There are often planned (for example, regular maintenance) and unplanned (for example, pipe bursts) interruptions in a water distribution network (WDN). Therefore, part of the isolation valves must be closed to isolat...
详细信息
There are often planned (for example, regular maintenance) and unplanned (for example, pipe bursts) interruptions in a water distribution network (WDN). Therefore, part of the isolation valves must be closed to isolate the part (segment) of the network that contains one or more pipes. Isolation of the target pipe segment with minimum possible disruption has been a problem to be solved. A large number of studies have been conducted to optimize the design of isolation valve placement in new WDNs, but less attention has been given to reducing the isolation zone and improving the reliability of old WDNs by adding optimally placed isolation valves. Therefore, this paper proposes a multiobjective optimization model for adding optimally located isolation valves to old WDNs, which considers the dual objectives of economy and reliability. The installation or removal of isolation valves can cause the original segments to split or merge, so this paper proposes the use of the segment-valve (SV) graph local update (SVLU) algorithm instead of the seed-filling algorithm to construct the SV graph. The optimization model was applied to the valve layout modification of part of the WDN in Changshu, Jiangsu Province, China, and the results showed that the model can solve the optimization solution quickly (15.358 s). Moreover, the use of the SVLU algorithm improved the efficiency of the solved model by 26.71%.
The most common methods to detect non-technical losses involve Deep Learning-based classifiers and samples of consumption remotely collected several times a day through Smart Meters (SMs) and Advanced Metering Infrast...
详细信息
The most common methods to detect non-technical losses involve Deep Learning-based classifiers and samples of consumption remotely collected several times a day through Smart Meters (SMs) and Advanced Metering Infrastructure (AMI). This approach requires a huge amount of data, and training is computationally expensive. However, most energy meters in emerging countries such as Brazil are technologically limited. These devices can measure only the accumulated energy consumption monthly. This work focuses on detecting energy theft in scenarios without AMI and SM. We propose a strategy called HyMOTree intended for the hyperparameter tuning of tree-based algorithms using different multiobjective optimization strategies. Our main contributions are associating different multiobjective optimization strategies to improve the classifier performance and analyzing the model's performance given different probability cutoff operations. HyMOTree combines NSGA-II and GDE-3 with Decision Tree, Random Forest, and XGboost. A dataset provided by a Brazilian power distribution company CPFL ENERGIA (TM) was used, and the SMOTE technique was applied to balance the data. The results show that HyMOTree performed better than the random search method, and then, the combination between Random Forest and NSGA-II achieved 0.95 and 0.93 for Precision and F1-Score, respectively. Field studies showed that inspections guided by HyMOTree achieved an accuracy of 76%.
The (minimizing) achievement function of the traditional Goal Programming (GP) model has five basic forms: ni,pi,(ni+pi),(n-pi),and (pi-ni),where ni and pi are nonnegative under and over achievement variables in t...
详细信息
ISBN:
(纸本)9781424436712
The (minimizing) achievement function of the traditional Goal Programming (GP) model has five basic forms: ni,pi,(ni+pi),(n-pi),and (pi-ni),where ni and pi are nonnegative under and over achievement variables in the ith goal-constraint. Zhang and Shang (2001) proposed the theory of Goal Programs with -ni,-pi and -(ni+pi) goals, which has many interesting and practical applications. This paper extends the theory further into the nonlinear situation and proposes a new algorithm for solving the ensuing nonconvex nonlinear program. Results obtained in this paper shows that the basic conclusions for the linear GP model still hold for the nonlinear case.
暂无评论