Forecasting the Municipal Solid Waste Using GSO-XGBoost Model

Waste production rises in tandem with population growth and increased utilization.The indecorous disposal of waste paves the way for huge disaster named as climate change.The National Environment Agency(NEA)of Singapore oversees the sustainable management of waste across the country.The three main contributors to the solid waste of Singapore are paper and cardboard(P&C),plastic,and food scraps.Besides,they have a negligible rate of recycling.In this study,Machine Learning techniques were utilized to forecast the amount of garbage also known as waste audits.The waste audit would aid the authorities to plan their waste infrastructure.The applied models were k-nearest neighbors,Support Vector Regressor,ExtraTrees,CatBoost,and XGBoost.The XGBoost model with its default parameters performed better with a lower Mean Absolute Percentage Error(MAPE)of 8.3093(P&C waste),8.3217(plastic waste),and 6.9495(food waste).However,Grid Search Optimization(GSO)was used to enhance the parameters of the XGBoost model,increasing its effectiveness.Therefore,the optimized XGBoost algorithm performs the best for P&C,plastics,and food waste with MAPE of 4.9349,6.7967,and 5.9626,respectively.The proposed GSO-XGBoost model yields better results than the other employed models in predicting municipal solid waste.

Energy cost minimization through optimization of EV, home and workplace battery storage

Besides grid-to-vehicle(G2 V) and vehicle-to-grid(V2 G) functions, the battery of an electric vehicle(EV) also has the specific feature of mobility. This means that EVs not only have the potential to utilize the storage of cheap electricity for use in high energy price periods, but can also transfer energy from one place to another place. Based on these special features of an EV battery, a new EV energy scheduling method has been developed and is described in this article. The approach is aimed at optimizing the utilization EV energy for EVs that are regularly used in multiple places. The objective is to minimize electricity costs from multiple meter points. This work applies real data in order to analyze the effectiveness of the method. The results show that by applying the control strategy presented in this paper at locations where the EVs are parked, the electricity cost can be reduced without shifting the demand and lowering customer's satisfaction. The effects of PV size and number of EVs on our model are also analyzed in this paper. This model has the potential to be used by energy system designers as a new perspective to determine optimal sizes of generators or storage devices in energy systems.

OPTIMAL COARSE GRID SIZE IN DOMAIN DECOMPOSITION

In most domain decomposition (DD) methods, a coarse grid solve is employed to provide the global coupling required to produce an optimal method. The total cost of a method can depend sensitively on the choice of the coaxse grid size H. In this paper, we give a simple analysis of this phenomenon for a model elliptic problem and a variant of Smith's vertex space domain decomposition method [11, 3]. We derive the optimal value Hopt which asymptotically minimises the total cost of method (number of floating point operations in the sequential case and execution time in the parallel case), for subdomain solvers with different complekities. Using the value of Hopt, we derive the overall complexity of the DD method, which can be significantly lower than that of the subdomain solver