Elsevier

Biomass and Bioenergy

Volume 132, January 2020, 105420
Biomass and Bioenergy

Optimization of the energy consumption in activated sludge process using deep learning selective modeling

https://doi.org/10.1016/j.biombioe.2019.105420Get rights and content

Highlights

  • High values of performance criteria in training and testing period

  • Determination of three classes of energy consumption: Underconsumption, overconsumption and optimal consumption.

  • Determination of warning limits of overconsumption of energy.

Abstract

This paper presents a method using an artificial neural network for creating an optimal model of energy consumption in wastewater treatment plant (WWTP) using activated sludge process. The advantage of this method is the use data usually measured in most of WWTP to optimize the energy consumption of the biological process. This method consists of selecting the data that represent the best energy consumption using different performance criteria then use this data to train a deep neural network. The procedure of selection is divided into two parts, in the first selection we selected the data that respect the environmental standards, and in the second part we selected the data with optimal energy consumption using different pollution indicators, and this data was used to train a deep neural network, finally the best model was used to estimate the energy savings on the data not selected. The model showed good results with a coefficient of determination that varies between 90% and 92% in training period and 74%–82% in testing period, the application of the best model on the data not selected showed a gain in energy for the most of the data.

Introduction

During the past twenty years, the number of papers about energy saving in wastewater treatment plant increases, and it shows the lack of tools for management and optimization of energy consumption. in the United States, 4% of electric energy is consumed by WWTP and the water sector [1], and in Europe, the WWTP's consume about 27 TWh/year [2]. Energy costs represent approximately 28% of wastewater costs [3]. It has been estimated that energy used in the WWTPs comprises around one-fifth of a municipality's total energy use by public utilities, and it will continue to rise by 20% in the next 15 years with the increasing water consumption and more stringent regulations [3,4]. The aeration process in secondary treatment is the highest energy consumption part of the wastewater treatment technology [3,5]. In most medium and large WWTPs with Conventional Activated Sludge systems, aeration takes up approximately 50–60% of all electricity consumption, while sludge treatment consumes 15–25% of energy, followed by secondary sedimentation including recirculation pumps (15%) [3,6].

Despite the use of various datasets and methodologies, studies concerning the WWTP energy efficiency agree on a specific point: the WWTPs are generally not efficient and a relevant energy-saving potential can be exploited [7][8]. The majority of WWTP in the world uses conventional activated sludge process, and a viable model of optimization of energy consumption would have the widest range of application, and it would be interesting in an economic and environmental point of view. It could also allow electricity generation from biomass technologies to be considered as an alternative to satisfy completely or a major part of the energy demand of WWTPs [9].

In Ref. [10] Nguyen et al. worked on optimization of aeration time using activated sludge model (ASM1) and benchmark simulation model (BSM1), the results showed 70% of gain in energy consumption for a small WWTP, and 30% for large WWTP, the main disadvantage of this method is the necessity of relative precise measures that describe the variation of physicochemical characteristics and the lack of adaptation of the method to different configuration of treatment processes[11][12]. Torregrossa et al. [13] worked on energy cost modeling using machine learning techniques, they compared different models (linear-exponential-logarithmic models) with Neural network and random forest models using a database of 317 WWTP using conventional activated sludge process situated in the north-west of Europe, they showed that the performances indicators of the machine learning cost models (MLCM) surpass those found in the literature. This indicates the power of machine learning techniques to model energy consumption of WWTP[8].

Longo et al. [14] reviewed many techniques of benchmarking of energy consumption using Key Performance Indicator (KPI) calculated with data easily measurable by most of WWTP. Three different approaches were described, Normalized approach, Statistical approach and Programming techniques using Data envelopment analysis. In any case, the various benchmarking methods applied so far are mainly diagnostic tools that fail at prescribing any improvement strategy to make inefficient WWTPs efficient [14].

To overcome this issue, This paper proposes a methodology of selection best experiences of energy consumption based on different KPIs calculated using data usually measured in WWTP at daily time-step, and optimize energy consumption using a Deep neural network trained with the data selected. The key benefit of this method is that it can be used on several WWTP as a diagnostic tool or to predict the daily energy consumption of the WWTP.

Section snippets

First selection

The first selection aims to detect data with values of effluent quality that are near the design values corresponding to environmental standards. To minimize the complexity of the multiple variables used in the study that can make difficult the modeling and the selection of the best experiences, we used Key Performance Indicators (KPIs).To measure the efficiency of the WWTP to treat the pollution of the influent we used Treatment Yield described as :Ti=1XieXii

  • Xie : Concentration of the i-th

Description of WWTP

The WWTP is situated in Boumerdes in Algeria and was designed to treat urban sewage using a conventional activated sludge process. First, the arrival of sewage into the storm basin, a portion of the effluent is pumped directly into the pre-treatment of the channel to extract maximum suspended solids [22]. The pretreated water is directed to 3 aeration basins that are mixed with aerated biomass and kept in suspension, each basin comprises 3 aerators [22]. We get mixed liquor composed of

Conclusions

The purpose of the current study was to determine a method using DNN in order to create an optimal model of energy consumption. The results of this study support the idea that we can optimize energy consumption by using the data previously measured on the WWTP. We have been able to optimize the values of energy consumption by creating a model using Deep Neural Network coupled with a procedure of selection using different KPI. This model was applied to the data judged nonoptimal and resulted in

References (27)

  • E. Means

    Water and wastewater industry energy efficiency: a research roadmap

    Awwa Res. Found.

    (2004)
  • F. Liu et al.

    A primer on energy efficiency for municipal water and wastewater utilities

    Energy Sect. Manag. Assist. Progr. (ESMAP)

    (2012)
  • D. Mamais et al.

    Wastewater treatment process impact on energy savings and greenhouse gas emissions

    Water Sci. Technol.

    (Jan 2015)
  • Cited by (0)

    View full text