Data-driven predictive energy optimization in a wastewater pumping station

Abstract

Urban wastewater sector is being pushed to optimize processes in order to reduce energy consumption without compromising its quality standards. Energy costs can represent a significant share of the global operational costs (between 50% and 60%) in an intensive energy consumer. Pumping is the largest consumer of electrical energy in a wastewater treatment plant. Thus, the optimal control of pump units can help the utilities to decrease operational costs. This work describes an innovative predictive control policy for wastewater variable-frequency pumps that minimize electrical energy consumption, considering uncertainty forecasts for wastewater intake rate and information collected by sensors accessible through the Supervisory Control and Data Acquisition system. The proposed control method combines statistical learning (regression and predictive models) and deep reinforcement learning (Proximal Policy Optimization). The following main original contributions are produced: i) model-free and data-driven predictive control;ii) control philosophy focused on operating the tank with a variable wastewater setpoint level; iii) use of supervised learning to generate synthetic data for pre-training the reinforcement learning policy, without the need to physically interact with the system.The results for a real case-study during 90 days show a 16.7% decrease in electrical energy consumption while still achieving a 97% reduction in the number of alarms (tank level above 7.2 meters) when compared with the current operating scenario (operating with a fixed set-point level). The numerical analysis showed that the proposed data-driven method is able to explore the trade-off between number of alarms and consumption minimization, offering different options to decision-makers.

Deep Reinforcement Learning-Based Smart Joint Control Scheme for On/Off Pumping Systems in Wastewater Treatment Plants

“…Many researchers have proposed methods for reducing energy consumption, cost, or both in the pumping system, including WWTPs and water supply system. These were entirely focused on scheduling the operation of pumps considering long-term flexibility [7]. To efficiently schedule the operation of pumps, the proper combination of pumps should be chosen for each time interval.…”

“…The agent reduced energy costs of the manufacturing process with efficient manufacturing schedule through DR. RL-based scheduling frameworks have been applied to not only manufacturing processes but also various plants, such as vinyl acetate monomer plant, circulating fluidized bed plant, coal-fired power plant, nuclear power plant and WWTP [19]- [24]. In particular, Filipe et al proposed a RL-based control framework for variablefrequency pumps in a WWTP [7]. The framework consists of a predictive model and a DRL method.…”

“…fixed-speed pumps) or variable-frequency pumps (i.e. variable-speed pumps), and the existing DRLbased data-driven control approach was proposed only for variable-frequency pumps [7]. This cannot be directly applied to on/off pumping systems because there are several different constraints (e.g.…”

Wastewater Treatment Plant: Modelling and Validation of an Activated Sludge Process

“…The majority of Countries implemented several actions to avoid the disposal of wastes and wastewater without treatment in land and water bodies, since it determines harmful effects on the health of environment, humans and animals [1]. Conventional wastewater treatment plants are extremely intensive energy consumers [2], since their processes require large amounts of electrical and thermal energy. Data from Germany as well as from Italy show that electricity demand for wastewater treatment accounts for about 1% of total consumption of the country [3].…”

Multi-period Quadratic Programming Model for Sewon-Bantul Facultative Ponds Optimization

“…Some advance researches were conducted to develop new approaches for wastewater treatment model using specific methods such as statistical analysis approaches [9], distillation column model approach [10], phosphorus content analysis [11], physio-chemical & micro-biological [12], oxygen electrode & biological approach [13], organism & organic matter analysis [14], quadratic programming approach [15], a multi-objective particle swarm optimization for conjunctive use of treated wastewater & groundwater [16], fenton oxidation process optimization [17], data-driven in pumping station [18], WEST software approach for solid retention time optimization [19], integrated wastewater treatment for multiple input configurations, reuse, & disposal options [20], electrochemical oxidation for saline wastewater treatment [21], and wastewater treatment optimization using moving bed biofilm reactor method [22]. Furthermore, some articles in the literature were published on the utilization of wastewater residual, such as, for brick making [23], recycling [24], sludge for biodiesel [25], microbial fuel cells for power generation [26], etc.…”