Assessing Energy Efficiency in Water Utilities Using Long-term Data Analysis

Silveira, Ana Paula Pereira da; Mata‐Lima, Herlander

doi:10.1007/s11269-021-02866-8

Cited by 8 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ensuring efficient water supply to the network requires pre-planning the operation mode of pumping stations (number of pumps in operation, their combinations, operating time, and sequence of switching on and off) and developing a control strategy for a given period of time (usually 24 h) to maintain the required pressure in the water supply network and to ensure the emergency status in the clean water reservoirs and the possibility of its restoration [5,6,[68][69][70][71]. Therefore, the daily WCPs, set taking into account the cyclic variations in water demand, are the basis for effective planning of pump operation schedules and the water supply process, as well as for adjusting pump operation schedules taking into account changes in consumer demand [72]. Usually, the total daily water consumption amount and its average and maximum values during the day are used as characteristics of water demand [5].…”

Section: Aspects Of the Energy-efficient Operation Of The Water Suppl...mentioning

confidence: 99%

“…Therefore, in order to plan the operation of water supply facilities, it is necessary to determine the management strategy in advance, considering water demand [27]. Under these conditions, one of the approaches to ensure effective water supply planning and adjust pumping operation schedules is to create a database of daily WCPs and analyze them to look for hidden regularities that determine the formation of water supply conditions [53,54,72].…”

Section: Aspects Of the Energy-efficient Operation Of The Water Suppl...mentioning

confidence: 99%

See 1 more Smart Citation

Efficient Energy Management for the Smart Sustainable City Multifloor Manufacturing Clusters: A Formalization of the Water Supply System Operation Conditions Based on Monitoring Water Consumption Profiles

Davydenko

Deja

et al. 2023

Energies

View full text Add to dashboard Cite

This study is devoted to improving the energy efficiency of urban infrastructure systems (UISs), in particular, the centralized water supply of a city multifloor manufacturing cluster (CMFMC), by developing the principles of effective energy consumption management. The CMFMCs are located in the residential area of a megapolis and include manufacturing and service enterprises, residential and non-residential buildings, and a city logistics node. Demand monitoring and identification of the influence of seasonal and social environmental factors on its fluctuations is considered as a tool for identifying changes in the operating conditions of the water supply system (WSS) for the CMFMC facilities. To identify the typical operating conditions of water supply facilities, an approach is proposed that involves the analysis of daily water consumption profiles (WCPs). The formation of a database, the formation of groups of the same type of daily WCPs, and the construction of typical daily WCPs for typical groups and their description are the main stages of the proposed approach. The database contains a set of classification characteristics that describe the daily water consumption and its unevenness, as well as the shape of the daily WCP. The principal component analysis was applied to determine the dominant components of daily water consumption. A set of morphometric parameters was used to describe the shape of the daily WCPs. The methods of cluster and discriminant analysis were used to identify the influence of seasonality and social factors on water consumption and to form groups of the same type of daily WCPs. The analysis of sets of similar type of daily WCPs for typical days of typical seasons was carried out for a formalized description of the typical operating conditions of water supply facilities. The results of the analysis are the clarification of the equations of the dominant components of daily water consumption, the determination of the average values of the characteristics of daily water consumption, and the construction and description of typical daily WCPs for typical operating conditions of water supply facilities. The research results were obtained on the basis of the data of the monitoring systems for water supply enterprises in Ukraine and Poland in 2021–2022. The obtained results are the basis for planning the water supply process and adjusting the operation modes of WSS pumping stations for the CMFMC, as well as planning power consumption for typical operating conditions, which will contribute to increasing the efficiency of water and electricity use.

show abstract

Section: Aspects Of the Energy-efficient Operation Of The Water Suppl...mentioning

confidence: 99%

Section: Aspects Of the Energy-efficient Operation Of The Water Suppl...mentioning

confidence: 99%

Efficient Energy Management for the Smart Sustainable City Multifloor Manufacturing Clusters: A Formalization of the Water Supply System Operation Conditions Based on Monitoring Water Consumption Profiles

Davydenko

Deja

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…However, the accurate prediction simplifies energy consumption which in turn reduces under -or an over-estimation [2]. A wrong prediction about energy use increases the financial impact on electricity supply, so the prices for electricity may grow high if the infrastructure is set up proportionally [3]. With energy consumption being taken for granted the supply of electricity may fall short, power systems may collapse and water supply systems would be disrupted.…”

