for the end service user.

The rapid growth of power electronics-based devices over the past years has increased the harmonics distortion along the power grid. This phenomenon may pose challenges to distribution network operators for managing harmonic levels. This paper proposes an approach to use grid-connected photovoltaic inverters as active filters. The proposed control algorithm consists of a proportional resonance controller for the inner current loop, notch filter for harmonic extraction and an automatic gain functionality to assist the state of the inverter. Active filter operation is activated based on irradiance conditions and system harmonic levels. The main contributions of this work consist in: applying this control scheme to multiple inverters connected at different locations, and using real irradiance and load data to assess the benefits of the proposed application.

This study describes the impact of short-circuit level on medium-voltage (MV) networks resulting from the increase in low-carbon technology (LCT) integration on the UK transmission and distribution network. Fault level (FL) is an important network measure that can instigate network investment and is expected to change as a result of LCT connections such as renewable resources, combined heat and power plants, storage units and electric vehicles connecting to the network. FL is anticipated to reduce in transmission networks and increase in low-voltage and MV distribution networks. The impact on FL variation due to LCT uptake in MV networks is investigated as part of FlexDGrid, an innovation project in the UK by Western Power Distribution investigating the fault level issues and mitigation techniques on MV networks.

Distribution losses can be difficult to measure when the loss power has a similar proportion to monitoring equipment sensor tolerances. Measurements for the Western Power Distribution Losses Investigation project have addressed this problem by using high resolution demand measurements combined with loss calculations with an I2R method. This is combined with additional measurements to verify accuracy of the network database used to calculate losses in each network branch.