Comparing the Performance of FSL and Traditional Operation Methods for On-Request Water Delivery in the Aghili Network, Iran

Savari, Hajar; Monem, M J; Shahverdi, Kazem

doi:10.1061/(asce)ir.1943-4774.0001089

Cited by 17 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 4(c) shows that for EFSL with an FST of 0.4, water depth variations were completely inside ±5% dead bands over 24 h. In the case of FSL, water depth recedes by a margin of −10%. The MAE is about 11%; however, it is still within a margin of ±20% which is consistent with the results reported in the literature (Savari et al, 2016; Shahverdi et al, 2016). According to Figure 4, in all cases except for EFSL with FST 0.2, water depth variations fall within a margin of ±20%.…”

Section: Resultssupporting

confidence: 92%

Irrigation canal control using enhanced fuzzy SARSA learning

Shahverdi

Monem

2022

Irrigation and Drainage

View full text Add to dashboard Cite

Fuzzy SARSA learning (FSL) is a robust reinforcement learning (RL) technique that represents successful solutions in various industrial problems. Water management in irrigation canals is one of these problems where an FSL agent interacts with the canal environment to control the gates. FSL often requires a large number of interactive experiences and takes a long time in real‐life problems. To reduce the iteration and speed up the learning process, an enhanced FSL (EFSL) was developed to accelerate the process of policy learning. A MATLAB program was written, and combined with the irrigation canal conveyance system simulation (ICSS) model. To evaluate the proposed idea, the E1R1 Dez canal, located in the south‐west of Iran, was considered as a case study. Standard performance indicators were used for assessing the results based on considered water delivery scenarios, showing a shorter learning time with reasonable performance in controlling water depth changes within the canal.

show abstract

Section: Resultssupporting

confidence: 92%

Irrigation canal control using enhanced fuzzy SARSA learning

Shahverdi

Monem

2022

Irrigation and Drainage

View full text Add to dashboard Cite

show abstract

“…The lower these indicators, the better the performance. Moreover, performance results show improvements with respect to other methods, e.g., the maximum deviations from the defined ±10% dead-band is 10%, much below the 42% reported in [17]. Therefore, the water level does not leave the dead band, and performance is acceptable.…”

Section: Resultsmentioning

confidence: 81%

“…The dead band is a margin around target depth within which water depth must be established. A dead band of ± 10% was used in this study based on previous studies [17]. Therefore, check structures are adjusted to control water depth within the dead band, and turnouts are adjusted to deliver water accurately.…”

Section: Studied Canalmentioning

confidence: 99%

Generalizing Fuzzy SARSA Learning for Real-Time Operation of Irrigation Canals

Shahverdi

Maestre

Alamiyan-Harandi

et al. 2020

Water

View full text Add to dashboard Cite

Recently, a continuous reinforcement learning model called fuzzy SARSA (state, action, reward, state, action) learning (FSL) was proposed for irrigation canals. The main problem related to FSL is its convergence and generalization in environments with many variables such as large irrigation canals and situations beyond training. Furthermore, due to its architecture, FSL may require high computation demands during its learning process. To deal with these issues, this work proposes a computationally lighter generalizing learned Q-function (GLQ) model, which benefits from the FSL-learned Q-function, to provide operators with a faster and simpler mechanism to obtain operational instructions. The proposed approach is tested for different water requests in the East Aghili Canal, located in the southwest of Iran. Several performance indicators are used for evaluating the GLQ model results, showing convergence in all the investigated cases and the ability to estimate operational instructions (actions) in situations beyond training, delivering water with high accuracy regarding several performance indicators. Hence, the use of the GLQ model is recommended for determining the operational patterns in irrigation canals.

show abstract

“…A performance evaluation study was carried out by considering FSL method and Conventional Operation Methods for Water Delivery On-Request in the Aghili Network, Iran by taking same canal. According to results both methods were acceptable in terms of capability showing an efficiency of greater than 90 % and the maximum water depth variation was less than 10%, but FSL method gave more promising results and was able to distribute the water more uniformly in water shortage conditions [9].…”

Section: Introduction Conomy Of Pakistan Is Based On Agriculturesmentioning

confidence: 93%

Remodelling and Rehabilitation of Irrigation Outlets in Water Distribution of Canals in Punjab, Pakistan

Ahmed¹,

Hashimi²,

Sheikh³

et al. 2022

murjet

View full text Add to dashboard Cite

This paper highlights the problems associated with the outlets in the irrigation system of Pakistan, leading to the design of outlets, to trace the gradual evolution of various outlets types and to describe most of the types that have been evolved so far. The advantages and limitations of each type have been examined critically so that the selection of a type for any particular set of conditions may be rendered easy. An outlet is a flow measuring and controlling device between farmer’s land and an irrigation system. In Punjab about fifty thousand outlets irrigate an area of approximately 25.5 million acres annually. Improperly designed outlets may cause a number of problems such as variation in their coefficients of discharge, inequitable distribution of water, silting of canals, inadequate availability water at the lowest outlets, lack of incentives for saving of water and poor drainage. Field calibration of the irrigation outlets proved that their calibrated Cd. vary from the designed Cd. (0.6 for OF & 0.9 for AOSM), as outlets were not designed according to their designed parameters. Defective outlets were also the main cause of silting in canals. The pipe-cum-semi module was very helpful to draw silt from the bed of the parent channel in a case if we want a higher setting of outlet. 20% of canal water in Rabi season and 40% water in Kharif season were snatched by illegally Theft problem. In order to prevent theft, the outlets should be tamper proof and the irrigation department should adopt the legal procedure strictly. All over the world, the engineers and farmers designed and installed various kinds of farm outlets suiting their local conditions. Work is being carried out to make them structurally, hydraulically and economically fit. An attempt is made to bring all the information together leading to economical and efficient design of outlets and to look upon their possibility of adaptability in Pakistan.

show abstract

Comparing the Performance of FSL and Traditional Operation Methods for On-Request Water Delivery in the Aghili Network, Iran

Cited by 17 publications

References 11 publications

Irrigation canal control using enhanced fuzzy SARSA learning

Irrigation canal control using enhanced fuzzy SARSA learning

Generalizing Fuzzy SARSA Learning for Real-Time Operation of Irrigation Canals

Remodelling and Rehabilitation of Irrigation Outlets in Water Distribution of Canals in Punjab, Pakistan

Contact Info

Product

Resources

About