Section: Introductionmentioning

confidence: 99%

Implementation of Machine Learning to Increase the Accuracy of Forecasting the Operating Modes of Deep-Sea Pumping Stations

Turchyn

2024

cit

View full text Add to dashboard Cite

This study endeavors at implementing ML algorithms that are capable of refining the forecast of operating modes of deep-water pumping stations which offshore processes draw their energy from. The classic forecasting methods often do not take into account the complexity of the underwater environment, and so they tend to show suboptimal efficiency, higher maintenance costs and of course wastage of resources. For this study, different ML algorithms including neural networks, support vector machines, random forests, gradient boosting, and linear regression are employed to evaluate how they can imagine operating circumstances under conditions of changes. The rental housing datasets, which contain historical operational data, environmental factors as well as system parameters, are applied to training and validation processes. Data illustrates enhanced capabilities of AI systems with leading candidates being neural network, random forests, and gradient boosting in demonstrating the exact relationships in the sample. The models deliver better performance than the traditional techniques, thereby allowing to assess in-depth the interaction scheme between environmental variables and working modes. These pivotal variables, depth, temperature and pump characteristics are among those that got scrutinized; therefore, insights as to what ought to be embraced for an efficient prediction. Comparative analyses bring forth the tradeoff between the model complexity and interoperability, which state that the algorithm chosen toward application must be thought out very wisely. Ensemble models, which contain a spectrum of different models with each one strong with its own abilities, are seen to be among the balanced way of making precise and useful forecasts. The deep sea water pumping stations developed model based on ML(ML) represents an example in practice that sets the framework for increased operational efficiency, reduced maintenance costs, and optimized resource utilization. The findings of this research uncover crucial aspect for engineers, researchers, as well as industry, experts who are prospects of deep-water resource extraction sector. This itself implies a transformation approach toward addressing the problems encountered in dynamic deep-sea environments. With developments in the area of ML, there is a lot of scope for future research ventures to explore new algorithms and real-time techniques which will help to further improve the forecasting capabilities and will certainly result in viable offshore operations. Thus, it can be said that the future of sustainable and resilient offshore operations can to some extent be credited to ML.

show abstract

Application of Machine Learning-based Energy Use Forecasting for Inter-basin Water Transfer Project

Kondolf

Sandoval-Solís

et al. 2022

Water Resour Manage

View full text Add to dashboard Cite

Energy use forecasting is crucial in balancing the electricity supply and demand to reduce the uncertainty inherent in the inter-basin water transfer project. Energy use prediction supports the reliable water-energy supply and encourages cost-effective operation by improving generation scheduling. The objectives are to develop subsequent monthly energy use predictive models for the Mokelumne River Aqueduct in California, US. Partial objectives are to (a) compare the model performance of a baseline model (multiple linear regression (MLR)) to three machine learning-based models (random forest (RF), deep neural network (DNN), support vector regression (SVR)), (b) compare the model performance of the whole system to three subsystems (conveyance, treatment, distribution), and (c) conduct sensitivity analysis. We simulate a total of 64 cases (4 algorithms (MLR, RF, DNN, SVR) x 4 systems (whole, conveyance, treatment, distribution) x 4 scenarios (different combinations of independent variables). We concluded that the three machine learning algorithms showed better model performance than the baseline model as they reflected non-linear energy use characteristics for water transfer systems. Among the three machine learning algorithms, DNN models yielded higher model performance than RF and SVR models. Subsystems performed better than the whole system as the models more closely reflected the unique energy use characteristics of the subsystems. The best case was having water supply (t), water supply (t-1), precipitation (t), temperature (t), and population (y) as independent variables. These models can help water and energy utility managers to understand energy performance better and enhance the energy efficiency of their water transfer systems.

show abstract

Assessing Energy Efficiency in Water Utilities Using Long-term Data Analysis

Cited by 8 publications

References 46 publications

Efficient Energy Management for the Smart Sustainable City Multifloor Manufacturing Clusters: A Formalization of the Water Supply System Operation Conditions Based on Monitoring Water Consumption Profiles

Efficient Energy Management for the Smart Sustainable City Multifloor Manufacturing Clusters: A Formalization of the Water Supply System Operation Conditions Based on Monitoring Water Consumption Profiles

Implementation of Machine Learning to Increase the Accuracy of Forecasting the Operating Modes of Deep-Sea Pumping Stations

Application of Machine Learning-based Energy Use Forecasting for Inter-basin Water Transfer Project

Contact Info

Product

Resources

About